Find the best CLAUDE.md, AGENTS.md and Claude skills

penpotAGENTS.md

penpot

penpot/penpot/AGENTS.md

organization Memories are grouped into folders that mirror project modules or topics: `backend/`, `common/`, `frontend/`, `render-wasm/`, `exporter/`, `workflow/`, etc. Each folder's top-level memory is ` /core`. --- # Role: Senior

No other project uses it yet

penpotSkill

local-ci

penpot/penpot/.agents/skills/local-ci/SKILL.md

Run local CI-style checks with ./scripts/ci (lint, tests, format, and on request production builds) per monorepo module. Use when verifying changes before declaring work done, running lint or tests locally, fixing formatting, repairing Clojure delimiter errors, or checking that a module still compiles.

penpotSkill

nrepl-eval

penpot/penpot/.agents/skills/nrepl-eval/SKILL.md

Evaluate Clojure code via nREPL using the standalone scripts/nrepl-eval.mjs CLI tool.

No other project uses it yet

penpotSkill

refactor-scss

penpot/penpot/.agents/skills/refactor-scss/SKILL.md

Migrate one Penpot SCSS module off the deprecated styles under frontend/resources/styles/common/refactor/ to the current Design System (ds/ tokens, mixins and px2rem). Pure refactor, no visual change. Use when the user asks to refactor, migrate or clean up a .scss file to the DS.

No other project uses it yet

penpotSkill

refine-prompt

penpot/penpot/.agents/skills/refine-prompt/SKILL.md

Refine and improve a user-supplied prompt for maximum clarity and effectiveness using prompt-engineering best practices and Penpot project context. Outputs a rewritten prompt (and brief rationale); never executes the prompt.

pingdotggReads credentialsAGENTS.md

t3code

pingdotgg/t3code/AGENTS.md

that works on the path you tested and is missing everywhere else. Before calling frontend work done, walk this list and say which entries applied: - **Entry points.** A behavior reachable

vectorize-ioReads credentialsCLAUDE.md

hindsight

vectorize-io/hindsight/CLAUDE.md

Plane (Next.js) ```bash ./scripts/dev/start-control-plane.sh # Or manually: cd hindsight-control-plane && npm run dev # Run frontend unit tests cd hindsight-control-plane && npm test # Run frontend linter cd hindsight-control-plane

vectorize-ioPipes a download into a shellSkill

hindsight-cloud

vectorize-io/hindsight/skills/hindsight-cloud/SKILL.md

Store team knowledge, project conventions, and learnings from tasks. Use to remember what works and recall context before new tasks. Connects to Hindsight Cloud. (user)

vectorize-ioPipes a download into a shellSkill

hindsight-self-hosted

vectorize-io/hindsight/skills/hindsight-self-hosted/SKILL.md

Store team knowledge, project conventions, and learnings from tasks. Use to remember what works and recall context before new tasks. Connects to a self-hosted Hindsight server. (user)

twentyhqSkill

syncable-entity-integration

twentyhq/twenty/.claude/skills/syncable-entity-integration/SKILL.md

Contributing to the Twenty codebase itself (twentyhq/twenty server internals), not for building apps on top of Twenty. Wire syncable entity services into NestJS modules, create service layer and resolvers for Twenty entities. Use when registering builders, validators, and action handlers in modules, creating business services, or exposing entities via GraphQL API with proper exception handling.

emilkowalskiSkill

break-ui

emilkowalski/skills/skills/break-ui/SKILL.md

Try to break a piece of UI by feeding it worst-case data — long names, unbreakable emails, one-letter names, missing fields, huge counts, zero items, long labels, non-Latin text, emoji, extreme numbers — then render it behind a "Demo data / Worst case" toggle and report everything that broke, with the fix for each. Use when the user asks to stress-test, break, or find edge cases in a component or screen, or to "try the worst case". For visual design critique use emil-design-eng; for motion use review-animations.

Often used withremove-animations·animation-performance·pick-ui-library

ChromeDevToolsAGENTS.md

chrome-devtools-mcp

ChromeDevTools/chrome-devtools-mcp/AGENTS.md

formatting in `src/formatters/*`. `McpResponse` does not resolve pages or workers. - [ ] If Puppeteer or devtools-frontend owns the bug, fix it there first. Do not copy or re-implement upstream code

No other project uses it yet

ChromeDevToolsSkill

memory-leak-debugging

ChromeDevTools/chrome-devtools-mcp/skills/memory-leak-debugging/SKILL.md

Diagnoses and resolves memory leaks in JavaScript/Node.js applications. Use when a user reports high memory usage, OOM errors, or wants to capture, compare, or inspect heap snapshots with Chrome DevTools MCP memory tools.

HKUDSReads credentialsAGENTS.md

DeepTutor

HKUDS/DeepTutor/AGENTS.md

textbook.pdf deeptutor memory show deeptutor serve --port 8001 # API server only deeptutor start # backend + frontend together ``` Examples beyond core require their owning modules; use `deeptutor module list` to inspect installed/enabled/ready

No other project uses it yet

HKUDSSkill

deeptutor-cli

HKUDS/DeepTutor/SKILL.md

Configure, manage, and use DeepTutor through its CLI, including capabilities, knowledge bases, partners, memory, sessions, notebooks, providers, skills, and the server or Web app.

No other project uses it yet

multica-aiReads credentialsAGENTS.md

multica

multica-ai/multica/AGENTS.md

actually ran and any skipped checks. Run these from the repository root: | Scope | Checks | | --- | --- | | Frontend excluding mobile | `pnpm typecheck`, `pnpm lint`, `pnpm test` | | `.github/` or `scripts/` | `pnpm test:scripts` (every

TryGhostSkill

add-service

TryGhost/Ghost/.agents/skills/add-service/SKILL.md

Create a new Ghost Core service with gx generate service, then finish what the generator leaves to the author - dependency wiring, boot initialization, tests and checks. Use when adding a new boot-owned capability under ghost/core/server/services. To adopt defineService in an existing service, use migrate-service instead.

emilkowalskiSkill

break-ui

emilkowalski/skill/skills/break-ui/SKILL.md

Try to break a piece of UI by feeding it worst-case data — long names, unbreakable emails, one-letter names, missing fields, huge counts, zero items, long labels, non-Latin text, emoji, extreme numbers — then render it behind a "Demo data / Worst case" toggle and report everything that broke, with the fix for each. Use when the user asks to stress-test, break, or find edge cases in a component or screen, or to "try the worst case". For visual design critique use emil-design-eng; for motion use review-animations.

Often used withremove-animations·animation-performance·pick-ui-library

AnthropicCLAUDE.md

claude-cookbooks / chief_of_staff_agent

anthropics/claude-cookbooks/claude_agent_sdk/chief_of_staff_agent/CLAUDE.md

Revenue per Employee**: $48K ## Team Structure - **Total Headcount**: 50 - **Engineering**: 25 (50%) - Backend: 12 - Frontend: 8 - DevOps/SRE: 5 - **Sales & Marketing**: 12 (24%) - **Product**: 5 (10%) - **Operations**: 5 (10%) - **Executive

No other project uses it yet