Agent instruction files

用 Personal Access Token 通过 GitHub REST API 分析 Actions CI 的失败 run/job/step、拉取日志、轮询运行状态、做 PR code review，并驱动 fix → push → watch → iterate 的闭环。Token 只从 GITHUBTOKEN 环境变量读取，不落盘、不回显。适合在 bifrost remote /…

bifrost-proxy/bifrost

[omh] Agent instruction file for a repo -- AGENTS.md, CLAUDE.md, a Cursor rule: write or update what an agent cannot derive from the code, inside a marked region, with every command verified or…

rlaope/oh-my-hermes

Runs Chat Customizations Evaluations analysis for the active customization file and summarizes the findings from the Problems panel.

microsoft/vscode-chat-customizations-evaluation

The single config quality skill. An agent skill from avibebuilder/claude-prime.

avibebuilder/claude-prime

Validate multi-skill workflows defined in CLAUDE.md by checking skill existence, inter-skill data contracts (JSON schema compatibility), file naming conventions, and handoff integrity.

tradermonty/claude-trading-skills

Apply Karpathy-style agentic engineering to any coding or building task.

LearnPrompt/andrej-karpathy-skills

Verify skills/graph-engineer/SKILL.md, README.md, and references/ all agree on the invariants documented in CLAUDE.md (8-node cycle, single entry point, pinned openai-codex version, DEBATE triage…

Ranteck/graph-engineer

Create, generate, update, repair, trim, or split minimal AGENTS.md files for repository roots and confirmed nested modules using progressive disclosure.

MADTeacher/mad-agents-skills

Review uncommitted code changes using parallel Claude sub-agents (Bug Hunter, Rules Auditor, optional Architect).

peterkrueck/Claude-Code-Development-Kit

维护 ZhouYiLab 仓库 skills 规范、聚合顺序及 AGENTS.md 生成脚本时使用，避免规范重复和生成文件漂移。

banderzhm/ZhouYiLab

Use this when writing or updating documentation — a README, docs/ page, CLAUDE.md, changelog entry, or doc comments — or when the user says 'document this'.

dcodesdev/LetterSpace

A skill your agent uses when the user wants to audit the memory and documents Claude Code loads into context — CLAUDE.md (user global + project + nested), MEMORY.md, @imports, .claude/skills…

AlexZio00/sovereign-skills

Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md.

affaan-m/ECC

Evaluate an agent instructions or agent definition for achievability and produce a structured, evidence-backed report artifact with per-dimension scores, findings, deterministic signals, and…

IBM/ibm-watsonx-orchestrate-adk

Adds the product layer to a repository that om-setup-agent-pipeline already configured — one yes per product role, a discovery block in .ai/agentic.config.json, the Discovery stage, Definition of…

open-mercato/skills

Find and fix the docs and agent guidance that a branch makes stale - agent skills and their reference files, AGENTS.md and .agents/.md prompts, READMEs, docs/ folders, and code-adjacent docs that…

Kiln-AI/Kiln

Moves legacy NanoClaw and Claude-native memory files into the shared memory tree and standing-instruction files, group by group, with approval before any move.

nanocoai/nanoclaw

A decision tree for an agent changing its own setup: edit memory directly, request approval for packages and MCP servers, and delegate code edits to a builder agent.

nanocoai/nanoclaw

Audit or rewrite AGENTS.md so it holds only lasting principles.

dzhng/skills

Doutrina de código do DeskcommCRM — multi-tenancy com RLS, tripla de migration, restrição de canal, eixo self-host.

melgarafael/DeskcommCRM

Creates, updates or audits CLAUDE.md files so they onboard an agent into a codebase with a short, universal set of facts rather than long style rules.

luongnv89/claude-howto

Ukrainian edition of a CLAUDE.md skill that writes, improves or audits project onboarding files for AI agents, keeping them short, universal and free of style rules.

