Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 600 files from 1 763 authors, of which 61 947 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Quick persona switching. Triggers: 'switch persona', 'switch to X', 'become X'. Lists personas, reads selected file, switches immediately.
Design, refactor, analyze, and review code by applying the principles and patterns of tactical domain-driven design. Triggers on: domain modeling, aggregate design, 'entity', 'value object', 'repository', 'bounded context', 'domain event', 'domain service', code touching domain/ directories, rich domain model discussions.
Principles for writing effective, maintainable tests. Covers naming conventions, assertion best practices, and comprehensive edge case checklists. Based on BugMagnet by Gojko Adzic. Triggers on: writing any test, 'add tests', test review, test naming, assertion choices, edge case coverage, 'what should I test', test structure decisions.
Strict test-driven development state machine with red-green-refactor cycles. Enforces test-first development, meaningful failures, minimum implementations, and full verification. Activates when user requests: 'use a TDD approach', 'start TDD', 'test-drive this'.
Sets up NX monorepo for TypeScript backend projects optimized for AI-assisted development. Delegates to NX commands where possible, patches configs as last resort. Triggers on: 'set up typescript backend project', 'create backend project', 'initialize typescript backend', 'create monorepo', or when working in an empty project folder.
>- IsaacTeleop CMake target layout and #include conventions. Use whenever you create or edit a CMakeLists.txt, add or move a module/library/executable/test target, set up target_include_directories or target_link_libraries, decide where a header file goes (private vs public inc/), write or reorder #include directives in C/C++ sources, or restructure directories under src/ or deps/. Also use when reviewing diffs that touch CMakeLists.txt, header placement, include paths, or the overall project/directory structure.
Crypto trading & wallet, and AI market analysis via Minara CLI. Swap, perps, transfer, deposit (credit card/crypto), withdraw, AI chat, market discovery, x402 payment, autopilot, limit orders, premium. EVM + Solana + Hyperliquid. Use when: (1) crypto tokens/tickers (ETH, BTC, SOL, USDC, $TICKER, contract addresses), (2) chain names (Ethereum, Solana, Base, Arbitrum, Hyperliquid), (3) trading actions (swap, buy, sell, long, short, perps, leverage, limit order, autopilot), (4) wallet actions (balance, portfolio, deposit, withdraw, transfer, send, pay, credit card), (5) market data (trending, price, analysis, fear & greed, BTC metrics, Polymarket, DeFi), (6) stock tickers in crypto context (AAPL, TSLA), (7) Minara/x402/MoonPay explicitly, (8) subscription/premium/credits.
Use when the user needs embedded hardware architecture, MCU/SoC selection, power tree design, interface planning, sensor/actuator selection, RF/connectivity, BOM risk assessment, PCB/layout constraints, schematic-ready proposals, validation plans, or hardware design review.
> fastapi-redis-sdk development skill. Use when writing code, tests, or configuration for the fastapi-redis-sdk library — the official Redis integration for FastAPI. Covers project setup (uv + nox), DI-based caching patterns, connection lifecycle, async/sync endpoints, testing conventions, and CI workflows. Do NOT use for general Redis or FastAPI questions unrelated to this library.
> Troubleshoot and resolve common issues with the ClickHouse Node.js client (@clickhouse/client). Use this skill whenever a user reports errors, unexpected behavior, or configuration questions involving the Node.js client specifically — including socket hang-up errors, Keep-Alive problems, stream handling issues, data type mismatches, read-only user restrictions, proxy/TLS setup problems, or long-running query timeouts. Trigger even when the user hasn't precisely named the issue; vague symptoms like "my inserts keep failing" or "connection drops randomly" in a Node.js context are strong signals to use this skill. Do NOT use for browser/Web client issues.
> Write idiomatic application code with the ClickHouse Node.js client (`@clickhouse/client`). Use this skill whenever a user is *building* against the Node.js client — configuring the client, pinging, inserting rows in JSON or raw formats, selecting and parsing results, binding query parameters, managing sessions and temporary tables, working with data types or customizing JSON parsing. Do NOT use for browser/Web client code.
> Generate TypeScript/JavaScript code that reads/decodes AND writes/encodes ClickHouse RowBinary streams for the ClickHouse HTTP server. Use this skill whenever a user wants to parse or produce `RowBinary`, `RowBinaryWithNames`, or `RowBinaryWithNamesAndTypes`. Node.js only, doesn't cover browsers.
> version, sync the protected `release` branch from `main`, watch the npm publish (which is gated by a manual approval on the `npm-publish` environment), and create the GitHub Release from the CHANGELOG. Use this skill whenever the task is to "release", "cut a release", "publish a new version", or "ship" one (Web), `@clickhouse/client-common` (deprecated, rarely released), the standalone `@clickhouse/datatype-parser` (the type parser, under `packages/datatype-parser`), or `@clickhouse/rowbinary` (the RowBinary codec skill/package, under `skills/clickhouse-js-node-rowbinary`). The agent drives the GitHub Actions workflows (`gh workflow run`), watches CI, pauses at the human-judgment points (PR review, the approval gate, GitHub Release text), and hands the deployment-approval link back to the human. Do NOT use this for fixing a failing release PR — that is the `fix-release-pr` skill.
