@skills · Owner

Agent skills by yonatangross

261 skills indexed from github.com/yonatangross. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.

accessibility · Skill · 215 stars
Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy
accessibility · Skill · 215 stars
Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy
agent-orchestration · Skill · 215 stars
Agent orchestration patterns for agentic loops, multi-agent coordination, alternative frameworks, and multi-scenario workflows. Use when building autonomou
agent-orchestration · Skill · 215 stars
Agent orchestration patterns for agentic loops, multi-agent coordination, alternative frameworks, and multi-scenario workflows. Use when building autonomou
ai-ui-generation · Skill · 215 stars
AI-assisted UI generation patterns for json-render, v0.app, Google Stitch, Bolt Cloud, and Cursor workflows. Covers prompt engineering for component and fu
ai-ui-generation · Skill · 215 stars
AI-assisted UI generation patterns for json-render, v0.app, Google Stitch, Bolt Cloud, and Cursor workflows. Covers prompt engineering for component and fu
analytics · Skill · 215 stars
Local OrchestKit usage analytics: agent and skill frequency, hook timing, session replay, cost estimates, model delegation trends. Use when reviewing usage
analytics · Skill · 215 stars
Local OrchestKit usage analytics: agent and skill frequency, hook timing, session replay, cost estimates, model delegation trends. Use when reviewing usage
animation-motion-design · Skill · 215 stars
Animation and motion design patterns using Motion library (formerly Framer Motion) and View Transitions API. Use when implementing component animations, pa
animation-motion-design · Skill · 215 stars
Animation and motion design patterns using Motion library (formerly Framer Motion) and View Transitions API. Use when implementing component animations, pa
api-design · Skill · 215 stars
API wire contracts for REST and GraphQL: resource shape, versioning and deprecation, RFC 9457 errors, OpenAPI. Use when designing an endpoint contract. Not
api-design · Skill · 215 stars
API wire contracts for REST and GraphQL: resource shape, versioning and deprecation, RFC 9457 errors, OpenAPI. Use when designing an endpoint contract. Not
architecture-decision-record · Skill · 215 stars
Nygard-format ADRs: context, decision, consequences, alternatives. Use when writing an ADR or recording an architectural decision.
architecture-decision-record · Skill · 215 stars
Nygard-format ADRs: context, decision, consequences, alternatives. Use when writing an ADR or recording an architectural decision.
architecture-patterns · Skill · 215 stars
Clean and layered architecture patterns, project structure and test-standard validation. Use when designing system boundaries or enforcing structure. For t
architecture-patterns · Skill · 215 stars
Clean and layered architecture patterns, project structure and test-standard validation. Use when designing system boundaries or enforcing structure. For t
assess · Skill · 215 stars
Rates code, designs or approaches 0-10 across quality dimensions with pros, cons and fixes. Use when evaluating or comparing options. Not for fixing or bui
assess · Skill · 215 stars
Rates code, designs or approaches 0-10 across quality dimensions with pros, cons and fixes. Use when evaluating or comparing options. Not for fixing or bui
async-jobs · Skill · 215 stars
Async job processing patterns for background tasks, Celery workflows, task scheduling, retry strategies, and distributed task execution. Use when implement
async-jobs · Skill · 215 stars
Async job processing patterns for background tasks, Celery workflows, task scheduling, retry strategies, and distributed task execution. Use when implement
audit-activation · Skill · 215 stars
Audits sub-agent activation from telemetry: attempted, started, completed, unattributed spawns, and zero-start agents. Use when agents feel under-used or b
audit-activation · Skill · 215 stars
Audits sub-agent activation from telemetry: attempted, started, completed, unattributed spawns, and zero-start agents. Use when agents feel under-used or b
audit-full · Skill · 215 stars
Whole-codebase audit in one 1M-token pass: security, architecture and dependencies with severity-ranked findings. Use before a release or security review.
audit-full · Skill · 215 stars
Whole-codebase audit in one 1M-token pass: security, architecture and dependencies with severity-ranked findings. Use before a release or security review.
auto · Skill · 215 stars
Default front door for goal-shaped requests: classifies a plain-English goal and routes it to the right skill. Use for do this, figure out, I want, help me
auto · Skill · 215 stars
Default front door for goal-shaped requests: classifies a plain-English goal and routes it to the right skill. Use for do this, figure out, I want, help me
bare-eval · Skill · 215 stars
Isolated eval and grading calls with claude -p in bare mode, free of plugin and hook interference. Use when grading skill outputs, benchmarking prompts or
bare-eval · Skill · 215 stars
Isolated eval and grading calls with claude -p in bare mode, free of plugin and hook interference. Use when grading skill outputs, benchmarking prompts or
brainstorm · Skill · 215 stars
Design ideation with parallel agents: 10+ ideas, feasibility filter, devil's-advocate scoring, trade-offs. Use when brainstorming or comparing alternatives
brainstorm · Skill · 215 stars
Design ideation with parallel agents: 10+ ideas, feasibility filter, devil's-advocate scoring, trade-offs. Use when brainstorming or comparing alternatives
browser-tools · Skill · 215 stars
Safety rules over the upstream agent-browser skill: scraping ethics, auth, request pacing, local URLs. Use for browser automation.
