Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
ivanhoinacki/team-exp-claude-config
Skill Claude Code
Review code quality with all 18 dimensions. Analyzes diff, gathers deep context, checks Known Gotchas, presents findings grouped by severity. If a PR exists, posts inline comments on GitHub. Use when the user says "code review", "review this PR", "review PR", "review", "pre-review", "check quality", or before opening…
Skill Claude Code
Operate an LLM-maintained personal knowledge base (an "LLM Wiki") — a persistent, interlinked markdown wiki that the LLM builds and maintains from raw sources, used for study, research, and reading notes. Use this whenever the user wants to ingest sources into their knowledge base — one at a time or in a batch via…
Skill Codex
Operate X/Twitter engagement workflows from a browser session: explore or choose a topic, optionally enrich topic context with Hermes Tweet/Xquik, understand visible posts, draft and publish topic-relevant posts, attach images, like posts, and write human-sounding replies. Use when the user asks Codex to post on X…
derjochenmeyer/claude-code-craft
Skill Claude Code
Fast project health check. Structure completeness, namespace purity, file staleness, hook functionality, decisions format, memory adoption, dream history, setup quality — all from local files. Works with or without git. No agents, no external fetches, 15-30 seconds. For deep analysis with feature adoption and session…
Skill Claude Code
Use when writing code in an app that does semantic search, RAG, or ingests documents into a vector database on the platform — running nearest-neighbor queries, listing/adding/removing documents, or feeding retrieved chunks into an LLM. Covers VectorDatabaseQuery(), ListDocumentsInVectorDatabase()…
rodrigoratouu-code/saas-factory-setup
Skill Claude Code
Guide for creating custom skills in SaaS Factory. Use when you need to create a new skill to extend Claude's capabilities with specialized knowledge, workflows, or tools.
Skill Claude CodeCodex
Behavioral guidelines to reduce agent mistakes across all task types — coding, research, configuration, file operations, and communication. Load for any complex or multi-step task where overcomplication, assumption errors, or scope creep are risks. Derived from Andrej Karpathy's observations on LLM coding pitfalls…
Skill Claude CodeCodex
Contract-driven, design-first quality guardrails for AI-assisted full-stack development. Prevents project chaos at scale by enforcing a five-layer protection system: Design → Contract → Implementation → Verification → PM. Use when: starting a new full-stack project, planning a non-trivial feature, dispatching…
Skill Claude CodeCodex
A research-topic adviser that turns a vague idea into a clearer study question through guided questions, different viewpoints, and checks against academic standards.
10xdev-startup/template-nodejs-express-next-supabase
Skill Claude Code
MANUAL TRIGGER ONLY: invoke only when user types /plan-ceo-review. CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD…
Skill Claude CodeCodex
Draft event copy in Mattie's voice — newsletter blurbs, Luma event descriptions and listings, invite copy, blast copy, forwardable event one-paragraphs. Use for anything an audience reads about an event we host, co-host, or lend the venue to. This is her EVENT register (image-first, receipt-backed, warm by…
Skill Claude CodeCodex
Benchmark whether Atlas measurably improves coding-agent behavior, by running every scenario twice — with and without Atlas — in clean contexts and scoring the pair blind.
Skill Claude CodeCodex
Process a batch of PDF or CSV bank and credit-card statements end to end: extract every transaction (parallel Haiku subagents), canonicalize the party names, categorize against your locked chart of accounts (parallel Sonnet subagents), detect inter-account transfers, and assemble a reviewed Google Sheets workbook with…
cwoodruff/dotnet-claude-code-kit
Skill Claude Code
Add a new Minimal API endpoint following this solution's conventions. Use when the user asks to add a route, endpoint, or new API operation (GET/POST/PUT/DELETE).
dongyu23/ai-driven-develop-skills
Skill Claude CodeCodex
A guide for turning project ideas and product discussions into a product requirements document, or PRD. A PRD describes what a product should do, what it should not do, and how it should be designed.
Skill Claude CodeCodex
Subagent skill for making changes to the FastAPI backend. Use when the task involves editing Python files in backend/, running backend tests, modifying the Dockerfile, or changing backend configuration.
Skill Claude Code
A repository setup skill that adds a reusable structure for working with coding agents, including instructions, skills, hooks, shared session state, and code checks.
BuaaJoseph/claude-code-best-practice-zh
Skill Claude Code
A task recipe for creating an SVG time card showing the current time in Dubai and saving it with a short Markdown summary.
Skill Claude CodeCodex
AI-powered QA test automation — record browser flows, generate test cases from PRDs or Figma designs, execute natural language test scripts, and convert to Playwright + Cucumber BDD tests. Use when asked to "record a test", "create test cases", "execute test script", "automate UI test", "convert to BDD", "generate…
Skill Claude CodeCodex
Activate when reviewing branches, commits, or pull requests using the emoji-driven review protocol.
Skill Claude CodeCodex
Manage Userorbit resources via the public API. Create and manage feedback, roadmap views, announcements, help center articles, product tours, interactive demos, checklists, surveys, support inbox threads, workflows, subscribers, analytics, and more.
Skill Claude CodeCodex
Diagnose errors in all failed Prow CI jobs for a given GitHub PR. Use when the user shares a PR URL and asks to check CI logs, investigate test failures, or understand why CI is failing.
Skill Claude CodeCodex
New project setup & product discovery workflow. Activate FIRST when the user wants to create a new project from scratch, plan a new product/idea from scratch, or setup initial scaffolding, tooling, and ADR-001 architecture documentation.
Skill Claude CodeCodex
Preview and share the current Cursor plan with your team for review. Opens the latest plan in a browser UI where teammates can annotate and give feedback. Use after creating or finalizing a plan.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: