Best agent instruction files skills, page 5

Runs as the last step after a completed change to keep AGENTS.md files, the project scope and linked spec status lines current, using only small surgical edits.

jsmastery-pro/skills

Sets up a project for Claude Code by surveying it and writing a .claude folder with a short CLAUDE.md, a CODEBASE.md overview, module docs and optional skills and hooks.

mp-web3/claude-starter-kit

Applies the fixes suggested by the Chat Customizations Evaluations extension to a prompt, agent, skill or instruction file, changing only what each diagnostic requires.

microsoft/vscode-chat-customizations-evaluation

Create or update AGENTS.md for this repository. An agent skill from 0xku/kon.

0xku/kon

Builds or refreshes a personal -mode skill that captures how you work, using patterns mined from your recent agent transcripts in the current workspace.

cursor/plugins

Generate a new Godot game project with standardized ECS structure and tooling.

RandallLiuXin/GodotMaker

Create or update a pull request for the current branch. An agent skill from bikeindex/bike_index.

bikeindex/bike_index

Generate AGENTS.md files for Go, Rust, TypeScript, and Java projects.

dimetron/pi-go

A skill your agent uses when: initializing, auditing, or optimizing repository AI guidance, including AGENTS.md/CLAUDE.md bridges, Agent Skills, trigger descriptions, progressive disclosure, source…

owent/libatbus

為 Twinkle Eval 新增一個評測 benchmark（IFEval、BFCL、RAGAS、Text2SQL、Vision MCQ 之類）。涵蓋 CLAUDE.md §6 的完整強制流程：先建 Milestone 與 6 個 Issue、準備 example dataset、實作 Extractor + Scorer 並註冊 PRESETS、與參考框架做分數與速度對比、撰寫…

ai-twinkle/Eval

Refactor CLAUDE.md files to follow progressive disclosure principles.

brianlovin/agent-config

Take the current branch from done-coding to merge-ready in one pass — review the diff against AGENTS.md, deslop, commit and push, open a PR using rule-validate's PR copy, then babysit until mergeable.

millionco/react-doctor

Code style, commenting, and documentation conventions for the Campfire codebase.

pandulapeter/campfire

Lint AI agent instruction files (SKILL.md, CLAUDE.md, AGENTS.md, GEMINI.md), tool definitions, system prompts, and agent configs with the deterministic LintLang CLI.

hermes-labs-ai/lintlang

在项目 AGENTS.md 约束下生成可直接交给 Codex 或 Agent 执行的中文任务 prompt。用于开发、修复、文档、验证、审计、治理或交接任务的 prompt 化，但不承载 Plan mode 和 code review 的完整模式规则。

Philip-Cao-9527/code-note-helper

Audit every CLAUDE.md in this project for drift against the last week of git history.

alirezarezvani/ClaudeForge

Audit an agent's harness against the four rings: containment, guides, sensors, permissions.

undefined-ui/second-brain-os

Audits your Claude Code settings and environment variables against the current official docs and returns a ranked list of changes tied to how you actually work.

vinta/hal-9000

Creates and structures custom command files for the code-forge CLI, with YAML frontmatter plus special tags for automated lint and test steps.

tailcallhq/forgecode

Build and review high-quality technical docs as well as agent instruction files in your repository.

openclaw/openclaw

Bootstrap a new project or experiment directory with README and optional AGENTS.md files.

jxnl/personal-monorepo-template

Every AGENTS.md must have a sibling CLAUDE.md symlink pointing to it.

pdparchitect/noodle

Judges a pasted tip, post or video summary against what the kipi system already has, and returns adopt, skip or already-built with the files that back the verdict.

assafkip/kipi-system

Transform legacy codebases into AI-ready projects with Claude Code configurations.

nicepkg/ai-workflow

Universal NL conventions: SKILL.md open spec, AGENTS.md, vague quantifiers, naming.

xiaolai/nlpm

Sets up or incrementally updates AGENTS.md and CLAUDE.md for legal professionals, with a minimal safety baseline and a check that a new session loads and follows the rules.

cat-xierluo/legal-skills

Audit and fix all Lattice documentation, README, docs/, PROJECT.md, GitHub issue templates, and CLAUDE.md to ensure they are fully aligned with the current skill inventory.

techygarg/lattice

A skill your agent uses when the user invokes /rpa-gen-rules or asks to create, refresh, audit, or synchronize project instructions such as root AGENTS.md, Cursor .cursor/rules, or Claude Code…

coddy-project/coddy-agent

Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles.

meshery/meshery-operator

Catalog of obstacles, anti-patterns and patterns for working with AI coding agents, covering context management and reliability, from a published patterns collection.

lexler/skill-factory

Audit Serial Studio's AI-facing material (CLAUDE.md, doc/claude/, .claude/skills/, and optionally the in-app assistant corpus under app/rcc/) against code ground truth.

Serial-Studio/Serial-Studio

Athena 全局偏好便利层。直接操作 CC 原生 ~/.claude/settings.json 的 permissions.allow/deny 和全局 CLAUDE.md。

m-xlsea/ruoyi-plus-soybean

配置项目的游戏引擎和版本。将引擎锁定到 CLAUDE.md 中，检测知识缺口，当版本超出 LLM 训练数据时通过 WebSearch 填充引擎参考文档。

pixel-cellar/Claude-Code-Game-Studios

Interview-based project setup — generates CLAUDE.md, ROADMAP, .gitignore, .env.example from scratch.

AlexZio00/sovereign-skills

Audits the instruction files (CLAUDE.md, .claude/rules, .claude/skills, tools/measuredax/CLAUDEWINDOWS.md) for accuracy and bloat against .claude/rules/instructions.md, and proposes a concrete edit…

antoinecellerier/speaker-tuning-to-easyeffects

Use BEFORE editing any file in supabase/migrations/ or supabase/schemas/, OR when the user runs a /database subcommand (compact local migration, rls scenarios, align).

gridaco/grida

Create, restructure, review, audit, or migrate Choruz Markdown documentation (docs/, README, AGENTS.md, the in-app docs pages) using one owner per fact, tier placement, executed-operation…

inclusionAI/Choruz

Extract your persona into CLAUDE.md or AGENTS.md for use in any AI agent

LilMGenius/polysona

Find and safely apply ONE worthwhile code optimization (reuse, simplification, efficiency, or a dead-weight cleanup) somewhere in packages//src, with new regression tests proving behavior is…

openplayerjs/openplayerjs

Sets up Caliber for automatic AI agent context sync. An agent skill from caliber-ai-org/ai-setup.

caliber-ai-org/ai-setup

Run a Tier 1 or Tier 2 feature end to end — feature level, story level, parallelism, integration, and retrospective.

Inebrio/Routerly

Creates new AI agent skills following the Agent Skills spec.

Gentleman-Programming/Gentleman-Skills

Methodology for writing or improving prompts and system prompts that drive any LLM.

hAcKlyc/MyAgents

A skill your agent uses when the user wants to work on a Claude Code skill file (SKILL.md): writing one from scratch, testing whether an existing one works well, running evals or benchmarks…

avibebuilder/claude-prime

Read-only audit of the entire MacMagazine codebase for quality, consistency, and compliance with CLAUDE.md and .claude/rules standards.

MacMagazine/app-iOS

Apply Robert C. Martin-inspired architecture rules when separating business policy from frameworks, databases, UI, or infrastructure details.

ciembor/agent-rules-books

Keeps Agents.md, claude.md and gemini.md identical across a project by scanning folders and copying the newest version over the others, once or continuously.

littleben/awesomeAgentskills

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

bitwarden/ai-plugins