browser-tools · Skill · 215 stars
Safety rules over the upstream agent-browser skill: scraping ethics, auth, request pacing, local URLs. Use for browser automation.
business-case · Skill · 215 stars
ROI, NPV, IRR, payback and TCO for investment decisions. Use when building a financial justification, cost-benefit or build-vs-buy analysis.
business-case · Skill · 215 stars
ROI, NPV, IRR, payback and TCO for investment decisions. Use when building a financial justification, cost-benefit or build-vs-buy analysis.
chain-patterns · Skill · 215 stars
Multi-phase pipeline patterns: MCP detection, handoff files, checkpoint-resume, worktree agents, cron monitoring. Use when building or debugging a pipeline
chain-patterns · Skill · 215 stars
Multi-phase pipeline patterns: MCP detection, handoff files, checkpoint-resume, worktree agents, cron monitoring. Use when building or debugging a pipeline
ci-debug · Skill · 215 stars
Diagnoses one failing CI run or PR check against an 11-pattern playbook and proposes the exact fix, never applying it unasked. Use when a GitHub Actions jo
ci-debug · Skill · 215 stars
Diagnoses one failing CI run or PR check against an 11-pattern playbook and proposes the exact fix, never applying it unasked. Use when a GitHub Actions jo
ci-sentinel · Skill · 215 stars
Daily headless classifier for every open PR with red required checks: runs ci-debug, posts a collapsed verdict comment, logs a ledger. Proposes only, never
ci-sentinel · Skill · 215 stars
Daily headless classifier for every open PR with red required checks: runs ci-debug, posts a collapsed verdict comment, logs a ledger. Proposes only, never
code-review-playbook · Skill · 215 stars
Review process, conventional comments, language checklists and feedback templates. Use when reviewing code or standardizing review practice. To review a PR
code-review-playbook · Skill · 215 stars
Review process, conventional comments, language checklists and feedback templates. Use when reviewing code or standardizing review practice. To review a PR
codex · Collection · 215 stars
commit · Skill · 215 stars
Creates Conventional Commits with scope detection, co-author lines and hook compliance; blocks secrets and generated-only files. Use when asked to commit,
commit · Skill · 215 stars
Creates Conventional Commits with scope detection, co-author lines and hook compliance; blocks secrets and generated-only files. Use when asked to commit,
competitive-analysis · Skill · 215 stars
Porter's Five Forces, SWOT, competitor profiles, feature gaps and battlecards. Use when analyzing market position or building sales battlecards.
competitive-analysis · Skill · 215 stars
Porter's Five Forces, SWOT, competitor profiles, feature gaps and battlecards. Use when analyzing market position or building sales battlecards.
component-search · Skill · 215 stars
Searches the 21st.dev registry for production React components, ranked with install steps. Use when looking for a UI component or an alternative to one.
component-search · Skill · 215 stars
Searches the 21st.dev registry for production React components, ranked with install steps. Use when looking for a UI component or an alternative to one.
configure · Skill · 215 stars
Interactive wizard for OrchestKit settings: MCP servers, hook permissions, keybindings, presets. Use when customizing plugin behavior.
configure · Skill · 215 stars
Interactive wizard for OrchestKit settings: MCP servers, hook permissions, keybindings, presets. Use when customizing plugin behavior.
cover · Skill · 215 stars
Writes tests that do not exist yet across unit, integration and end-to-end tiers, healing failures up to 3 times. Use when code lacks tests. Not for gradin
cover · Skill · 215 stars
Writes tests that do not exist yet across unit, integration and end-to-end tiers, healing failures up to 3 times. Use when code lacks tests. Not for gradin
create-pr · Skill · 215 stars
Opens a GitHub PR after pre-flight checks (tests, lint, types, security) with a conventional title and summary. Use only when asked for this skill; an ever
create-pr · Skill · 215 stars
Opens a GitHub PR after pre-flight checks (tests, lint, types, security) with a conventional title and summary. Use only when asked for this skill; an ever
database-patterns · Skill · 215 stars
Schema design, Alembic migrations and database versioning. Use when creating migrations, designing or normalizing schemas, or fixing schema drift.
database-patterns · Skill · 215 stars
Schema design, Alembic migrations and database versioning. Use when creating migrations, designing or normalizing schemas, or fixing schema drift.
demo-producer · Skill · 215 stars
Demo videos for skills, plugins, CLIs and code walkthroughs: scripts, storyboards, VHS terminal recordings, Remotion. Use when producing a showcase or mark
demo-producer · Skill · 215 stars
Demo videos for skills, plugins, CLIs and code walkthroughs: scripts, storyboards, VHS terminal recordings, Remotion. Use when producing a showcase or mark
design-context-extract · Skill · 215 stars
Extracts design DNA from screenshots, URLs or recordings: colors, type, spacing, components and motion as tokens or Tailwind config. Use when asked to extr
design-context-extract · Skill · 215 stars
Extracts design DNA from screenshots, URLs or recordings: colors, type, spacing, components and motion as tokens or Tailwind config. Use when asked to extr
design-import · Skill · 215 stars
Scaffolds React components from a Claude Design bundle and stops at files on disk. Use when handed a claude.ai/design URL or bundle. For a full PR with tes
design-import · Skill · 215 stars
Scaffolds React components from a Claude Design bundle and stops at files on disk. Use when handed a claude.ai/design URL or bundle. For a full PR with tes
design-ship · Skill · 215 stars
Turns a claude.ai/design link into a PR: design-import, then cover, then expect, then open the PR. Use when a design should come back as a PR. For files on
design-ship · Skill · 215 stars
Turns a claude.ai/design link into a PR: design-import, then cover, then expect, then open the PR. Use when a design should come back as a PR. For files on
design-stylecards · Skill · 215 stars
Catalog of named aesthetic recipes: shadow stacks, glass, gradients, type scales as copy-paste values. Use for polished elevation, glassmorphism, mesh back
design-stylecards · Skill · 215 stars
Catalog of named aesthetic recipes: shadow stacks, glass, gradients, type scales as copy-paste values. Use for polished elevation, glassmorphism, mesh back
design-system-tokens · Skill · 215 stars
W3C design tokens: global, alias and component tiers, OKLCH color, Style Dictionary, dark mode. Use when creating token files or theme systems.
