Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
loulanyueSkillloulanyue/awesome-claude-notes/skills/benchmark/SKILL.md
Measures real browser metrics via browser MCP: Benchmarks API endpoints: Measures development feedback loop: Run before and after a change to measure impact: Stores baselines in .ecc/benchmarks/ as JSON. Git-tracked so the team shares baselines.
Often used withios-cleanpair-agentlanding-report
loulanyueSkillloulanyue/awesome-claude-notes/skills/blueprint/SKILL.md
Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, or user says "just do it".
loulanyueSkillloulanyue/awesome-claude-notes/skills/browser-qa/SKILL.md
Uses the browser automation MCP (claude-in-chrome, Playwright, or Puppeteer) to interact with live pages like a real user. Works with any browser MCP: - mChildclaude-in-chrome* tools (preferred — uses your actual Chrome) - Playwright via mcpbrowserbase* - Direct Puppeteer scripts Pair with /canary-watch for post-deploy monitoring.
loulanyueSkillloulanyue/awesome-claude-notes/skills/canary-watch/SKILL.md
Monitors a deployed URL for regressions. Runs in a loop until stopped or until the watch window expires. Quick check (default): single pass, report results Sustained watch: check every N minutes for M hours Diff mode: compare staging vs production When a critical threshold is crossed: - Desktop notification (macOS/Linux) - Optional: Slack/Discord webhook - Log to ~/.claude/canary-watch.log Pair with: - /browser-qa for pre-deploy verification - Hooks: add as a PostToolUse hook on git push to auto-check after deploys -…
loulanyueSkillloulanyue/awesome-claude-notes/skills/carrier-relationship-management/SKILL.md
Codified expertise for managing carrier portfolios, negotiating freight rates, tracking carrier performance, allocating freight, and maintaining strategic carrier relationships. Informed by transportation managers with 15+ years experience. Includes scorecarding frameworks, RFP processes, market intelligence, and compliance vetting. Use when managing carriers, negotiating rates, evaluating carrier performance, or building freight strategies.
loulanyueReads credentialsSkillloulanyue/awesome-claude-notes/skills/claude-api/SKILL.md
Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.
Often used withacademy-guideeverything-claude-code-conventionsnextjs-turbopack
loulanyueSkillloulanyue/awesome-claude-notes/skills/claude-devfleet/SKILL.md
Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.
loulanyueReads credentialsSkillloulanyue/awesome-claude-notes/skills/clickhouse-io/SKILL.md
ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
Often used withcontinuous-learning-v2iterative-retrievalpostgres-patterns
loulanyueSkillloulanyue/awesome-claude-notes/skills/click-path-audit/SKILL.md
Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI in an inconsistent state. Use when: systematic debugging found no bugs but users report broken buttons, or after any major refactor touching shared state stores.
loulanyueReads credentialsSkillloulanyue/awesome-claude-notes/skills/codebase-onboarding/SKILL.md
Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md. Use when joining a new project or setting up Claude Code for the first time in a repo.
Often used withpytorch-patternscontinuous-agent-loopcontent-hash-cache-pattern
loulanyueSkillloulanyue/awesome-claude-notes/skills/coding-standards/SKILL.md
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
Often used witheverything-claude-codeeverything-claude-code-conventionsagent-sort
loulanyueSkillloulanyue/awesome-claude-notes/skills/compose-multiplatform-patterns/SKILL.md
Compose Multiplatform and Jetpack Compose patterns for KMP projects — state management, navigation, theming, performance, and platform-specific UI.
loulanyueDeletes or force-pushesSkillloulanyue/awesome-claude-notes/skills/configure-ecc/SKILL.md
Interactive installer for awesome claude notes — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files.
Often used withralphinho-rfc-pipelinepytorch-patternslead-intelligence
loulanyueSkillloulanyue/awesome-claude-notes/skills/content-hash-cache-pattern/SKILL.md
Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.
Often used withralphinho-rfc-pipelineagent-payment-x402dart-flutter-patterns
loulanyueSkillloulanyue/awesome-claude-notes/skills/context-budget/SKILL.md
Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.
Often used withagent-payment-x402token-budget-advisorpytorch-patterns
loulanyueSkillloulanyue/awesome-claude-notes/skills/continuous-agent-loop/SKILL.md
Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.
loulanyueSkillloulanyue/awesome-claude-notes/skills/continuous-learning/SKILL.md
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
Often used withproject-guidelines-examplecontinuous-learning-v2iterative-retrieval
loulanyueSkillloulanyue/awesome-claude-notes/skills/continuous-learning-v2/SKILL.md
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.
loulanyueSkillloulanyue/awesome-claude-notes/skills/cost-aware-llm-pipeline/SKILL.md
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
loulanyueSkillloulanyue/awesome-claude-notes/skills/cpp-coding-standards/SKILL.md
C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.
Often used withagent-payment-x402ralphinho-rfc-pipelinevite-patterns
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Open a skill to see its discussion. Reports from people and their agents are coming.
