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

loulanyueSkill

documentation-lookup

loulanyue/awesome-claude-notes/.cursor/skills/documentation-lookup/SKILL.md

Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).

Often used witheverything-claude-code-conventions·agent-sort·mle-workflow

loulanyueSkill

frontend-slides

loulanyue/awesome-claude-notes/.cursor/skills/frontend-slides/SKILL.md

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

Often used witheverything-claude-code·everything-claude-code-conventions·nextjs-turbopack

loulanyueSkill

investor-materials

loulanyue/awesome-claude-notes/.cursor/skills/investor-materials/SKILL.md

Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.

Often used withbrand-discovery·configure-ecc·ralphinho-rfc-pipeline

loulanyueSkill

investor-outreach

loulanyue/awesome-claude-notes/.cursor/skills/investor-outreach/SKILL.md

Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.

Often used witheverything-claude-code-conventions·agent-sort·bun-runtime

loulanyueSkill

market-research

loulanyue/awesome-claude-notes/.cursor/skills/market-research/SKILL.md

Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.

Often used witheverything-claude-code·everything-claude-code-conventions·nextjs-turbopack

loulanyueSkill

mcp-server-patterns

loulanyue/awesome-claude-notes/.cursor/skills/mcp-server-patterns/SKILL.md

Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.

Often used witheverything-claude-code-conventions·agent-sort·brand-voice

loulanyueSkill

nextjs-turbopack

loulanyue/awesome-claude-notes/.cursor/skills/nextjs-turbopack/SKILL.md

Next.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.

Often used witheverything-claude-code-conventions·agent-sort·brand-voice

loulanyuellms.txt

awesome-claude-notes

loulanyue/awesome-claude-notes/llms.txt

Independent community distribution of AI coding workflow assets derived from affaan-m/ECC, focused on Chinese documentation, packaging, and cross-harness use. Core documentation: - README.md - ROADMAP.md - GOVERNANCE.md - UPSTREAM.md - CONTRIBUTING.md - TROUBLESHOOTING.md - docs/SELECTIVE-INSTALL-ARCHITECTURE.md Core assets: - agents/ - commands/ - skills/ - hooks/ - rules/ - mcp-configs/ - manifests/ CLI entry points: - npx ecc <language> - npx ecc-install <language> - node scripts/install-plan.js --profile <name> --target <harness> - node scripts/install-apply.js --profile <name> --target <harness> Provenance and support: -…

loulanyueSkill

agent-eval

loulanyue/awesome-claude-notes/skills/agent-eval/SKILL.md

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

loulanyueSkill

agent-harness-construction

loulanyue/awesome-claude-notes/skills/agent-harness-construction/SKILL.md

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

Often used withagent-payment-x402·token-budget-advisor·parallel-execution-optimizer

loulanyueSkill

agentic-engineering

loulanyue/awesome-claude-notes/skills/agentic-engineering/SKILL.md

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

Often used withaegis-gateway·dart-flutter-patterns·agent-payment-x402

loulanyueSkill

ai-first-engineering

loulanyue/awesome-claude-notes/skills/ai-first-engineering/SKILL.md

Engineering operating model for teams where AI agents generate a large share of implementation output.

loulanyueSkill

android-clean-architecture

loulanyue/awesome-claude-notes/skills/android-clean-architecture/SKILL.md

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns.

loulanyueSkill

api-design

loulanyue/awesome-claude-notes/skills/api-design/SKILL.md

REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.

loulanyueSkill

architecture-decision-records

loulanyue/awesome-claude-notes/skills/architecture-decision-records/SKILL.md

Capture architectural decisions made during Claude Code sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale. Maintains an ADR log so future developers understand why the codebase is shaped the way it is.

Often used withpytorch-patterns·content-hash-cache-pattern·ralphinho-rfc-pipeline

loulanyueSkill

autonomous-loops

loulanyue/awesome-claude-notes/skills/autonomous-loops/SKILL.md

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

loulanyueSkill

benchmark

loulanyue/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-clean·pair-agent·landing-report

loulanyueSkill

blueprint

loulanyue/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".

loulanyueSkill

browser-qa

loulanyue/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.

loulanyueSkill

canary-watch

loulanyue/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 -…