Best agent instruction files skills, page 8

All-in-one project configuration and health management. An agent skill from jezweb/claude-skills.

jezweb/claude-skills

Initialize or extend an Agent from a user requirement - write AGENTS.md, set identity metadata, and create, install or import Skills and hook packages (scripts the harness runs on every prompt…

Prism-Shadow/penguin-harness

Reference for writing briefs to a subagent or a fork: what context to include, what never to delegate, and how a custom subagent's definition limits the prompt.

QwenLM/qwen-code

把长期项目的文档当成一个小系统来维护，防止文档腐烂——四份各司其职的脊柱文件（CLAUDE.md 共享章程 / CLAUDEMAP.md 地图 / PROJECTSTATUS.md 健康仪表盘 / PROJECTLOG.md 流水账）+ Codex 的 AGENTS.md 入口桥接 + 固定读序，并按需连接 ARCHITECTURE、CONTEXT、ADR、契约、测试、回归和 Issue…

qshanx/docs-governance

Developer-experience friction auditing and fixing — slow onboarding, repeated manual setup steps, missing bootstrap/reset/seed scripts, undiscoverable conventions.

pproenca/dot-skills

Bridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execution helpers, and enables seamless interoperability between both tools

alirezarezvani/claude-code-skill-factory

Turns mistakes you correct into proposed updates to persistent Rules and Skills so the same error does not recur in later sessions, triggered automatically or with /reflect.

davidYichengWei/agentic-engineering-framework

Review code for logging patterns and suggest evlog adoption.

evloghq/evlog

A skill your agent uses when writing, completing, improving, or adapting SKILL.md and agents/.md in a bundle-plugin — integrating external skills, filling scaffolded stubs, or rewriting for better…

OdradekAI/bundles-forge

使用AgentShield扫描您的Claude代码配置（.claude/目录），以发现安全漏洞、配置错误和注入风险。检查CLAUDE.md、settings.json、MCP服务器、钩子和代理定义。

affaan-m/ECC

Explains how the Codex Rules plugin injects project instructions and file-specific rules into a session, which rule files it reads and which settings control it.

code-yeongyu/oh-my-openagent

Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude…

AI-Builder-Club/skills

Sets up a shared repo environment for people and agents: CLAUDE.md, a CONTEXT.md glossary, ADRs, standards and a design-system folder, and audits drift with --check.

Yeachan-Heo/oh-my-claudecode

用户说“第一次接管这个项目”“分析仓库并生成项目规则”时使用。分析已有代码并生成 Codex AGENTS.md 与 CM/Claude 兼容规则；仅适用于非空存量项目，不创建脚手架、不承接普通代码修改。

kingxiaozhe/cm-workflow

Translate and sync bilingual user documentation between docs/zh/ and docs/en/ following the source-of-truth rules in docs/AGENTS.md.

MoonshotAI/kimi-code

把"已提交但尚未真机验证"的改动登记成 GitHub issue,避免未验收当已完成。当改动触碰 AGENTS.md 要求真机验收的运行时/UI 行为,但验证被阻塞(没拿到部署授权、或用户选择先提交后验证)时使用。

jinzhongjia/decky-music

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

JNTMTMTM/eIsland

Initialize a Harness Engineering framework in the current project.

kangarooking/kangarooking-skills

Designs multi-agent topologies that run on OpenRig: writes RigSpec and AgentSpec files and agent startup content, and diagnoses rigs whose agents misbehave.

mvschwarz/openrig

Generate AGENTS.md at the repo root by scanning the codebase first, pre-filling placeholders from observed signals, and asking only the genuine gaps.

CorridorTech/PoseCap

Audits a project's agent rule files, picks a source of truth and generates bridges so Claude Code, Codex, Grok and generic agents all see one structure, in Chinese.

dontbesilent2025/dbskill

A skill your agent uses when writing, reviewing, restoring, trimming, or auditing prose in this repository, including deciding where documentation or comments are required across Markdown, Rust doc…

inclusionAI/Choruz

Create or reshape a Python FastAPI service repo into the specx clean core/delivery architecture using packaged scoped foundation bases.

maksimzayats/specx

Expert code simplification and refactoring specialist that autonomously enhances code clarity, consistency, and maintainability while preserving exact functionality.

chendongqi/OPB-Skills

Trae 项目规范化配置专家。用于快速初始化 Trae 项目配置文件、生成项目规则、用户偏好设置和 Skill 模板。当用户需要：(1) 初始化新项目的 Trae 配置 (2) 生成 .trae 目录结构 (3) 创建 USERPREFERENCES.md 用户偏好文件 (4) 创建 projectrules.md 项目规则文件 (5) 创建新的 Skill 模板 时使用此 Skill。

boshi-xixixi/TraeSkill

Writing standards for documents that agents read in order to act, such as CLAUDE.md, specs and tickets, so a fresh session can follow them without chat history.