design-system-tokens · Skill · 215 stars
W3C design tokens: global, alias and component tiers, OKLCH color, Style Dictionary, dark mode. Use when creating token files or theme systems.
design-to-code · Skill · 215 stars
Mockup to React component via Stitch, 21st.dev and Storybook MCP, reusing existing components first. Use when building UI from a mockup or screenshot. To c
design-to-code · Skill · 215 stars
Mockup to React component via Stitch, 21st.dev and Storybook MCP, reusing existing components first. Use when building UI from a mockup or screenshot. To c
dev · Skill · 215 stars
One-command dev loop: portless HTTPS subdomain, emulate API mocks, dev server and an agent-browser session keyed to the git branch. Use when starting a bra
dev · Skill · 215 stars
One-command dev loop: portless HTTPS subdomain, emulate API mocks, dev server and an agent-browser session keyed to the git branch. Use when starting a bra
devops-deployment · Skill · 215 stars
CI/CD, containers and infrastructure as code: GitHub Actions, Docker, Kubernetes, Helm, Terraform. Use when setting up pipelines or deployments.
devops-deployment · Skill · 215 stars
CI/CD, containers and infrastructure as code: GitHub Actions, Docker, Kubernetes, Helm, Terraform. Use when setting up pipelines or deployments.
distributed-systems · Skill · 215 stars
Distributed systems patterns for locking, resilience, idempotency, and rate limiting. Use when implementing distributed locks, circuit breakers, retry poli
distributed-systems · Skill · 215 stars
Distributed systems patterns for locking, resilience, idempotency, and rate limiting. Use when implementing distributed locks, circuit breakers, retry poli
doctor · Skill · 215 stars
Diagnoses OrchestKit and project health: manifests, hooks, skills, agents, MCP servers, CC version and permissions, with severity and remedies. Use to run
doctor · Skill · 215 stars
Diagnoses OrchestKit and project health: manifests, hooks, skills, agents, MCP servers, CC version and permissions, with severity and remedies. Use to run
documentation-patterns · Skill · 215 stars
Technical documentation patterns for READMEs, ADRs, API docs (OpenAPI 3.1), changelogs, and writing style guides. Use when creating project documentation,
documentation-patterns · Skill · 215 stars
Technical documentation patterns for READMEs, ADRs, API docs (OpenAPI 3.1), changelogs, and writing style guides. Use when creating project documentation,
domain-driven-design · Skill · 215 stars
DDD tactical patterns for complex business modeling including entities, value objects, aggregates, domain services, repositories, specifications, and bound
domain-driven-design · Skill · 215 stars
DDD tactical patterns for complex business modeling including entities, value objects, aggregates, domain services, repositories, specifications, and bound
dream · Skill · 215 stars
Nightly memory consolidation: prunes stale entries, merges duplicates, resolves contradictions, rebuilds MEMORY.md. Use when memory needs cleanup. To store
dream · Skill · 215 stars
Nightly memory consolidation: prunes stale entries, merges duplicates, resolves contradictions, rebuilds MEMORY.md. Use when memory needs cleanup. To store
emulate-seed · Skill · 215 stars
Seed configs for Vercel emulate: stateful GitHub, Vercel, Google, Slack, Stripe, AWS and more, not mocks. Use when setting up test environments, CI or offl
emulate-seed · Skill · 215 stars
Seed configs for Vercel emulate: stateful GitHub, Vercel, Google, Slack, Stripe, AWS and more, not mocks. Use when setting up test environments, CI or offl
errors · Skill · 215 stars
Claude Code session error triage: categorizes network, auth, model, tool and permission errors, finds prior occurrences, suggests recovery. Use when a sess
errors · Skill · 215 stars
Claude Code session error triage: categorizes network, auth, model, tool and permission errors, finds prior occurrences, suggests recovery. Use when a sess
expect · Skill · 215 stars
Diff-aware browser testing: maps the git diff to affected pages, plans and runs targeted checks via agent-browser. Use when testing UI changes before merge
expect · Skill · 215 stars
Diff-aware browser testing: maps the git diff to affected pages, plans and runs targeted checks via agent-browser. Use when testing UI changes before merge
explore · Skill · 215 stars
Multi-angle codebase exploration by parallel agents: structure, data flow, architecture, health. Use to map an unfamiliar repo. NOT for task research files
explore · Skill · 215 stars
Multi-angle codebase exploration by parallel agents: structure, data flow, architecture, health. Use to map an unfamiliar repo. NOT for task research files
figma-design-handoff · Skill · 215 stars
Figma-to-code design handoff patterns including Figma Variables to design tokens pipeline, component spec extraction, Dev Mode inspection, Auto Layout to C
figma-design-handoff · Skill · 215 stars
Figma-to-code design handoff patterns including Figma Variables to design tokens pipeline, component spec extraction, Dev Mode inspection, Auto Layout to C
fix-issue · Skill · 215 stars
Fixes a GitHub issue: parallel root-cause analysis, a fix with tests, a PR linked back to the issue, and prevention notes. Use when fixing a bug, regressio
fix-issue · Skill · 215 stars
Fixes a GitHub issue: parallel root-cause analysis, a fix with tests, a PR linked back to the issue, and prevention notes. Use when fixing a bug, regressio
github-operations · Skill · 215 stars
gh CLI and REST patterns for issues, PRs, milestones and Projects v2. Use when managing GitHub issues, PRs or projects.
