Topic · Agent Workflows
Best agent instruction files skills, page 11
Agent instruction files skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 481 | 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/ | 1k | — | ~502 | Automated safety check: Pass | MIT | yesterday |
| 482 | 482.Scan Scans the codebase to generate project-doc.md and AGENTS.md. | wshobson/ | 40k | — | ~2.2k | Automated safety check: Pass | MIT | 4 days ago |
| 483 | 483.Scorecard Show the CLAUDE.md compliance scorecard: which rules Claude actually follows vs ignores | karanb192/ | 533 | — | ~231 | Automated safety check: Pass | MIT | 5 days ago |
| 484 | 484.Aris Register Register or update an ARIS run on the web dashboard. An agent skill from CurryTang/Amadeus. | CurryTang/ | 176 | — | ~1.3k | Automated safety check: Pass | No licence | 6 mo ago |
| 485 | 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/ | 886 | — | ~1.9k | Automated safety check: Pass | MIT | 2 days ago |
| 486 | 486.Clarify Docs TRIGGER when: asked to clarify or improve existing documentation, PR drafts or issue descriptions, including URLs and pasted bodies. | serpro69/ | 151 | — | ~1.2k | Automated safety check: Pass | Unknown | today |
| 487 | 487.Project Init 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/ | 717 | — | ~1k | Automated safety check: Pass | MIT | yesterday |
| 488 | Create or audit ECL Agent Harness infrastructure: AGENTS.md, change tracking, repository guidance, lint checks, CI gates, and agent handoff docs. | sickn33/ | 47k | 1 repo | ~623 | Automated safety check: Pass | MIT | today |
| 489 | 489.Dotnet Init Interactive project initialization. An agent skill from codewithmukesh/dotnet-claude-kit. | codewithmukesh/ | 755 | — | ~1.7k | Automated safety check: Pass | MIT | 2 mo ago |
| 490 | Decide whether a rule belongs in an AGENTS.md / CLAUDE.md file, and write it so it holds. | PostHog/ | 40k | — | ~2k | Automated safety check: Pass | Unknown | today |
| 491 | 491.Harvest Capture durable session learnings, stage for human promotion to 05-knowledge/lizard, and propose skill/CLAUDE.md patches. | huytieu/ | 1.3k | — | ~609 | Automated safety check: Pass | MIT | 7 days ago |
| 492 | 새 프로젝트를 시작할 때 자동으로 PRD, CLAUDE.md, Wiki, 마일스톤을 생성하세요. An agent skill from imgompanda/fireauto. | imgompanda/ | 140 | — | ~400 | Automated safety check: Pass | MIT | 6 mo ago |
| 493 | Scans the session for lessons and workflows, then proposes scoped CLAUDE.md edits. | jamditis/ | 417 | — | ~904 | Automated safety check: Pass | MIT | 4 days ago |
| 494 | 494.Refactor Memory 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/ | 138 | — | ~887 | Automated safety check: Pass | MIT | yesterday |
| 495 | 495.Md Starter 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/ | 139 | — | ~2k | Automated safety check: Pass | MIT | 3 mo ago |
| 496 | 496.Split Memory Modular AGENTS.md management strategy for projects that outgrow a single instruction file. | Resgrid/ | 229 | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | today |
| 497 | 497.Agent Md Advisor 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/ | 740 | — | ~915 | Automated safety check: Pass | Unknown | today |
| 498 | 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/ | 740 | — | ~982 | Automated safety check: Pass | Unknown | today |
| 499 | 499.Add Task TRIGGER when user asks to add a workflow step, agent step, agentic task, task endpoint, or workflow phase. | microbus-io/ | 172 | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | 11 days ago |
| 500 | This skill should be used when working with Claude Code infrastructure including agents, skills, slash commands, hooks, plugins, settings.json, or CLAUDE.md files. | closedloop-ai/ | 122 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | today |
| 501 | Adopt repository-level harness engineering for coding agents. | github/ | 40k | — | ~2k | Automated safety check: Pass | MIT | today |
| 502 | 502.Agents Md Revise Capture learnings from the current session into the project-rules file (AGENTS.md, CLAUDE.md, or local override) so future sessions benefit. | waybarrios/ | 533 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 503 | When the user repeats the same correction or convention multiple times, suggest a Cursor rule to encode it permanently. | spencerpauly/ | 843 | — | ~544 | Automated safety check: Pass | CC0-1.0 | 2 mo ago |
| 504 | Structure and abstraction rules for PostHog UI code — any React component or frontend file under frontend/src/ or products//frontend/. | PostHog/ | 40k | — | ~4.1k | Automated safety check: Pass | Unknown | today |
| 505 | 505.Manage Skills 세션 변경사항을 분석하여 검증 스킬 누락을 탐지합니다. An agent skill from sangrokjung/claude-forge. | sangrokjung/ | 852 | — | ~2.8k | Automated safety check: Pass | MIT | 1 mo ago |