> Use the TypeScript language server (`typescript-language-server`) for precise references, hover (type signatures and JSDoc, including `@deprecated` info), workspace-wide symbol search, completions, and per-file type diagnostics. Prefer this over grep when you need to resolve a symbol's actual definition, find all usages of an exported API, or inspect inferred types across the `packages/*` workspaces. The server is preinstalled as a root devDependency — run the repository `setup` skill (`npm install`) first so `node_modules` is populated. Do NOT use this skill for downstream projects that merely depend on `@clickhouse/client`; it is specific to working inside this repo.
> Set up the `clickhouse-js` repository in a fresh checkout so the agent can run tests, lints, type checks, builds, or examples. Use this skill before invoking `npm run run-examples` script — or after pulling changes that touch any `package.json` (root, `examples/node`, or `examples/web`). Covers Node.js version requirements, installing dependencies across the npm workspaces and the two independent example packages, building the workspace packages so inter-package imports resolve, and starting ClickHouse via Docker Compose for integration tests. Do NOT use this skill for downstream user projects that merely depend on `@clickhouse/client` or `@clickhouse/client-web`; it is specific to contributing to the `ClickHouse/clickhouse-js` repo itself.
> Fix CI failures and address code-review comments on a pull request that targets the protected `release` branch of `ClickHouse/clickhouse-js`. Release PRs are snapshots of `main` (their head branch is usually `main` itself) and cannot be edited directly — branch protection blocks pushing fixes onto them. Use this skill whenever the work is "fix the CI / address the review comments separate PR to `main`, then closes the loop on the original release PR by replying to and resolving the review threads. Triggers on phrasing like "fix this release PR", "the release PR is failing CI", "address the review comments but it's a release branch", or after checking out a PR whose base is `release`. Do NOT use this for ordinary feature/fix PRs that target `main` — for those, just push to the PR's own branch.
> Query ClickHouse system tables to inspect query logs, monitor cluster health, check replication status, and analyze slow queries. Use when the user mentions "system tables", "query_log", "ClickHouse monitoring", "cluster status", "slow queries", or asks to diagnose ClickHouse operational issues.
Expert system for generating, validating, and optimizing ClickHouse SQL. Use this when the user needs data, queries, or analysis.
Optimize slow queries, analyze SQL performance, and collect evidence for expensive workloads.
Diagnose ClickHouse runtime query failures when the user wants database-level cause and fix guidance from an error or numeric error code, not source-code root cause analysis.
Diagnose ClickHouse cluster health and provide concrete remediation.
Investigate application or repository source code with search_file and read_file to explain behavior, trace root causes of runtime or query errors, and answer with precise file citations.
Rules for charts and visualization. Use when the user asks for charts, graphs, plots, or visual representations (line, bar, pie, timeseries).
Write and debug React Native Harness tests for app code. Use when the user asks to create or fix tests that import from react-native-harness, mock modules, spy on functions, render React Native components on-device, use setupFiles or setupFilesAfterEnv, or add optional UI tests with @react-native-harness/ui.
>- Check GKE Kubernetes version support status using the endoflife.date API (auto-scraped from Google's GKE release schedule). Use whenever someone asks about GKE K8s version support, EOL dates, or whether the current GKE cluster version is still supported. GKE uses a long-running static cluster whose version is not managed in CI config.
>- List AKS test entries in RHDH ci-operator config files and update the AKS Kubernetes version per branch. Use when listing e2e-aks tests, changing MAPT_KUBERNETES_VERSION for AKS, or checking which AKS K8s version each release branch uses.
>- Add a new step-registry step (ref YAML + commands.sh) in openshift/release. Use when creating a new CI step, atomic test action, or reusable ref component. Run step-finder first to avoid duplicates.
>- Search openshift/release step-registry for existing steps, workflows, and chains before creating new CI components. Use when adding tests, jobs, or step-registry entries, or when asked to find reusable pre/test/post components.
>- List EKS test entries in RHDH ci-operator config files and update the EKS Kubernetes version per branch. Use when listing e2e-eks tests, changing MAPT_KUBERNETES_VERSION for EKS, or checking which EKS K8s version each release branch uses.
>- Use when decommissioning an end-of-life RHDH release branch by removing CI config, generated Prow jobs, and branch protection from the openshift/release repository
>- Check EKS Kubernetes version support status using the official AWS EKS docs source and compare against versions configured in CI config files. Use whenever someone asks about EKS K8s version support, EOL dates, or whether the configured EKS version is still in standard support. Also use when planning EKS K8s version upgrades — run this before using rhdh-eks-tests to make changes.