github-operations · Skill · 215 stars
gh CLI and REST patterns for issues, PRs, milestones and Projects v2. Use when managing GitHub issues, PRs or projects.
golden-dataset · Skill · 215 stars
Golden dataset lifecycle patterns for curation, versioning, quality validation, and CI integration. Use when building evaluation datasets, managing dataset
golden-dataset · Skill · 215 stars
Golden dataset lifecycle patterns for curation, versioning, quality validation, and CI integration. Use when building evaluation datasets, managing dataset
help · Skill · 215 stars
OrchestKit skill directory by category. Use when looking for the right skill or workflow.
help · Skill · 215 stars
OrchestKit skill directory by category. Use when looking for the right skill or workflow.
i18n-date-patterns · Skill · 215 stars
Implements internationalization (i18n) in React applications. Covers user-facing strings, date/time handling, locale-aware formatting, ICU MessageFormat, a
i18n-date-patterns · Skill · 215 stars
Implements internationalization (i18n) in React applications. Covers user-facing strings, date/time handling, locale-aware formatting, ICU MessageFormat, a
implement · Skill · 215 stars
Builds a new feature with parallel backend, frontend, test and security agents in worktrees, then verifies. Use when asked to build, add or scaffold a feat
implement · Skill · 215 stars
Builds a new feature with parallel backend, frontend, test and security agents in worktrees, then verifies. Use when asked to build, add or scaffold a feat
interaction-patterns · Skill · 215 stars
UI interaction design patterns for skeleton loading, infinite scroll with accessibility, progressive disclosure, modal/drawer/inline selection, drag-and-dr
interaction-patterns · Skill · 215 stars
UI interaction design patterns for skeleton loading, infinite scroll with accessibility, progressive disclosure, modal/drawer/inline selection, drag-and-dr
issue-progress-tracking · Skill · 215 stars
GitHub issue workflow ceremony using gh CLI — labels issues as in-progress, creates feature branches (issue/N-description), commits with issue references,
issue-progress-tracking · Skill · 215 stars
GitHub issue workflow ceremony using gh CLI — labels issues as in-progress, creates feature branches (issue/N-description), commits with issue references,
json-render-catalog · Skill · 215 stars
json-render catalogs for AI-safe generative UI: Zod-typed components, @json-render/shadcn, YAML specs, patch/merge/diff edits. Use when defining component
json-render-catalog · Skill · 215 stars
json-render catalogs for AI-safe generative UI: Zod-typed components, @json-render/shadcn, YAML specs, patch/merge/diff edits. Use when defining component
langgraph · Skill · 215 stars
LangGraph 1.x (LTS) Python workflow patterns for state management, delta channels, resilience (node timeouts, error handlers, graceful drain), routing, par
langgraph · Skill · 215 stars
LangGraph 1.x (LTS) Python workflow patterns for state management, delta channels, resilience (node timeouts, error handlers, graceful drain), routing, par
llm-integration · Skill · 215 stars
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool
llm-integration · Skill · 215 stars
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool
market-sizing · Skill · 215 stars
TAM, SAM and SOM with top-down and bottom-up estimates and cross-checked assumptions. Use when sizing a market or preparing pitch market slides.
market-sizing · Skill · 215 stars
TAM, SAM and SOM with top-down and bottom-up estimates and cross-checked assumptions. Use when sizing a market or preparing pitch market slides.