| 506 | 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/ | 1.9k | — | ~386 | Automated safety check: Pass | MIT | today |
| 507 | 507.Doc Sync 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/ | 1.6k | — | ~1.7k | Automated safety check: Notes | MIT | 9 days ago |
| 508 | 508.Sync Agent 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/ | 116 | — | ~893 | Automated safety check: Pass | Apache-2.0 | today |
| 509 | Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to agents-memory-updater. | cursor/ | 10k | — | ~159 | Automated safety check: Pass | No licence | yesterday |
| 510 | 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/ | 276k | — | ~270 | Automated safety check: Pass | MIT | 4 days ago |
| 511 | 511.Review Steering 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/ | 125 | — | ~1.1k | Automated safety check: Pass | No licence | 2 mo ago |
| 512 | Write or audit AGENTS.md/CLAUDE.md instructions. An agent skill from pedronauck/skills. | pedronauck/ | 634 | 1 repo | ~769 | Automated safety check: Pass | No licence | 24 days ago |
| 513 | 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/ | 32k | — | ~5k | Automated safety check: Pass | CC-BY-4.0 | today |
| 514 | 514.SEO Analitica Skills para otimização de SEO técnico, análise de dados, criação de dashboards e inteligência de negócio para empresas brasileiras. | ricneves-ai/ | 115 | — | ~2.3k | Automated safety check: Pass | MIT | 13 days ago |
| 515 | 515.Context Audit 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/ | 31k | — | ~3.2k | Automated safety check: Pass | MIT | today |
| 516 | House cold-start interview (request list + prior memo), or --new-deal for deal-specific context. | anthropics/ | 9.6k | 2 repos | ~10k | Automated safety check: Pass | Apache-2.0 | 9 days ago |
| 517 | Cold-start setup — learns your jurisdictional footprint and escalation rules from your handbook and termination memos. | anthropics/ | 9.6k | 2 repos | ~8k | Automated safety check: Pass | Apache-2.0 | 9 days ago |
| 518 | 518.Honey Memory Create and maintain one committed per-project memory file (PROJECT.md) so agents stop re-discovering the same facts every cold session. | Green-PT/ | 313 | — | ~950 | Automated safety check: Pass | MIT | 1 mo ago |
| 519 | 519.Setup Deploy Configure deployment settings for /land-and-deploy. An agent skill from mr-daedalium/ostack-saas. | mr-daedalium/ | 114 | — | ~4.5k | Automated safety check: Notes | MIT | 6 mo ago |
| 520 | 520.Release It Apply Michael T. An agent skill from ciembor/agent-rules-books. | ciembor/ | 2.9k | — | ~174 | Automated safety check: Pass | MIT | 29 days ago |
| 521 | Reference: review of an inbound vendor agreement against the team playbook in ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md. | anthropics/ | 9.6k | 1 repo | ~5.9k | Automated safety check: Pass | Apache-2.0 | 9 days ago |
| 522 | 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/ | 740 | — | ~10k | Automated safety check: Pass | Unknown | today |
| 523 | Coordinate complex Rudder delivery when concurrent integration, runtime/data identity, or release gates require a machine-readable evidence packet. | Undertone0809/ | 292 | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | today |
| 524 | 524.Superself A skill your agent uses when a project keeps its state in Superself (a <!-- superself:begin block in AGENTS.md or CLAUDE.md, or self setup resolves the directory to a registered project): read self… | wshobson/ | 40k | — | ~1.3k | Automated safety check: Pass | MIT | 4 days ago |
| 525 | 525.Aif Rules Check Run a standalone read-only rules compliance gate against changed files or a git ref. | unxed/ | 241 | — | ~2.4k | Automated safety check: Pass | BSD-3-Clause | today |
| 526 | Create or review an AGENTS.md file so coding agents get stable repo-local instructions: environment setup, testing, style, security boundaries, PR policy, and handoff rules. | stevesolun/ | 588 | — | ~447 | Automated safety check: Pass | MIT | 5 days ago |
| 527 | 527.Nav Sync Claude Sync project CLAUDE.md to the installed Navigator version, preserving customizations. | qf-studio/ | 355 | — | ~3k | Automated safety check: Notes | MIT | today |
| 528 | 528.Nav Upgrade Automates Navigator plugin updates. An agent skill from qf-studio/navigator. | qf-studio/ | 355 | — | ~4.6k | Automated safety check: Notes | MIT | today |
Explore related skills
Category
More topics in Agent Workflows
- MCP servers2,050
- Subagents1,014
- Multi-agent orchestration526
- Agent memory509
- Skill authoring499
- Planning497
- Brainstorming461
- Hooks and plugins353
- Autonomous loops323
- Context engineering299
- Session handoff259
- Requirements gathering229
- Task breakdown224
- Human-in-the-loop approvals201
- Skill management196
- Codebase knowledge for agents189
- Verification before completion171
- Agent evaluation and testing131