Agent instruction files

Audit named agent instructions, tool definitions, and supported Python prompts with local LintLang checks; return finding codes and locations without changing files.

sickn33/agentic-awesome-skills

Find which APIs of a project's pinned Python dependencies changed after the model's training cutoff, where the code uses them, and write short AGENTS.md or CLAUDE.md notes.

sickn33/agentic-awesome-skills

Run the cold-start interview — learns your privacy practice and writes CLAUDE.md from your policy, DPA template, and a reference PIA.

anthropics/claude-for-legal

reddi.tech fork of self-improving-agent. An agent skill from LeoYeAI/openclaw-master-skills.

LeoYeAI/openclaw-master-skills

A skill your agent uses when the user asks to generate or update a project's CLAUDE or AGENTS context file from a codebase scan.

Varnan-Tech/opendirectory

Set up or update a project in the vault: the four-stage folder pipeline, a project-scoped CLAUDE.md with one goal, and links to the concept pages it depends on.

undefined-ui/second-brain-os

Show the CLAUDE.md compliance scorecard: which rules Claude actually follows vs ignores

karanb192/claude-code-hooks

Scans the codebase to generate project-doc.md and AGENTS.md.

wshobson/agents

A skill your agent uses when the user asks to "optimize CLAUDE.md", "create a new skill", "write a custom agent", "configure hooks", "manage context window", "set up MCP servers", "scaffold a skill…

borghei/Claude-Skills

Register or update an ARIS run on the web dashboard. An agent skill from CurryTang/Amadeus.

CurryTang/Amadeus

TRIGGER when: asked to clarify or improve existing documentation, PR drafts or issue descriptions, including URLs and pasted bodies.

serpro69/claude-toolbox

项目初始化工具。读取全局协议 ~/.claude/CLAUDE.md，分析项目实际情况，生成项目特定的 CLAUDE.md 和 docs/ 上下文。本技能应在用户说"初始化项目"、"项目设置"、"配置 Claude Code"、"新建项目配置"时使用，或在进入一个新项目需要快速配置时使用。不要用于：Skill 内容开发或验收（用 skill-lint）、单次 Skill 安装（用…

cat-xierluo/legal-skills

Create or audit ECL Agent Harness infrastructure: AGENTS.md, change tracking, repository guidance, lint checks, CI gates, and agent handoff docs.

sickn33/agentic-awesome-skills

Interactive project initialization. An agent skill from codewithmukesh/dotnet-claude-kit.

codewithmukesh/dotnet-claude-kit

Decide whether a rule belongs in an AGENTS.md / CLAUDE.md file, and write it so it holds.

PostHog/posthog

Capture durable session learnings, stage for human promotion to 05-knowledge/lizard, and propose skill/CLAUDE.md patches.

huytieu/COG-second-brain

새 프로젝트를 시작할 때 자동으로 PRD, CLAUDE.md, Wiki, 마일스톤을 생성하세요. An agent skill from imgompanda/fireauto.

imgompanda/fireauto

A skill your agent uses when refactoring Claude Code or Codex memories to remove stale or derivable entries, resolve contradictions, promote standing instructions, or reorganize recall.

vinta/hal-9000

Scans the session for lessons and workflows, then proposes scoped CLAUDE.md edits.

jamditis/claude-skills-journalism

Modular AGENTS.md management strategy for projects that outgrow a single instruction file.

Resgrid/Core

Generates a fully structured, project-specific CLAUDE.md by scanning the repo for signal files (package.json, Makefile, .github/workflows/, .env.example, etc.), inferring stack, commands…

Infrasity-Labs/dev-gtm-claude-skills

AGENTS.md / CLAUDE.md 最佳实践顾问。用于用户询问 agents markdown、AGENTS.md、CLAUDE.md、Claude Code memory、AI coding agent 指令文件的格式、结构、最佳实践；也用于审查、诊断、重写、优化或从零创建 AGENTS.md、CLAUDE.md、CLAUDE.local.md、.claude/rules 等…

chujianyun/skills

审查或设计 Claude Code 项目配置。用于用户提到 .claude、CLAUDE.md、Claude 配置文件、项目级 Claude 自定义配置、配置结构是否合理、该创建哪些配置文件，或希望从零规划 Claude 配置时使用。默认先审查或诊断，再给方案；只有用户明确要求时，才进一步输出推荐结构或样例文件。

chujianyun/skills

TRIGGER when user asks to add a workflow step, agent step, agentic task, task endpoint, or workflow phase.