mcp-patterns · Skill · 215 stars
MCP server building, advanced patterns, and security hardening. Use when building MCP servers, implementing tool handlers, choosing a transport, adding OAu
mcp-patterns · Skill · 215 stars
MCP server building, advanced patterns, and security hardening. Use when building MCP servers, implementing tool handlers, choosing a transport, adding OAu
mcp-visual-output · Skill · 215 stars
Upgrades MCP tool JSON results to dashboards via @json-render/mcp (stat grids, tables, badges) in MCP clients. Use when a tool result reads better visually
mcp-visual-output · Skill · 215 stars
Upgrades MCP tool JSON results to dashboards via @json-render/mcp (stat grids, tables, badges) in MCP clients. Use when a tool result reads better visually
memory · Skill · 215 stars
Read-side memory: search past decisions, load context, timelines and graph views. Use when finding what memory holds. To store use remember; to clean up us
memory · Skill · 215 stars
Read-side memory: search past decisions, load context, timelines and graph views. Use when finding what memory holds. To store use remember; to clean up us
memory-fabric · Skill · 215 stars
Memory retrieval internals: knowledge graph orchestration with entity extraction, natural language query parsing, deduplication (>85% similarity), and cros
memory-fabric · Skill · 215 stars
Memory retrieval internals: knowledge graph orchestration with entity extraction, natural language query parsing, deduplication (>85% similarity), and cros
monitoring-observability · Skill · 215 stars
Monitoring and observability patterns for Prometheus metrics, Grafana dashboards, Langfuse v4 LLM tracing (as_type, score_current_span, should_export_span,
monitoring-observability · Skill · 215 stars
Monitoring and observability patterns for Prometheus metrics, Grafana dashboards, Langfuse v4 LLM tracing (as_type, score_current_span, should_export_span,
multi-surface-render · Skill · 215 stars
One json-render spec to many targets: React, Next.js, React Native, Ink, PDF, email, Remotion, OG images, 3D. Use when one component spec must render on se
multi-surface-render · Skill · 215 stars
One json-render spec to many targets: React, Next.js, React Native, Ink, PDF, email, Remotion, OG images, 3D. Use when one component spec must render on se
multimodal-llm · Skill · 215 stars
Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI
multimodal-llm · Skill · 215 stars
Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI
okr-design · Skill · 215 stars
OKR trees, KPIs, North Star metric, leading and lagging indicators, experiment guardrails. Use when setting goals or success metrics.
okr-design · Skill · 215 stars
OKR trees, KPIs, North Star metric, leading and lagging indicators, experiment guardrails. Use when setting goals or success metrics.
orchestkit · Collection · 215 stars
ork · Collection · 215 stars
ork-assess · Skill · 215 stars
Assess a code change, design, architecture, workflow, or competing options against explicit criteria and evidence. Use when a request asks to assess, rate,
ork-assess · Skill · 215 stars
Assess a code change, design, architecture, workflow, or competing options against explicit criteria and evidence. Use when a request asks to assess, rate,
ork-brainstorm · Skill · 215 stars
Compare plausible implementation, architecture, product, or operational approaches before committing to one. Use when a request asks to brainstorm, think t
ork-brainstorm · Skill · 215 stars
Compare plausible implementation, architecture, product, or operational approaches before committing to one. Use when a request asks to brainstorm, think t
ork-codex · Collection · 215 stars
ork-codex · Collection · 215 stars
ork-explore · Skill · 215 stars
Map an unfamiliar codebase, feature, architecture, data flow, or operational path with file-backed evidence. Use when a request asks how a system works, wh
ork-explore · Skill · 215 stars
Map an unfamiliar codebase, feature, architecture, data flow, or operational path with file-backed evidence. Use when a request asks how a system works, wh
ork-review-pr · Skill · 215 stars
Review a pull request or branch for correctness, regressions, security, operational risk, and missing evidence. Use when a request asks to review a PR, rev
ork-review-pr · Skill · 215 stars
Review a pull request or branch for correctness, regressions, security, operational risk, and missing evidence. Use when a request asks to review a PR, rev
ork-verify · Skill · 215 stars
Verify that existing work is ready to merge, release, or hand off using an explicit evidence contract. Use when a request asks to verify, validate, prove,
ork-verify · Skill · 215 stars
Verify that existing work is ready to merge, release, or hand off using an explicit evidence contract. Use when a request asks to verify, validate, prove,
performance · Skill · 215 stars
Performance patterns: Core Web Vitals, React renders, lazy loading, images, backend profiling, LLM inference. Use when improving page speed, slow renders,
performance · Skill · 215 stars
Performance patterns: Core Web Vitals, React renders, lazy loading, images, backend profiling, LLM inference. Use when improving page speed, slow renders,
plugins · Collection · 215 stars
portless · Skill · 215 stars
Named HTTPS .localhost URLs with portless (v0.15.x): no port collisions, branch subdomains for worktrees, LAN and Tailscale sharing. Use for local dev URLs
portless · Skill · 215 stars
Named HTTPS .localhost URLs with portless (v0.15.x): no port collisions, branch subdomains for worktrees, LAN and Tailscale sharing. Use for local dev URLs
prd-to-goal · Skill · 215 stars
Turns a PRD, issue or spec into one copy-paste /goal line of AND-joined boolean checks. Use when running /goal against a spec.
prd-to-goal · Skill · 215 stars
Turns a PRD, issue or spec into one copy-paste /goal line of AND-joined boolean checks. Use when running /goal against a spec.
prioritization · Skill · 215 stars
RICE, WSJF, ICE, MoSCoW and opportunity-cost scoring. Use when ranking a backlog or justifying roadmap trade-offs.
prioritization · Skill · 215 stars
RICE, WSJF, ICE, MoSCoW and opportunity-cost scoring. Use when ranking a backlog or justifying roadmap trade-offs.
product-analytics · Skill · 215 stars
A/B test evaluation, cohort retention, funnels and significance. Use when analyzing experiments, feature adoption or conversion drop-offs.