luongnv89/claude-howto

Vietnamese version of the CLAUDE.md skill, covering create, update and audit modes, with guidance to keep the file short and put task-specific detail in separate files.

luongnv89/claude-howto

Chinese edition of the CLAUDE.md skill: create, update or audit the file, keep it within a line budget, and move detail into agent_docs references instead of code snippets.

luongnv89/claude-howto

Reviews Claude configuration files for security, structure, and prompt engineering quality.

bitwarden/ai-plugins

A skill your agent uses when creating, updating, or explaining a standing Repowire agent folder, worker folder, durable-job executor context, or reusable agent-specific AGENTS.md guidance.

prassanna-ravishankar/repowire

Initialize new project with CLAUDE.md, .knowledge/ structure, company rules, and git

Stanshy/AgentHub

Automated quality-assured commit workflow. An agent skill from Julian-adv/OpenMMO.

Julian-adv/OpenMMO

Reference for the Omnigent agent platform: agent directory layout, config.yaml fields, executor types, harness options, AGENTS.md and skill structure.

omnigent-ai/omnigent

Home Assistant Android agent instructions upkeep. An agent skill from home-assistant/android.

home-assistant/android

Create complete Claude Code workflow directories with curated skills.

nicepkg/ai-workflow

Scaffold deterministic quality gates per WORKFLOW.md §11 — pre-commit (lint, format, secret-scan), pre-push (build, unit, integration).

CorridorTech/PoseCap

Update or create documentation in the eIsland VuePress docs site (web/eisland-web-docs).

JNTMTMTM/eIsland

This skill should be used when creating, refreshing, or validating a repository AGENTS.md so it stays concise, current, and grounded in repository evidence.

alchemiststudiosDOTai/harness-engineering

Audits a repository's agent-readable context, from AGENTS.md and CLAUDE.md to skills and PRODUCT or TECH specs, and recommends the smallest useful improvements.

majiayu000/spellbook

Required before adding or changing anything an agent reads — a convention in AGENTS.md, a procedure as a skill, a pattern-scoped rule.

epam/cloud-pipeline

Installs, refreshes or repairs oh-my-claudecode for plugin, npm and local-dev installs through a phased setup flow with help, local, global and force flags.

Yeachan-Heo/oh-my-claudecode

Review uncommitted local changes in the current git working tree for bugs, smells, missing tests, and CLAUDE.md voice violations.

timothywarner-org/claude-code

Audit and improve project-rules files (AGENTS.md, CLAUDE.md, .agents/instructions, local overrides) so the agent keeps accurate project context.

waybarrios/opencode-power-pack

Audit the instructions an agent already carries — CLAUDE.md, AGENTS.md, skills, tool descriptions — for contradictions, over-constraint, and duplication, then propose a cut list.

Neeeophytee/finding-unknowns-skills

Scaffold a new SciAgent-Skills entry. An agent skill from jaechang-hits/SciAgent-Skills.

jaechang-hits/SciAgent-Skills

Conduct a thorough code review of the current Git branch or specific files in Megingiard.

stormpanda/megingiard

Diagnose and strengthen a repository's harness layer: AGENTS.md rules, knowledge layout, architecture boundaries, lint and type gates, API and generated-client contracts, test scaffolding…

PacificStudio/openase

Guides development workflow, design system, scripts, and component inventory for @ant-design/agentic-ui.

antdigital-ai/agentic-ui

Update project documentation after code changes. An agent skill from peterkrueck/Claude-Code-Development-Kit.

peterkrueck/Claude-Code-Development-Kit

Unified memory management - CLAUDE.md updates and documentation generation with interactive routing.

catlog22/Claude-Code-Workflow

Migrate ANY cortextOS agent from the claude-code runtime to the live codex-app-server runtime.

grandamenium/cortextos

Analyzes recent sessions for corrections, preferences and implicit feedback, then routes the real learnings to the right knowledge or rules file.

mp-web3/claude-starter-kit