microbus-io/fabric

This skill should be used when designing prompts, system prompts, or context windows for Claude.

closedloop-ai/claude-plugins

Adopt repository-level harness engineering for coding agents.

github/awesome-copilot

Capture learnings from the current session into the project-rules file (AGENTS.md, CLAUDE.md, or local override) so future sessions benefit.

waybarrios/opencode-power-pack

When the user repeats the same correction or convention multiple times, suggest a Cursor rule to encode it permanently.

spencerpauly/awesome-cursor-skills

Structure and abstraction rules for PostHog UI code — any React component or frontend file under frontend/src/ or products//frontend/.

PostHog/posthog

세션 변경사항을 분석하여 검증 스킬 누락을 탐지합니다. An agent skill from sangrokjung/claude-forge.

sangrokjung/claude-forge

Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to agents-memory-updater.

cursor/plugins

The evlog content doctrine, for anyone drafting or judging evlog prose: a docs page, the landing, a blog post, a package README, a skill, an AGENTS.md, a changeset.

evloghq/evlog

Before merge, mechanize Documentation-First — derive the code delta from git diff, then verify required docs are in sync (CHANGELOG, docs/api, CLAUDE.md/ROADMAP).

Prismer-AI/PrismerCloud

基于 VLink 当前代码、doc、目录、工具和 GitHub 工作流事实,审计并同步 AGENTS.md、AI-POLICY.md、Copilot 指令、.agents 路由/索引/语言分册/ CI 说明、skill frontmatter、agents/openai.yaml 与 README 清单.用户 要求"同步 Agent 文件"、"根据代码更新 .agents"、"检查…

thun-res/vlink

不慣れなコードベースを分析し、アーキテクチャマップ、主要なエントリポイント、規約、スターターCLAUDE.mdを含む構造化オンボーディングガイドを生成します。新しいプロジェクトに参加するか、リポでClaude Codeを初めてセットアップする場合に使用します。

affaan-m/ECC

Compiles REVIEW.md and keeps CLAUDE.md accurate as the two sanctioned surfaces for steering Anthropic's managed Code Review service, translating this repo's rules into terse reviewer imperatives.

dralgorhythm/claude-agentic-framework

Write or audit AGENTS.md/CLAUDE.md instructions. An agent skill from pedronauck/skills.

pedronauck/skills

Audit a codebase and bind every claim it makes about itself to a mechanism that fails when the claim stops being true, so it is legible to people and AI agents.

davila7/claude-code-templates

Skills para otimização de SEO técnico, análise de dados, criação de dashboards e inteligência de negócio para empresas brasileiras.

ricneves-ai/flowgrammers-skills

Token-hygiene audit of the always-loaded context stack — CLAUDE.md, AGENTS.md, auto-memory MEMORY.md, and the bootstrap-rendered identity files (SOUL.md, USER.md, ACCESSPOLICY.md, HEARTBEAT.md) or…

garrytan/gbrain

House cold-start interview (request list + prior memo), or --new-deal for deal-specific context.

anthropics/claude-for-legal

Cold-start setup — learns your jurisdictional footprint and escalation rules from your handbook and termination memos.

anthropics/claude-for-legal

Create and maintain one committed per-project memory file (PROJECT.md) so agents stop re-discovering the same facts every cold session.

Green-PT/honey-for-devs

Apply Michael T. An agent skill from ciembor/agent-rules-books.

ciembor/agent-rules-books

Configure deployment settings for /land-and-deploy. An agent skill from mr-daedalium/ostack-saas.

mr-daedalium/ostack-saas

Reference: review of an inbound vendor agreement against the team playbook in ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md.

anthropics/claude-for-legal

A skill your agent uses when the user or project explicitly adopts hexagonal (ports and adapters) architecture — a README, CLAUDE.md, or ADR that says so is the opt-in.

citypaul/.dotfiles

Coordinate complex Rudder delivery when concurrent integration, runtime/data identity, or release gates require a machine-readable evidence packet.

Undertone0809/rudder