product-analytics · Skill · 215 stars
A/B test evaluation, cohort retention, funnels and significance. Use when analyzing experiments, feature adoption or conversion drop-offs.
product-frameworks · Skill · 215 stars
Product management frameworks for business cases, market analysis, strategy, prioritization, OKRs/KPIs, personas, requirements, and user research. Use when
product-frameworks · Skill · 215 stars
Product management frameworks for business cases, market analysis, strategy, prioritization, OKRs/KPIs, personas, requirements, and user research. Use when
python-backend · Skill · 215 stars
Async Python runtime patterns: asyncio TaskGroup, FastAPI dependencies and middleware, SQLAlchemy 2.0 async sessions, pool tuning. Use when building async
python-backend · Skill · 215 stars
Async Python runtime patterns: asyncio TaskGroup, FastAPI dependencies and middleware, SQLAlchemy 2.0 async sessions, pool tuning. Use when building async
quality-gates · Skill · 215 stars
Task complexity scoring (1-5), escalation when stuck, and best-practice checks. Use before complex tasks or after repeated failed attempts.
quality-gates · Skill · 215 stars
Task complexity scoring (1-5), escalation when stuck, and best-practice checks. Use before complex tasks or after repeated failed attempts.
rag-retrieval · Skill · 215 stars
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, conte
rag-retrieval · Skill · 215 stars
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, conte
react-server-components-framework · Skill · 215 stars
Next.js 16+ with React Server Components: App Router, Cache Components, streaming SSR, Server Actions. Use when building server-first Next.js apps.
react-server-components-framework · Skill · 215 stars
Next.js 16+ with React Server Components: App Router, Cache Components, streaming SSR, Server Actions. Use when building server-first Next.js apps.
release-management · Skill · 215 stars
Automates GitHub releases with semantic versioning, changelog generation from merged PRs, and gh CLI integration. Supports draft, prerelease, and standard
release-management · Skill · 215 stars
Automates GitHub releases with semantic versioning, changelog generation from merged PRs, and gh CLI integration. Supports draft, prerelease, and standard
release-sync · Skill · 215 stars
After a version tag, syncs CHANGELOG and release notes to NotebookLM and the knowledge base, optionally a podcast. Use after tagging a release.
release-sync · Skill · 215 stars
After a version tag, syncs CHANGELOG and release notes to NotebookLM and the knowledge base, optionally a podcast. Use after tagging a release.
remember · Skill · 215 stars
Write-side memory: stores decisions, patterns and outcomes in the knowledge graph. Use when something worth keeping was learned or decided. To search use m
remember · Skill · 215 stars
Write-side memory: stores decisions, patterns and outcomes in the knowledge graph. Use when something worth keeping was learned or decided. To search use m
responsive-patterns · Skill · 215 stars
Responsive design with Container Queries, fluid typography, cqi/cqb units, subgrid, intrinsic layouts, foldable devices, and mobile-first patterns for Reac
responsive-patterns · Skill · 215 stars
Responsive design with Container Queries, fluid typography, cqi/cqb units, subgrid, intrinsic layouts, foldable devices, and mobile-first patterns for Reac
review-pr · Skill · 215 stars
PR review by parallel agents (quality, security, tests, architecture, performance) with conventional comments and an approve or request-changes verdict. Us
review-pr · Skill · 215 stars
PR review by parallel agents (quality, security, tests, architecture, performance) with conventional comments and an approve or request-changes verdict. Us
scope-appropriate-architecture · Skill · 215 stars
Classifies a project into 6 tiers to right-size its architecture and prevent over-engineering. Use when choosing patterns for a project's scope.
scope-appropriate-architecture · Skill · 215 stars
Classifies a project into 6 tiers to right-size its architecture and prevent over-engineering. Use when choosing patterns for a project's scope.
security-patterns · Skill · 215 stars
Auth, defense in depth, input validation, OWASP Top 10, LLM prompt-injection defense and PII masking. Use when implementing auth or security layers.
security-patterns · Skill · 215 stars
Auth, defense in depth, input validation, OWASP Top 10, LLM prompt-injection defense and PII masking. Use when implementing auth or security layers.