>- Check AKS Kubernetes version support status using the official AKS release status API and compare against versions configured in CI config files. Use whenever someone asks about AKS K8s version support, EOL dates, deprecation, or whether the configured AKS version is still GA. Also use when planning AKS K8s version upgrades — run this before using rhdh-aks-tests to make changes.
>- List, generate, add, and remove OCP-versioned test entries (e2e-ocp-*) in RHDH ci-operator config files. Covers only OCP cluster-claim tests, not K8s platform tests (AKS, EKS, GKE, OSD)
>- List GKE test entries in RHDH ci-operator config files. Use when listing e2e-gke tests or checking which branches have GKE test entries. Unlike AKS/EKS, GKE uses a pre-existing static cluster — version upgrades are performed via the GCP Console.
>- Analyze RHDH OCP version coverage by cross-referencing cluster pools and CI test configs against both RHDH and OCP lifecycle APIs to find gaps, stale configurations, and compatibility mismatches
>- List existing RHDH OCP Hive ClusterPool configurations and generate new pool YAML for a target OCP version, with imageSetRef aligned from other pools in the openshift/release repository. Covers OCP pools only, not K8s platforms
>- Check which OCP versions are supported by active RHDH releases and which are end-of-life, using the Red Hat Product Life Cycles API for both RHDH and OCP lifecycle data including EUS phases. Supports OCP 4.x and future 5.x+
> Use when someone asks "does this sound AI?", "check if this is AI-written", "what gives this away as AI", "run ai-check on this", or "score this text". Also use when reviewing a draft for AI tells before publishing, or when a piece of text reads as suspiciously polished, generic, or pattern-y and the user wants a forensic breakdown of why.
> Use whenever the user asks to "humanize", "make this sound more human", "rewrite to avoid AI detection", "make this less AI-sounding", "add a human voice", or "write like a person". Also use when the user pastes text and asks why it reads as robotic, generic, flat, or AI-like, or when generating new text in a register where AI tells (em dashes, semicolons, hedges, banned vocabulary like "delve", "leverage", "robust") would damage credibility.
Catalog every config axis, its defaults and guards. Use when adding or auditing configuration. Do not use for running gates; use night-market-operations.
Bind loop 'done' to unfakeable gates. Use to harden egregore/herald loops or promote completion_integrity. Not for QA gates; use night-market-validation-and-qa.
Triage night-market failures by symptom (hooks, CI, tests). Use when a check fails unexpectedly. Do not use for routine gates; use night-market-operations.
Classify, gate, and review changes. Use when landing a PR, releasing, or amending rules. Do not use for failure triage; use night-market-debugging-playbook.
Explain plugin, skill, command, agent, and hook mechanics used here. Use when authoring or debugging plugins. Do not use for ops; use night-market-operations.
States load-bearing decisions, invariants, and weak points. Use when judging a design change. Do not use for gating; use night-market-change-control.
Rebuild the dev environment: uv, Python tiers, pins, traps. Use when onboarding or toolchain breaks. Do not use for daily commands; use night-market-operations.
Search and record project memory (Discussions, journal, ADRs). Use before re-investigating anything. Do not use for settled battles; see failure-archaeology.
Run and interpret repo diagnostic scripts (ratchets, validators, token stats). Use when measuring health. Do not use to run tests; use night-market-operations.
Map open problems where this repo can advance SOTA. Use when scoping research. Do not use to run the campaign; use night-market-completion-integrity-campaign.
Chronicles settled battles, reverts, and dead ends. Use when a fix echoes a past failure. Do not use for live triage; use night-market-debugging-playbook.
Run and ship this repo: make targets, artifacts, release runbook. Use when testing, linting, or releasing. Do not use for setup; use night-market-build-and-env.
Maintain docs of record, ADRs, changelog, and house style. Use when writing repo docs. Do not use for release steps; use night-market-operations instead.
Turn hunches into accepted results: worthiness score, evidence bar, research-to-rules. Use when vetting ideas. Not for QA; use night-market-validation-and-qa.
Enforce evidence bar, coverage gates, and regression guards. Use when adding tests or claiming done. Do not use to run suites; use night-market-operations.
Assess whether to escalate models. Use when evaluating reasoning depth.
Select hook scope (plugin, project, global) by audience. Use when authoring a hook.
Guide creating Claude Code hooks with security-first design. Use for validation and enforcement.
Detect friction signals; graduate patterns into rules. Use for session retrospectives.
Analyze and improve the improvement process. Use for detecting regressions and meta-optimization.
Build composable skill modules with hub-and-spoke loading. Use when token budget is tight.
Claude Skills — questions
Answers built from the skills we actually parsed.