Best agent instruction files skills, page 6

自然言語メモリファイル（CLAUDE.md, todos, 設定）を原始人形式に圧縮し入力トークン削減. An agent skill from InterfaceX-co-jp/genshijin.

InterfaceX-co-jp/genshijin

Convert Claude Code skills to work on OpenAI Codex, Google Gemini CLI, Google Antigravity, and Cursor.

AgriciDaniel/skill-forge

Generates or updates an AGENTS.md file

agent-substrate/substrate

Change the org-level CLAUDE.md that governs every attmcojp repository.

natsukium/dotfiles

A skill your agent uses when asked to mine the commit history for lessons the agent instruction files have not captured, to audit whether domain-context and contracts reflect what actually broke, or…

ZoneMinder/zmNinjaNg

A skill your agent uses when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.

BuilderIO/skills

Generates a tree of AGENTS.md files for a repository, one at the root and more in complex subdirectories, so agents learn its structure and conventions.

code-yeongyu/oh-my-openagent

Starts a non-development project in MoAI-Cowork by interviewing you, scanning installed plugins and generating AGENTS.md, CLAUDE.md and custom agent and skill chains.

modu-ai/moai-cowork

Mine recent Claude Code sessions for non-obvious, multi-file CLAUDE.md candidates, adversarially verify them, and propose paste-ready additions.

ragnar-pwninskjold/tech-snacks

Generate, review, and optimize natural language instructions for Business Central agents (Designer or SDK).

javiarmesto/ALDC-AL-Development-Collection

melta DS の契約から画面 1 枚（ページ / スクリーン）を生成し、checkhtml で自己検証して coverage と評価不可まで報告する。トリガー: 「画面を作って」「〜ページを生成」「画面生成」「ダッシュボードを作って」「設定画面を作って」「build screen」「generate a page」。AGENTS.md のタスクベース読み込みガイドで契約を引き当て、最大 3…

tsubotax/melta-ui

Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield.

affaan-m/ECC

Inspect a repository and draft an AGENTS.md file using the standard template, capturing commands, structure, and workflow rules.

dmitriiweb/extract-emails

Create comprehensive CLAUDE.md files with tech stack, standard commands, repository structure, and boundaries to optimize repositories for AI-assisted development

ambient-code/agentready

A skill your agent uses when reviewing code changes against AGENTS.md implementation quality standards, or when asked to do an implementation quality review

ReviewStage/stage-cli

AI agent integration layer for the Pump SDK — agent instruction files, .well-known discovery, LLM context documents, 15+ skill files, MCP server prompts, and terminal management rules for GitHub…

nirholas/pump-fun-sdk

[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

Operating rules for OpenCreator's internal Creator Agent: read context first, change data only through the apply-action tool with revision checks, and wait for stage results.

krillinai/OpenCreator

Verify every @path chain import and every markdown link inside every CLAUDE.md in this project resolves to an existing file.

alirezarezvani/ClaudeForge

Prune and route AGENTS.md trees for durable, high-signal context.

Signet-AI/signetai

Transform any boring B2B business problem into a complete software blueprint with architecture, database schema, feature breakdown, and step-by-step implementation plan formatted as a CLAUDE.md file…

zanecole10/software-tailor-skills

Bootstraps a project's tool-agnostic AGENTS.md files for a greenfield project, an undocumented codebase or one area, adding only what is missing and never overwriting curated content.

jsmastery-pro/skills

Agent-only reference for changing firstmate's shared, tracked material per AGENTS.md section 1.

kunchenguid/firstmate

Self-reflect on the current session to identify mistakes and propose improvements to .claude configuration (CLAUDE.md, hooks, skills).

anam-org/metaxy

Injects a project's own skills and AGENTS.md content into generic bundled agent template files, adding a tech-stack line and real conventions without touching an agent's core logic.

aspenkit/aspens

This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise.

henryalouf/ruflow

OpenLark 项目代码规范检查技能。用于快速审查仓库内的架构一致性、API 实现套路、参数校验、命名与导出规范，并输出可执行检查清单与证据路径。Triggers: code review / consistency check / architecture audit / 规范检查 / 风格一致性 / 体检 / 对齐约定。项目锚点见 AGENTS.mdCONVENTIONS 与…

foxzool/openlark

Record a lesson learned into crates/AGENTS.md (CONVENTIONS or ANTI-PATTERNS section).

UniClipboard/UniClipboard

Reports what the watchmen plugin found in this workspace since its last curator run: new or changed skills, CLAUDE.md edits and a suggested skill to load.

firstbatchxyz/watchmen

Runs the daily review of evlog's written material: picks the worst-scoring files in one group, rewrites what holds up, and opens a single pull request that reports the changes.

evloghq/evlog

Maintain repository agent guidance. An agent skill from videojs/video.js.

videojs/video.js

Audits the agent rules in the current folder (AGENTS.md, nested AGENTS.md files) and the skill descriptions the agent sees at start, then reports what to cut, move or rewrite and edits only after…

serejaris/personal-corp-os

Configure or reconcile a project for linked-intent development (LID).

jszmajda/lid

Create a new skill from scratch. An agent skill from getnao/sylph.

getnao/sylph

Codex CLI artifact schemas: config.toml, .codex-plugin, skills, hooks, AGENTS.md.

xiaolai/nlpm

PromptKit composition engine. An agent skill from microsoft/PromptKit.

microsoft/PromptKit

Read-only drift audit — compare AGENTS.md, ARCHITECTURE.md, ADR statuses, feature specs in doc/specs/, and documentation discipline against what the code actually does.

CorridorTech/PoseCap

Re-indexes a repository into gbrain and refreshes the agent search guidance in CLAUDE.md, safe to run again whenever search results look stale.

garrytan/gstack

Audit and update CLAUDE.md files (root or any directory-scoped one) against the actual current state of the code they document.

therxmv/Telegram-Themer

Writes project agent instructions and tool setup from decided requirements and the existing repo, keeping only stable, non-obvious guidance in always-loaded files.

KhazP/vibe-coding-prompt-template

Has the agent read a project wiki's AGENTS.md and pull the guidelines that fit the task it is about to start, instead of loading the wiki at session start.

AgentToolkit/altk-evolve

Keep the repository's documentation accurate, honest, and synchronized with the code.

extra-org/extra

Sync THIS LLM-Wiki framework with its public GitHub repo, ONE direction per run: --push (vault → repo) publishes your framework; --pull (repo → vault) updates your framework from a newer repo version.

HurricaHjz/second-yourself

How to keep CLAUDE.md under its character Floor without deleting a rule: measure sections first, rotate by derivability, two edits per rotation.

jgravelle/jcodemunch-mcp

Check a diff against Polar's written conventions in server/AGENTS.md and clients/AGENTS.md — module structure, repository and service patterns, session types, auth dependencies, test organisation…

polarsource/polar

分析、设计、验证或更新本 wiki 的 Codex Skill 体系、AGENTS.md 唯一路由、职责图和验证规则。当前目标只要求分析时保持只读。

lihaozheCharlie/the-way-here

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

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

microsoft/vscode-chat-customizations-evaluation