setup · Skill · 215 stars
Onboarding wizard: scans the codebase and stack, recommends skills and MCP servers, scores readiness. Use when setting up OrchestKit in a project or rescan
setup · Skill · 215 stars
Onboarding wizard: scans the codebase and stack, recommends skills and MCP servers, scores readiness. Use when setting up OrchestKit in a project or rescan
skills · Collection · 215 stars
skills · Collection · 215 stars
skills · Collection · 215 stars
skills · Collection · 215 stars
src · Collection · 215 stars
storybook-mcp-integration · Skill · 215 stars
Reference for the Storybook MCP server (@storybook/addon-mcp): its tools, toolsets and availability. Use when calling those tools on existing components. T
storybook-mcp-integration · Skill · 215 stars
Reference for the Storybook MCP server (@storybook/addon-mcp): its tools, toolsets and availability. Use when calling those tools on existing components. T
storybook-testing · Skill · 215 stars
Storybook 10 testing patterns with Vitest integration, ESM-only distribution, CSF3 typesafe factories, play() interaction tests, Chromatic TurboSnap visual
storybook-testing · Skill · 215 stars
Storybook 10 testing patterns with Vitest integration, ESM-only distribution, CSF3 typesafe factories, play() interaction tests, Chromatic TurboSnap visual
swarm-migrate · Skill · 215 stars
Cross-repo migration swarm: one coordinator and a subagent per repo apply the same change, open PRs, wait for CI, and log to a shared ledger. Use for org-w
swarm-migrate · Skill · 215 stars
Cross-repo migration swarm: one coordinator and a subagent per repo apply the same change, open PRs, wait for CI, and log to a shared ledger. Use for org-w
task-dependency-patterns · Skill · 215 stars
Task Management patterns with TaskCreate, TaskUpdate, TaskGet, TaskList tools. Decompose complex work into trackable tasks with dependency chains. Use when
task-dependency-patterns · Skill · 215 stars
Task Management patterns with TaskCreate, TaskUpdate, TaskGet, TaskList tools. Decompose complex work into trackable tasks with dependency chains. Use when
telemetry-inspect · Skill · 215 stars
Read-only check of this project's OrchestKit telemetry files: write counts, sizes, schema locks, growth and orphans. Use when verifying the observability p
telemetry-inspect · Skill · 215 stars
Read-only check of this project's OrchestKit telemetry files: write counts, sizes, schema locks, growth and orphans. Use when verifying the observability p
testing-e2e · Skill · 215 stars
Playwright E2E patterns: page objects, visual regression, axe-core accessibility, CI. Use when writing E2E tests or setting up Playwright.
testing-e2e · Skill · 215 stars
Playwright E2E patterns: page objects, visual regression, axe-core accessibility, CI. Use when writing E2E tests or setting up Playwright.
testing-integration · Skill · 215 stars
Integration and contract tests: API endpoints, databases, Pact contracts, property-based tests, Zod validation. Use when testing API or service boundaries.
testing-integration · Skill · 215 stars
Integration and contract tests: API endpoints, databases, Pact contracts, property-based tests, Zod validation. Use when testing API or service boundaries.
testing-llm · Skill · 215 stars
LLM testing patterns: mocked responses, DeepEval and RAGAS evaluation, structured output checks, agentic tests. Use when testing AI features.
testing-llm · Skill · 215 stars
LLM testing patterns: mocked responses, DeepEval and RAGAS evaluation, structured output checks, agentic tests. Use when testing AI features.
testing-perf · Skill · 215 stars
Load and performance tests with k6 and Locust, plus pytest speed (xdist). Use when writing load tests or speeding up a test suite.
testing-perf · Skill · 215 stars
Load and performance tests with k6 and Locust, plus pytest speed (xdist). Use when writing load tests or speeding up a test suite.
testing-unit · Skill · 215 stars
Unit test patterns: AAA, parametrized tests, fixture scope, MSW or VCR network mocks, data factories, for Vitest, Jest and pytest. Use when writing unit te
testing-unit · Skill · 215 stars
Unit test patterns: AAA, parametrized tests, fixture scope, MSW or VCR network mocks, data factories, for Vitest, Jest and pytest. Use when writing unit te
ui-components · Skill · 215 stars
UI component library patterns for shadcn/ui and Radix Primitives. Use when building accessible component libraries, customizing shadcn components, using Ra
ui-components · Skill · 215 stars
UI component library patterns for shadcn/ui and Radix Primitives. Use when building accessible component libraries, customizing shadcn components, using Ra
user-research · Skill · 215 stars
Personas, journey maps, interview guides, usability tests, card sorting and Jobs-to-Be-Done. Use when planning user research.
user-research · Skill · 215 stars
Personas, journey maps, interview guides, usability tests, card sorting and Jobs-to-Be-Done. Use when planning user research.
verify · Skill · 215 stars
Grades work for merge: runs unit, integration and E2E suites plus security and type checks, scores 0-10 with a VERIFIED vs CLAIMED manifest. Use when decid
verify · Skill · 215 stars
Grades work for merge: runs unit, integration and E2E suites plus security and type checks, scores 0-10 with a VERIFIED vs CLAIMED manifest. Use when decid
visualize-plan · Skill · 215 stars
Renders planned changes as before/after architecture, risk heat maps, execution order and dependency graphs in ASCII, HTML or NotebookLM. Use when reviewin
visualize-plan · Skill · 215 stars
Renders planned changes as before/after architecture, risk heat maps, execution order and dependency graphs in ASCII, HTML or NotebookLM. Use when reviewin
vite-advanced · Skill · 215 stars
Advanced Vite 8 patterns including Rolldown-powered builds, advancedChunks, Environment API, plugin development, SSR configuration, library mode, and build
vite-advanced · Skill · 215 stars
Advanced Vite 8 patterns including Rolldown-powered builds, advancedChunks, Environment API, plugin development, SSR configuration, library mode, and build
web-research-workflow · Skill · 215 stars
Unified decision tree for web research and competitive monitoring. Auto-selects WebFetch, Tavily, or agent-browser based on target site characteristics and
web-research-workflow · Skill · 215 stars
Unified decision tree for web research and competitive monitoring. Auto-selects WebFetch, Tavily, or agent-browser based on target site characteristics and
write-prd · Skill · 215 stars
Product Requirements Documents: 8-section template, user stories, acceptance criteria, go/no-go. Use when writing a PRD or user stories.