Yeachan-Heo/oh-my-claudecode

Reads an agent environment's own traces, friction reports and logs across sessions, then proposes fixes on the surface that owns each one, only with your approval.

Yeachan-Heo/oh-my-claudecode

Audits and edits agent instruction files, verifies repository commands, and migrates repositories to AGENTS.md as the single shared source.

mblode/agent-skills

Claude Code Hero Level 2: The Tome of First Instructions -- create .claude/CLAUDE.md with real personal instructions

kylesnowschwartz/claude-code-hero

Creates or changes a druxt.js contributor skill in .agents/skills, with its evals and the tests that gate it.

druxt/druxt.js

Scaffold a new book project — folders, memoir-based LaTeX skeleton, custom style with voiced sidebars, bibliography stub, CLAUDE.md, README, and a chapter-per-file structure that converts cleanly to…

scunning1975/MixtapeTools

Angular framework reference for building this signals-first, headless directive library.

radix-ng/primitives

Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source.

dyoshikawa/rulesync

Zed editor configuration expert. An agent skill from wcygan/dotfiles.

wcygan/dotfiles

Guides creating and editing custom agents for the code-forge application as Markdown files with YAML frontmatter in the project's .forge/agents folder.

tailcallhq/forgecode

Explains how the aspens generator routes output to Claude Code or Codex CLI targets and transforms generated skills and instruction files between their formats.

aspenkit/aspens

Writing documents for agents. An agent skill from openchamber/openchamber.

openchamber/openchamber

How to update an existing docouture documentation site when a feature, change, deprecation or fix lands in the repo — figuring out what's affected from a diff/commit/PR, confirming with the user…

InditexTech/weavejs

将 mattpocock/skills 的内容翻译、刷新或复核到简体中文本地化仓库 vinvcn/mattpocock-skills-zh-CN 时使用这个项目级 skill。适用于 skill files、README content、CLAUDE.md、GLOSSARY.md、docs，以及其他需要保留行为关键 identifiers 的上游用户可见内容。

vinvcn/mattpocock-skills-zh-CN

Configures a game project's engine and version, pins them in CLAUDE.md and uses web search to build reference docs when the version is newer than the model knows.

Donchitos/Claude-Code-Game-Studios

AgentShield を使用して、Claude Code の設定（.claude/ ディレクトリ）のセキュリティ脆弱性、設定ミス、インジェクションリスクをスキャンします。CLAUDE.md、settings.json、MCP サーバー、フック、エージェント定義をチェックします。

affaan-m/ECC

Load the practitioner's global rules — the host's CLAUDE.md or AGENTS.md, symlinks resolved — and reinforce them by listing their topics in the conversation, alongside whatever the repo and the…

alexandremendoncaalvaro/CorridorKey-Runtime

Guides writing an agents.md project-context file: plain markdown with no frontmatter, focused on what an AI coding assistant cannot already know.

pr-pm/prpm

Decide where a learning, gotcha, or decision should live so it is not lost, and capture it there while context is fresh.

citypaul/.dotfiles

使用本机 fleet 分派 Codex GPT-6.1 Sol、Gemini、Grok 或 JEV 任务，或调用 Kollab 图片/视频/音频/多模态能力时使用；包括用户点名 agent-fleet、Nano Banana、nanobanana、香蕉、便宜模型、多模型并行，用户说“让 Codex 或 GPT-6.1 Sol 做某事”的编码、调研与 review 派单，以及按全局…

yan-labs/yan-skills

Prevent AI style drift on legacy projects by scanning the codebase for implicit conventions, resolving conflicts with the operator one at a time, and writing an enforceable .ai-style-rules.md…

affaan-m/ECC

Design or audit a repo-local markdown knowledge graph with wiki links, source-code backlinks, drift checks, and searchable sections.

stevesolun/ctx

Two-axis fresh-context code review per WORKFLOW §10. An agent skill from CorridorTech/PoseCap.

CorridorTech/PoseCap