Best agent instruction files skills, page 10

Run the cold-start interview to learn your commercial contracts practice and write your team practice profile.

anthropics/claude-for-legal

Comprehensive knowledge base for Claude Code formats, patterns, and configuration.

dykyi-roman/awesome-claude-code

Distill imperative markdown guidance (AGENTS.md, CLAUDE.md, .clinerules/, GEMINI.md, SKILL.md with hard imperatives) into deterministic Interlinked harness hook rules with verbatim source provenance.

QuentinCody/interlinked-cli

One-time project setup for adr-kit. An agent skill from rvdbreemen/OTGW-firmware.

rvdbreemen/OTGW-firmware

Generate project-specific AGENTS.md and companion rules by analyzing a codebase.

sickn33/agentic-awesome-skills

Convert human-written CLAUDE.md into AI-native structured-label format.

sickn33/agentic-awesome-skills

Especialista profundo em Claude Code - CLI da Anthropic. An agent skill from sickn33/agentic-awesome-skills.

sickn33/agentic-awesome-skills

Persist user preferences and styles across sessions. An agent skill from TyrealQ/q-skills.

TyrealQ/q-skills

A skill your agent uses when creating or refactoring CLAUDE.md files - enforces best practices for size, structure, and content organization

serejaris/personal-corp-os

Professor's one-time clinic setup — practice areas, jurisdiction, supervision style (formal review queue / configurable flags / lighter-touch), and handbook/rules upload.

anthropics/claude-for-legal

Edit pixiv-cli documentation, AGENTS.md, client bridges, repository maintenance skills, or the distributed product skill.

FlanChanXwO/pixiv-cli

A skill your agent uses when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps…

alirezarezvani/claude-skills

A skill your agent uses when designing, reviewing, or paying for an agent memory system — adding memory to an agent, choosing between long-context / RAG / graph / agentic memory, auditing what a…

alirezarezvani/claude-skills

Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement.

alirezarezvani/claude-skills

Curate Claude Code's auto-memory into durable project knowledge.

alirezarezvani/claude-skills

Resume execution of an approved plan from the next unchecked subtask, following the gated Task Execution Workflow in AGENTS.md.

maotoumao/Cebian

Build, review, and audit technical docs and agent instruction files.

vincentkoc/dotskills

Complete AI coding workflow system. An agent skill from rohitg00/pro-workflow.

rohitg00/pro-workflow

Agent 工作台迁移。把任意项目整理成 Claude Code / Codex / Grok 三端一致、可长期维护的 Agent 工作台：审计规则文件、识别真源、统一命名并生成 bridge。

Pluviobyte/rnskill

Apply Martin Fowler-inspired refactoring rules when improving existing code structure while preserving observable behavior.

ciembor/agent-rules-books

Route a contract issue to the right approver per the escalation matrix in ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md, and draft the ask.

anthropics/claude-for-legal

TRIGGER when: asked to clarify or improve the explanation in existing local human documentation or a PR-description draft, including a PR URL or pasted body.

serpro69/claude-toolbox

Intelligent README.md generation prompt that analyzes project documentation structure and creates comprehensive repository documentation.

github/awesome-copilot

Audit, generate, update, and lint AGENTS.md files across all projects.

espennilsen/pi

Refresh fact-based sections of crates/AGENTS.md (STRUCTURE, WHERE TO LOOK, COMPLEXITY HOTSPOTS, KNOWN BROKEN) from current codebase state.

UniClipboard/UniClipboard

为 agent 编写文档。适用于创建或编辑 skills，或修改 AGENTS.md 或 CLAUDE.md 时. An agent skill from vinvcn/mattpocock-skills-zh-CN.

vinvcn/mattpocock-skills-zh-CN

Generate tailored AI agent instruction files via AgentRC instructions command.

github/awesome-copilot

Prompt for generating an AGENTS.md file for a repository. An agent skill from github/awesome-copilot.

github/awesome-copilot

How to write and manage Cursor rules - invoke with @cursor-usage

trycompai/comp

The method for profiling and optimizing anything whose success is a measured cost — frame the phase and metric, choose an instrument that can actually see the cost, label the waste, falsify the…

happier-dev/happier

Read-only drift audit — compare AGENTS.md, ARCHITECTURE.md, and ADR statuses against what the code actually does.

alexandremendoncaalvaro/CorridorKey-Runtime

A skill your agent uses when working in this repository after receiving recurring coding feedback, adding or reviewing durable lint guardrails from AGENTS.md, updating rules/.md, or finishing…

CorrectRoadH/OpenTickly

网文写作工具集基础设施部署。将 hooks/rules/agents/CLAUDE.md/AGENTS.md 等基础设施部署到用户项目目录，支持 Claude Code / OpenCode / Codex / OpenClaw。触发方式：/story-setup、$story-setup、「准备写书」「帮我搭一下环境」「配置写作项目」。

Xiaoyangy/novel-studio

Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks.

akitaonrails/my-skills

Update docs (CHANGELOG, CLAUDE.md, READMEs), commit, and push.

TyrealQ/q-skills

Upgrade an existing website or app to premium quality without breaking functionality — audit the current design, identify generic/AI tells, then apply taste and system rules surgically.

plugin87/ux-ui-agent-skills

House cold-start for the litigation plugin — branches by role (in-house, firm associate, solo) and side (plaintiff, defense, both), captures risk calibration, landscape, and house style, and writes…

anthropics/claude-for-legal

How Inkline documentation is written and kept true — the doc surface, pointers-not-duplicates, the drift watch with its current inventory, voice rules, and the future docs website.

inkline/inkline

Make any repo AI-ready — analyzes your codebase and generates AGENTS.md, copilot-instructions.md, CI workflows, issue templates, and more.

github/awesome-copilot

piper-plus のコミットルール (CLAUDE.md 準拠) でステージ済みファイルをコミットします。--no-verify 禁止、HEREDOC、適切な prefix を強制。

ayutaz/piper-plus

Create, revise, or audit AGENTS.md files from repository evidence, verified commands, and correctly scoped instructions without overwriting maintainer intent.

sickn33/agentic-awesome-skills

Create folder-scoped CLAUDE.md and AGENTS.md guidance for future agents working in that area.

sickn33/agentic-awesome-skills

Map, explain, and lint repository-scoped coding-agent instructions before changing code.

sickn33/agentic-awesome-skills

Audit named agent instructions, tool definitions, and supported Python prompts with local LintLang checks; return finding codes and locations without changing files.

sickn33/agentic-awesome-skills

Find which APIs of a project's pinned Python dependencies changed after the model's training cutoff, where the code uses them, and write short AGENTS.md or CLAUDE.md notes.

sickn33/agentic-awesome-skills

Run the cold-start interview — learns your privacy practice and writes CLAUDE.md from your policy, DPA template, and a reference PIA.

anthropics/claude-for-legal

reddi.tech fork of self-improving-agent. An agent skill from LeoYeAI/openclaw-master-skills.

LeoYeAI/openclaw-master-skills

A skill your agent uses when the user asks to generate or update a project's CLAUDE or AGENTS context file from a codebase scan.

Varnan-Tech/opendirectory