write-prd · Skill · 215 stars
Product Requirements Documents: 8-section template, user stories, acceptance criteria, go/no-go. Use when writing a PRD or user stories.
zustand-patterns · Skill · 215 stars
Reference for Zustand 5.x state management including slices, middleware, Immer, useShallow, persistence, selectors, and devtools integration. Documents 7 c
zustand-patterns · Skill · 215 stars
Reference for Zustand 5.x state management including slices, middleware, Immer, useShallow, persistence, selectors, and devtools integration. Documents 7 c
agents · Collection
careful · Skill
Blocks destructive shell commands once invoked: a PreToolUse Bash guard denies rm -rf outside temp dirs, force pushes and remote branch deletes, git reset
careful · Skill
Blocks destructive shell commands once invoked: a PreToolUse Bash guard denies rm -rf outside temp dirs, force pushes and remote branch deletes, git reset
create-plan · Skill
Writes an implementation plan file (.ork/tasks/TASK/NN-plan-SLUG.md) with phases, file changes and runnable success criteria. Use when research is done and
create-plan · Skill
Writes an implementation plan file (.ork/tasks/TASK/NN-plan-SLUG.md) with phases, file changes and runnable success criteria. Use when research is done and
create-research · Skill
Documents how code works today for a task's questions, with file:line citations. Use before planning a change; describes, never proposes. NOT for mapping a
create-research · Skill
Documents how code works today for a task's questions, with file:line citations. Use before planning a change; describes, never proposes. NOT for mapping a
error-analysis · Skill
Clusters real LLM traces (Langfuse or JSONL) into a confirmed failure taxonomy with counts, then proposes pass/fail evals. Use to learn what to measure bef
error-analysis · Skill
Clusters real LLM traces (Langfuse or JSONL) into a confirmed failure taxonomy with counts, then proposes pass/fail evals. Use to learn what to measure bef
fixtures · Collection
freeze · Skill
Confines file edits to one directory until lifted: an Edit, Write, MultiEdit and NotebookEdit hook refuses any path whose real location, symlinks followed,
freeze · Skill
Confines file edits to one directory until lifted: an Edit, Write, MultiEdit and NotebookEdit hook refuses any path whose real location, symlinks followed,
glyph · Skill
Renders an answer as inline ASCII art with emojis, verdict first, one render per reply. Use for status, inventories, comparisons, rankings, pipelines or sh
glyph · Skill
Renders an answer as inline ASCII art with emojis, verdict first, one render per reply. Use for status, inventories, comparisons, rankings, pipelines or sh
iterate-plan · Skill
Revises a create-plan file from its review comments or new instructions, keeping comments and bumping the revision. Use when a plan got feedback; never to
iterate-plan · Skill
Revises a create-plan file from its review comments or new instructions, keeping comments and bumping the revision. Use when a plan got feedback; never to
iterate-research · Skill
Re-checks a create-research file when a claim is challenged or the question widens, citing file:line afresh. Use after review comments on research.
iterate-research · Skill
Re-checks a create-research file when a claim is challenged or the question widens, citing file:line afresh. Use after review comments on research.
mcp-body-ungranted · Collection
ork-glyph · Skill
Render an answer inline as compact ASCII or box-drawing art with semantic status icons. Use for status, inventories, budgets, comparisons, rankings, pipeli
ork-glyph · Skill
Render an answer inline as compact ASCII or box-drawing art with semantic status icons. Use for status, inventories, budgets, comparisons, rankings, pipeli
ork-implement · Skill
Make an approved, scoped change and prove the affected behavior. Use when a request asks to implement, build, add, or land a feature that already has an ag
ork-implement · Skill
Make an approved, scoped change and prove the affected behavior. Use when a request asks to implement, build, add, or land a feature that already has an ag
page-serve · Skill
Serves a rendered HTML page to a human at a stable https://NAME.localhost/ URL via portless, never a port, and tears it down on stop. Use when an agent mad
page-serve · Skill
Serves a rendered HTML page to a human at a stable https://NAME.localhost/ URL via portless, never a port, and tears it down on stop. Use when an agent mad
paired-probe · Skill
Refuses a verdict a check did not earn: runs it with the fault present and absent and blocks when both agree; catches zero-sample sweeps and swallowed erro
paired-probe · Skill
Refuses a verdict a check did not earn: runs it with the fault present and absent and blocks when both agree; catches zero-sample sweeps and swallowed erro
prompt-focus · Skill
Shows where your attention went from your own Claude Code and Codex prompts over 20 weeks, as a local counts-only report. Use when asking where your focus
prompt-focus · Skill
Shows where your attention went from your own Claude Code and Codex prompts over 20 weeks, as a local counts-only report. Use when asking where your focus
review-artifact-comments · Skill
Works through review comments in a plan or research artifact: replies, resolves, hands off to iterate-plan or iterate-research, approves when none are open
review-artifact-comments · Skill
Works through review comments in a plan or research artifact: replies, resolves, hands off to iterate-plan or iterate-research, approves when none are open
scratch-stitch-one-prefix · Skill
Fixture skill that grants only mcp__stitch__list_projects (no hq-ext twin).
scratch-stitch-ungranted · Skill
Fixture skill that names a Stitch tool without granting it.
tests · Collection

Browse the @skills marketplace