@skills · Owner

Agent skills by cursor

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

• agent-compatibility · Collection · 2,555 stars
• architect · Skill · 2,555 stars

  Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'des

• arena · Skill · 2,555 stars

  Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the

• automate-me · Skill · 2,555 stars

  Use for \"automate me\", \"create/update/refresh my -mode skill\", \"turn/capture my preferences or working style into a skill\", or wanting agents to foll

• automations · Collection · 2,555 stars
• benny · Collection · 2,555 stars
• blast-radius · Skill · 2,555 stars

  Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of

• bro · Skill · 2,555 stars

  Restate the last message in plain human language, with no jargon.

• cancel-ralph · Skill · 2,555 stars

  Cancel an active Ralph Loop. Use when the user wants to stop, cancel, or abort a running ralph loop.

• check-agent-compatibility · Skill · 2,555 stars

  Run the full repository compatibility pass: scanner score, startup path, validation loop, and docs reliability.

• check-compiler-errors · Skill · 2,555 stars

  Run compile and type-check commands and report failures

• cli-for-agent · Collection · 2,555 stars
• cli-for-agents · Skill · 2,555 stars

  Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable error

• continual-learning · Skill · 2,555 stars

  Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to `agents-memory-updater`.

• continual-learning · Collection · 2,555 stars
• control-cli · Skill · 2,555 stars

  Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services. Use for CLI UX checks, startup regressio

• control-ui · Skill · 2,555 stars

  Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI. Use for local UI verification, screenshots, accessibility snaps

• create-learning-path · Skill · 2,555 stars

  Build a personalized learning roadmap with milestones and practice checkpoints

• create-plugin · Collection · 2,555 stars
• create-plugin-scaffold · Skill · 2,555 stars

  Create a new Cursor plugin scaffold with a valid manifest, component directories, and marketplace wiring. Use when starting a new plugin or adding a plugin

• create-verification-skill · Skill · 2,555 stars

  Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-s

• cursor-sdk · Skill · 2,555 stars

  Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor TypeScript SDK (`@cursor/sdk`). Use this skill whenever the user ment

• cursor-sdk · Collection · 2,555 stars
• cursor-team-kit · Collection · 2,555 stars
• deslop · Skill · 2,555 stars

  Remove AI-generated code slop and clean up code style

• docs-canvas · Skill · 2,555 stars

  Render a documentation-style Cursor Canvas that organizes architecture notes, API references, walkthroughs, and how-tos into a navigable layout with sectio

• docs-canvas · Collection · 2,555 stars
• figure-it-out · Skill · 2,555 stars

  Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Sca

• fix-ci · Skill · 2,555 stars

  Find failing PR checks, inspect logs or external check links, and apply focused fixes

• fix-merge-conflicts · Skill · 2,555 stars

  Resolve merge conflicts non-interactively, validate build and tests, and finalize conflict resolution

• get-pr-comments · Skill · 2,555 stars

  Fetch and summarize review comments from the active pull request

• how · Skill · 2,555 stars

  Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should this live\", \"whi

• interrogate · Skill · 2,555 stars

  Use for \"interrogate\", \"adversarial review\", \"multi-model review\", \"challenge this\", \"stress test this code\", \"find blind spots\", or \"tear thi

• loop-on-ci · Skill · 2,555 stars

  Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.

• maintain-verification-skill · Skill · 2,555 stars

  Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature

• make-pr-easy-to-review · Skill · 2,555 stars

  Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make thi

• new-branch-and-pr · Skill · 2,555 stars

  Create a fresh branch, complete work, and open a pull request

• no-comments · Skill · 2,555 stars

  Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.

• orchestrate · Skill · 2,555 stars

  Use only when the user explicitly types `/orchestrate <goal>` to decompose a large task, spawn a tree of parallel cloud-agent workers/subplanners/verifiers

• orchestrate · Collection · 2,555 stars
• plugins · Collection · 2,555 stars
• Poteto Mode · Skill · 2,555 stars

  poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode,

• pr-review-canvas · Skill · 2,555 stars

  Generate an interactive PR review walkthrough as an HTML page. Fetches PR data via gh API, categorizes files into core vs mechanical changes, adds reviewer

• pr-review-canvas · Skill · 2,555 stars

  Render a PR diff review as a Cursor Canvas that groups changes by reviewer importance, separates boilerplate from core logic, and highlights tricky or unex

• pr-review-canvas · Collection · 2,555 stars
• principle-boundary-discipline · Skill · 2,555 stars

  Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust i

• principle-build-the-lever · Skill · 2,555 stars

  Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generato

• principle-encode-lessons-in-structure · Skill · 2,555 stars

  Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runti

• principle-exhaust-the-design-space · Skill · 2,555 stars

  Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by si

• principle-experience-first · Skill · 2,555 stars

  Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rou

• principle-fix-root-causes · Skill · 2,555 stars

  Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that sile

• principle-foundational-thinking · Skill · 2,555 stars

  Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data

• principle-guard-the-context-window · Skill · 2,555 stars

  Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread,

• principle-laziness-protocol · Skill · 2,555 stars

  Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change tha

• principle-make-operations-idempotent · Skill · 2,555 stars

  Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless

• principle-migrate-callers-then-delete-legacy-apis · Skill · 2,555 stars

  Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving comp

• principle-minimize-reader-load · Skill · 2,555 stars

  Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-ca

• principle-model-the-domain · Skill · 2,555 stars

  Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scat

• principle-never-block-on-the-human · Skill · 2,555 stars

  Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmati

• principle-outcome-oriented-execution · Skill · 2,555 stars

  Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states

• principle-prove-it-works · Skill · 2,555 stars

  Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a pr

• principle-redesign-from-first-principles · Skill · 2,555 stars

  Apply when integrating a new requirement into an existing design. Redesign as if the requirement had been a foundational assumption from day one, instead o

• principle-separate-before-serializing-shared-state · Skill · 2,555 stars

  Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one

• principle-sequence-verifiable-units · Skill · 2,555 stars

  Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a v

• principle-subtract-before-you-add · Skill · 2,555 stars

  Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.

