@skills · Owner
Agent skills by paulrberg
47 skills indexed from github.com/paulrberg. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.
- agent-skills · Collection · 69 stars
- agents-brain · Skill · 69 stars
Create or polish repo agent context: README.md, AGENTS.md/CLAUDE.md, project-installed and source-catalog skills, and other Markdown context docs.
- agents-docs · Skill · 69 stars
Use for current official documentation about Codex, Codex CLI, or Claude Code behavior, configuration, prompting, skills, permissions, tools, surfaces, cap
- agents-introspection · Skill · 69 stars
Assess recurrence risk for agent behavior using local Codex/Claude Code transcripts and recommend evidence-backed durable fixes to AGENTS.md or skills. Not
- autoresearch · Skill · 69 stars
Use for autoresearch or "optimize X overnight/in a loop"; plans bounded measurable experiment batches, then delegates execution through codex-handoff.
- claude-handoff · Skill · 69 stars
Orchestrate read-only Explore research subagents in any mode, or one to eight Claude subagents to implement an approved plan.
- cli-cast · Skill · 69 stars
Use for Foundry cast transaction actions: prepare, trace, simulate, sign, or broadcast; sign messages; or encode/decode ABI/calldata. Delegate every standa
- cli-coingecko · Skill · 69 stars
Use for CoinGecko/cg CLI crypto market data: prices, market cap, trending coins, top gainers/losers, coin search, or historical/OHLC data.
- cli-gh · Skill · 69 stars
Use for GitHub CLI automation: repository reads, workflow runs, search, codespaces, releases, configuration, or gh command syntax. Use yeet for contributio
- cli-just · Skill · 69 stars
Use for just/justfile task automation: create justfiles, write recipes, configure settings, add modules/attributes, or set up command-runner workflows.
- code-polish · Skill · 69 stars
Polish changed code when the user explicitly asks, or when an active workflow requests post-implementation simplification and risk-profiled review over a f
- codex-handoff · Skill · 69 stars
Orchestrate read-only Codex research in any mode, or one to eight Codex agents to implement approved plans from Claude Code or Codex CLI.
- commit · Skill · 69 stars
Commit staged or intended changes: compose a Conventional Prefix or Natural Language message, then use ai-commit — with --all, --staged, --close, --finding
- effect-ts · Skill · 69 stars
Use for nontrivial Effect 3 work including services/layers, typed errors, Schema/JSONSchema, Config, runtime/concurrency, @effect/vitest, @effect/ai, @effe
- evm-atlas · Skill · 69 stars
Use for targeted EVM chain, account, transaction, RPC, explorer, bridge, and DEX evidence: chain name/ID, native symbol, RouteMesh, wallet balances via Blo
- fresh-eyes-sweep · Skill · 69 stars
Audit an entire repository with fresh eyes for correctness errors, bugs, omissions, duplication, inconsistencies, and other evidenced mistakes; fix every s
- frontend-design · Skill · 69 stars
Use when creating or substantially redesigning web interfaces, landing pages, dashboards, components, or other frontend UI where visual direction and imple
- git-squash · Skill · 69 stars
Squash a feature branch into one commit via soft reset to the merge base, ready for a clean PR.
- grill-me · Skill · 69 stars
Interview the user relentlessly about a plan or design until every branch of the decision tree has an explicit recorded decision and no open questions rema
- html-debrief · Skill · 69 stars
Use for interactive HTML debriefs or saved HTML findings/reports from the current task.
- html-playground · Skill · 69 stars
Use to build interactive single-file HTML playgrounds, explorers, or tools with visual controls, live preview, and prompt copy-out.
- large-file-refactor · Skill · 69 stars
Discover large source-file refactor candidates and propose cohesion- and risk-driven split plans using available semantic tooling.
- naming-refactor · Skill · 69 stars
Refactor naming and repository structure exhaustively while preserving behavior and external contracts.
- node-deps-bumper · Skill · 69 stars
Use for dependency updates: bump npm/pnpm/yarn/bun packages, check outdated, or run taze.
- release-bumper · Skill · 69 stars
Cut a release: bump versions, write changelogs, commit, tag.
- repo-harmonization · Skill · 69 stars
Audit multiple interdependent repositories for alignment, then plan and apply surgical fixes for drift and duplication.
- repo-rename · Skill · 69 stars
Preview or rename a GitHub upstream repo and matching local project folder, update origin, and preserve Codex CLI and Claude Code continuity references.
- skill-doctor · Skill · 69 stars
Use to audit Agent Skills catalogs or installed skill roots for metadata and doc-link issues; optionally apply conservative --fix-safe repairs.
- skill-harmonization · Skill · 69 stars
Harmonize a repository's skill portfolio across catalog and user-installed skills.
- skill-map · Skill · 69 stars
Use to find agent skill installs, repository skill portfolios, duplicate skills, cross-dependencies, invocations, and cross-references across the local mac
- skill-writing · Skill · 69 stars
Create/scaffold/init a project-local agent skill under `.agents/skills` in an ordinary repository; defer to repository instructions that define a source ca
- skills · Collection · 69 stars
- spreadsheets · Skill · 69 stars
Use when CSV, TSV, or Excel (.xlsx) is the primary input/output: design or review text-table schemas; inspect, transform, validate, convert, or recalc form
- stale-comments-audit · Skill · 69 stars
Audit and fix JavaScript, TypeScript, and Go comments that are verified as stale, orphaned, misleading, or redundant.
- tailwind-css · Skill · 69 stars
Use for Tailwind v4 styling: add/fix classes, configure or migrate Tailwind, use tailwind-variants, or tw-animate-css.
- task-handoff · Skill · 69 stars
Create one decision-complete task handoff in its repository or on the Desktop for cross-repository work, return a command for a fresh interactive Codex ses
- todo-archive · Skill · 69 stars
Archive checked TODO.md tasks into `.ai/todos/YYYY-MM/DD.md`, leaving unchecked tasks.
- tool-finder · Skill · 69 stars
Use to find, compare, and recommend current tools, packages, libraries, CLIs, VSCode extensions, agent skills, databases, or infrastructure options for a d
- vitest · Skill · 69 stars
Use for Vitest in TypeScript projects (Node, bun, React/Next.js, Effect): write, run, or debug unit/component tests, mocks, testing utilities, and coverage
- yeet · Skill · 69 stars
Use for GitHub PR/issue/discussion workflows: create/update PRs, issues, or discussions and post issue or discussion comments; triggers include yeet.
- brainstorm · Skill
Brainstorm with the user to generate, combine, and refine non-obvious ideas into a promising concept. Use when the user wants to brainstorm, ideate, explor
- chromium-browser · Skill
Use Chrome DevTools through PRB's shared attach-only Chromium browser for browsing, debugging, automation, visual inspection, console or network analysis,
- codebase-design · Skill
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where
- copy-transcript-path · Skill
Copy the active Claude Code or Codex CLI chat transcript path to the macOS clipboard.
- interview-me · Skill
Interview the user about a plan, idea, or design through a short sequence of high-leverage questions, then summarize the direction and next step. Use when
- pdf · Skill
Use when PDF files are the primary input or output: read, compare, reconcile, extract text/tables/images, OCR scans, fill forms, split, merge, rotate, rena
- wrap-up · Skill
Wind down a long-running session fast when the user must leave — freeze new work, preserve active subagents, secure finished work, and hand off the remaind