Best agent instruction files skills, page 14

How to write .claude/rules/ files: golden format, enforceability, budget, scope.

xiaolai/nlpm

Generate a high-quality, repo-specific AGENTS.md file that tells AI agents how to work effectively in a repository.

OpenHands/extensions

A skill your agent uses to design the data model AND generate the actual forward + rollback migrations in one pass — shippable SQL, not a plan.

genkovich/sdd

Onboard an AI agent to an unknown codebase by generating a comprehensive instructions file.

bitovi/ai-enablement-prompts

Sets up how you and your team build and work with AI agents, and produces an Agent Workflow Charter (agent lanes, plan-mode loop, autonomy ladder with promotion criteria, rules file, review policy…

menkesu/awesome-pm-skills

Diagnose evolve health on Claude — verify the CLAUDE.md @import is actually loading the thin EVOLVE.md into sessions

AgentToolkit/altk-evolve

Sets up ai-toolkit in a project: symlinks, CLAUDE.md, intent interview.

softspark/ai-toolkit

Close out a coding session. An agent skill from kdeldycke/dotfiles.

kdeldycke/dotfiles

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

CorridorTech/PoseCap

Update LunCoSim's canonical documentation and agent guidance when behavior, ownership, APIs, scenes, tutorials, validation rules, or workflows change.

LunCoSim/lunco-sim

Build high-performing OpenClaw agents end-to-end with comprehensive safety features.

LeoYeAI/openclaw-master-skills

A skill your agent uses when starting hyperflow in a new project, re-initializing analysis, refreshing .hyperflow/ cache, or installing multi-tool auto-detection shims (AGENTS.md, Cursor rules…

ccplugins/awesome-claude-code-plugins

Initialize plugin in a project — install Iron Laws, auto-activation rules, and reference auto-loading into CLAUDE.md.

oliver-kriska/claude-elixir-phoenix

Use before editing AGENTS.md — enforces the 120-line launch and Steward boundaries, protected operator templates, and focused-document ownership.

richlander/dotnet-inspect

Write architecture fitness functions — deterministic tests that enforce a project's hard rules (module boundaries, offline guarantees, content contracts) from inside its own test target.

rshankras/claude-code-apple-skills

Update a project's own CLAUDE.md, README.md, or docs/ to reflect current state.

flonat/flonat-research

How to add or edit Cursor rules in our project. An agent skill from spiriMirror/libuipc.

spiriMirror/libuipc

Configure Cursor project rules using .cursor/rules/.mdc files and legacy .cursorrules.

jeremylongshore/tons-of-skills-marketplace

A skill your agent uses when starting hyperflow in a new project, refreshing the .hyperflow/ cache, or installing auto-detection shims (AGENTS.md, CLAUDE.md).

jeremylongshore/tons-of-skills-marketplace

Choose and create Devin Desktop customizations: Rules, AGENTS.md, Workflows, Skills, and Memories.

jeremylongshore/tons-of-skills-marketplace

Migrate to Devin Desktop (formerly Windsurf) from VS Code, Cursor, or other AI IDEs with full configuration transfer.

jeremylongshore/tons-of-skills-marketplace

Edit opencode.json, AGENTS.md, and config files. An agent skill from IgorWarzocha/Opencode-Workflows.

IgorWarzocha/Opencode-Workflows

A skill your agent uses when found gap or repetative issue, that produced by you or implemenataion agent.

NeoLabHQ/context-engineering-kit

Harness Engineering 第一阶段：扫描现有项目，生成 AGENTS.md（目录文件）和完整的 docs/ 知识库结构。

simbajigege/book2skills

Harness Engineering 第二阶段：建立跨 session 状态管理，解决 agent 每次对话失忆的问题。

simbajigege/book2skills

Onboard a new GTM project — run an agency-style interview, then generate CLAUDE.md, PROGRESS.md, about/me.md, strategy/brand.md, and scaffold content + assets folders.

manojbajaj95/claude-gtm-plugin

Suede Labs full writing stack: sharper copy for docs, pages, email, social, headlines, CTAs, product listings, and public explainers, with an SEO/AEO/AI EO pass, persona and framework selection…

JasonColapietro/suede-creator-skills

Use this standalone skill when the user asks to mine a repo's existing coding conventions for future AI coding, generate or refresh project rules with AGENTS.md/CLAUDE.md pointers, create Cursor or…

leo-kuang-ai/spec-first

Provides documentation audit checklists and quality standards.

microsoft-foundry/foundry-agent-webapp

Summarize the current session and propose improvements to CLAUDE.md, rules, docs, and skills, applying them after user confirmation.

MillenniumDawn/Millennium-Dawn

Shrink the memory files sessions load — the root AGENTS.md plus every nested AGENTS.md / CLAUDE.md — to the minimum words that state the same rules: compress wording, delete duplicates and…

iusztinpaul/squid

Generate baseline CLAUDE.md and AGENTS.md instruction files for a project.

CurryTang/Amadeus

Generate optimized project context from codebase scan. An agent skill from FerroxLabs/ijfw.

FerroxLabs/ijfw

Generates AGENTS.md files for repository folders — coding agent context files with build commands, testing instructions, code style, project structure, and boundaries.

microsoft/skills

Maintain AGENTS.md-based project instructions for tools that support AGENTS.md.

hashgraph-online/awesome-codex-plugins

A skill your agent uses when evaluating repository agent-readiness, mapping harness roles, choosing the next smallest improvement, or designing and reconciling agent entrypoints such as AGENTS.md…

hashgraph-online/awesome-codex-plugins

Audit and improve the CLAUDE.md files listed in the run worklist: apply only high/medium priority fixes, create the ones that are missing, and delete instructions already fully covered by a…

PackmindHub/packmind

Provides comprehensive memory file management capabilities including auditing, quality assessment, and targeted improvements for files such as CLAUDE.md.

giuseppe-trisciuoglio/developer-kit

Two-tier memory system that makes Claude a true workplace collaborator.

w95/awesome-claude-corporate-skills

A gazda megkér, hogy nevezd át magad ("mostantól legyél X", "nevezd át magad X-re", "hívjunk inkább X-nek").

Szotasz/marveen

Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering

NeoLabHQ/context-engineering-kit

How any agent grows its soul as it works — adding to its docs, decisions, memory, and skills (but never its AGENTS.md or role).

awebai/aweb

A skill your agent uses when configuring Claude Code — installing skills or agents, writing hook configurations, setting up tool permissions, registering MCP servers, or authoring CLAUDE.md project…

kid-sid/claude-spellbook

当项目首次接入 Spec 驱动开发 / R&K Flow，需要创建 AGENTS.md、.agents/rules/、 .agents/skills/、spec/ 目录、记忆系统和 HTML 报告资产时使用。

HHU3637kr/skills

Toggle a project-local concise-output directive that suppresses agent prose padding during SDD steps.

haru/redmine_ai_helper

A skill your agent uses when reviewing a pull request in the alego repo — orients the reviewer to this codebase's standards (AGENTS.md conventions, defensive patterns, ADRs, quality gates) and the…

singula-ai/alego

当用户用 Claude 写小红书、公众号、视频脚本等内容时，输出出现翻译腔、英文思考、西式框架，导致“像外国人假装写中文”时使用。

majiayu000/spellbook

当确定要修改 AGENTS.md、commands、项目 AI 规则、skill/references、治理脚本，或明确优化 AI 驱动开发体系时使用；普通规则讨论和一次性纠偏不提前触发。

Peiiii/nextclaw