• principle-type-system-discipline · Skill · 2,555 stars

  Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand se

• pstack · Collection · 2,555 stars
• ralph-loop · Skill · 2,555 stars

  Start a Ralph Loop for iterative self-referential development. Use when the user asks to run a ralph loop, start an iterative loop, or wants repeated auton

• ralph-loop · Collection · 2,555 stars
• ralph-loop-help · Skill · 2,555 stars

  Explain the Ralph Loop plugin, how it works, and available skills. Use when the user asks for help with ralph loop, wants to understand the technique, or n

• recall · Skill · 2,555 stars

  Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand bac

• reflect · Skill · 2,555 stars

  Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the u

• reproduce-and-fix-issues · Skill · 2,555 stars

  Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-a

• review-and-ship · Skill · 2,555 stars

  Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.

• review-plugin-submission · Skill · 2,555 stars

  Audit a Cursor plugin for marketplace readiness. Use when validating manifests, component metadata, discovery paths, and submission quality before publishi

• run-learning-retrospective · Skill · 2,555 stars

  Evaluate learning progress, identify blockers, and adjust the learning plan

• run-smoke-tests · Skill · 2,555 stars

  Run Playwright smoke tests, debug failures, and verify fixes

• setup-benny · Skill · 2,555 stars

  Configure Benny and prepare its triage and repro automations. Use when installing Benny or changing its Slack, tracker, repository, routing, control, model

• setup-pstack · Skill · 2,555 stars

  Configure which models pstack uses per role. Detects your available models and writes an always-applied rule that overrides the skill defaults. Use for /se

• show-me-your-work · Skill · 2,555 stars

  Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default;

• skills · Collection · 2,555 stars
• skills · Collection · 2,555 stars
• skills · Collection · 2,555 stars
• skills · Collection · 2,555 stars
• skills · Collection · 2,555 stars
• skills · Collection · 2,555 stars
• skills · Collection · 2,555 stars
• skills · Collection · 2,555 stars
• skills · Collection · 2,555 stars
• skills · Collection · 2,555 stars
• skills · Collection · 2,555 stars
• skills · Collection · 2,555 stars
• skills · Collection · 2,555 stars
• skills · Collection · 2,555 stars
• swarm · Skill · 2,555 stars

  Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.

• tdd · Skill · 2,555 stars

  Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the

• teach · Skill · 2,555 stars

  Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. U

• teaching · Collection · 2,555 stars
• technical-writing · Skill · 2,555 stars

  Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-

• thermo-nuclear-code-quality-review · Skill · 2,555 stars

  Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality

• thermo-nuclear-code-quality-review · Skill · 2,555 stars

  Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality

• thermo-nuclear-review · Skill · 2,555 stars

  Comprehensive security and correctness audit of a branch's changes. Use for thermo nuclear, thermonuclear, or deep review requests, or branch/PR diff audit

• thermos · Skill · 2,555 stars

  Launch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug/security an

• thermos · Collection · 2,555 stars
• triage-issue-reports · Skill · 2,555 stars

  Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only fr

• typescript-best-practices · Skill · 2,555 stars

  TypeScript best practices. Use when reading or editing any .ts or .tsx file.

• unslop · Skill · 2,555 stars

  Cut AI tells from any writing. Must always apply.

• verify-this · Skill · 2,555 stars

  Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or

• weekly-review · Skill · 2,555 stars

  Produce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work

• what-did-i-get-done · Skill · 2,555 stars

  Summarize authored commits over a user-specified time period into a concise update

• why · Skill · 2,555 stars

  Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and

• workflow-from-chats · Skill · 2,555 stars

  Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mi

• add-dictation · Skill

  Use when the user runs /add-dictation or wants speech turned into text with Grok speech-to-text: a mic button that dictates into the composer, live caption

• add-read-aloud · Skill

  Use when the user runs /add-read-aloud or wants the app to speak text with Grok text-to-speech: read-aloud button on assistant replies, auto-speak, TTS, vo

• add-voice · Skill

  Use when the user runs /add-voice, types Voice Mode, or asks to add Grok realtime voice to an app, including replacing an STT-LLM-TTS cascade or OpenAI Rea

• advisor · Skill

  Advisor mode. Consult a stronger (or different) model at key checkpoints: before major decisions, when stuck on an error, and before declaring a task done.

• advisor · Collection
• debug-voice · Skill

  Use when the user runs /debug-voice, says voice mode has flaws, asks to see or capture what happened in a Grok realtime voice session, or a voice integrati

• grok-voice · Collection
• Make Bot UI · Skill

  Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or wh

• principle-attack-the-premise · Skill

  Apply when two or more fixes that share one premise have failed the same gate. Take a census of which actors hold the imbalance before the next fix, then q

• principle-test-behavior-not-implementation · Skill

  Apply when you write, change, or keep a test. Call the code the way its users do and assert the result they observe against a literal expected value. If th

• skills · Collection
• skills · Collection
• skills · Collection
• third_party · Collection
• x · Collection
• X MCP guide · Skill

  ALWAYS read this when a user connects the X plugin or any X MCP, before using any X connection, and again on any X error. Do not call an X tool until this

Browse the @skills marketplace