Battle-tested coding-agent skills for product, content, writing, presentations, and workflow automation.
Supply asset profile
Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.
Scenario
Coding agents
I need a coding agent that can understand a repository, edit code, and review pull requests.
Agent fit
Claude Code + CLI + Codex
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add YiShu5/claude-skills
Maintenance
fresh
2d since push
Risk
Safe to try
Stars/forks activity: 131 stars, 0 forks; issue activity unavailable in current metadata
GitHub quality
131
93/100 quality · 84/100 trust
Coverage tags
Review notes
Stars/forks activity: 131 stars, 0 forks; issue activity unavailable in current metadata
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
ExcellentHigh-confidence pick with strong adoption and healthy maintenance signals.
Trust
Review then installGood shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.
Audit
Safe to tryInstall readiness, security metadata, maintenance, and adoption risk.
Trust Score v5
Use as the primary candidate after human or sandbox review.
Stars
131 GitHub stars
Repo activity
131 stars, 0 forks
Maintenance
2d since push
License
MIT
Install
npx skills add YiShu5/claude-skills
Install safety
standard package or runtime install path
Permission surface
shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Strong README/SKILL.md context
Risk summary
Install readiness
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Do not use when
Alternative
164.7K stars
npx skills add mattpocock/skills --skill grill-with-docs
Alternative
168.6K stars
npx skills add mattpocock/skills --skill code-review
Alternative
164.7K stars
npx skills add mattpocock/skills --skill to-spec
Alternative
176.7K stars
npx skills add mattpocock/skills --skill to-tickets
Agent safety v2
Usable candidate, but the agent should surface permission and audit notes before installation.
Require human approval before installing into a real workspace.
high
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
Install targets
Copy the registry command or an agent-specific install prompt for Codex, Claude Code, and Cursor.
Use the registry command when your workflow supports the OpenAgentSkill installer.
$ npx skills add YiShu5/claude-skillsAgent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Resolve JSON
/api/agent/resolve?task=Use%20Claude%20Skills%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20Claude%20Skills%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/yishu5-claude-skills/install
Agent should check
Copy prompt
Task: Use Claude Skills in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20Claude%20Skills%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/yishu5-claude-skills/install
Install command: npx skills add YiShu5/claude-skills
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/yishu5-claude-skills/install
LLM text format
/api/skills/yishu5-claude-skills/install?format=text
Find alternatives
/api/skills/search?q=Claude%20Skills&limit=3
Agent prompt
Use Claude Skills for this task. Review https://www.openagentskill.com/api/skills/yishu5-claude-skills/install, then install with: npx skills add YiShu5/claude-skillsRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/yishu5-claude-skills
LLM text
/api/registry/manifest/yishu5-claude-skills?format=text
Install alias
/api/registry/install/yishu5-claude-skills
Recommend
/api/registry/recommend?task=Use%20Claude%20Skills%20in%20an%20agent%20workflow&limit=3
Agent fit
Coding agents
Platforms
Python, Claude Code
Audit report
Review install readiness, maintenance, trust, quality, and metadata warnings before adding this skill to an agent workflow.
Agent decision cockpit
Use this as a leading candidate, then validate the README and install path in your own agent stack.
Role in stack
Primary pick
Primary fit
Coding agents
Trust label
Production-ready
Install path
Command ready
Use when
Evidence
Review first
Implementation path
Trust profile
Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.
GitHub adoption
INFO131 GitHub stars
Stars/forks activity
CHECK131 stars, 0 forks; issue activity unavailable in current metadata
Recent maintenance
PASS2d since push
License clarity
PASSMIT
Good signals
Review before install
Recommended action
Use as the primary candidate after human or sandbox review.
Quality profile
High-confidence pick with strong adoption and healthy maintenance signals.
Workflow fit
Build and ship code
I need a coding agent that can understand a repository, edit code, and review pull requests.
Operate web apps
I need my agent to control a browser, fill forms, and verify web app workflows.
Create decks
I need my agent to create a polished presentation deck from a brief, document, URL, or research notes, preferably with editable PPTX or HTML slides.
Stack fit
Inspect, patch, and verify code
A stack for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.
Operate and verify web apps
A stack for agents that navigate products, fill forms, take screenshots, and verify real user flows across web applications.
Turn skills into distribution
A stack for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Alternative shortlist
Similar skills in this category, ranked with the same readiness and quality signals.
A relentless interview that pressure-tests a plan against the codebase, sharpens domain language, and updates CONTEXT.md and ADRs when decisions become durable.
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
Turn the current conversation and codebase context into a structured implementation spec, then publish it to the configured project issue tracker.
Break a plan, spec, or conversation into independently actionable tracer-bullet tickets with explicit blocking relationships.
<div align="center">
# 🧩 Claude Skills
**按场景整理的 Claude Code Skills：HTML 首页/演示、公众号工作流、动画生成、PRD 整理、中文写作与经验记忆**
[](./skills) [](https://claude.com/claude-code) [](./LICENSE)
</div>
---
## 🤔 Why this?
这个仓库不是大而全的插件市场，而是一组已经在真实工作流里反复打磨过的 Claude Code Skills。它们面向具体任务：做一个可运行的 HTML Hero、把 Hero 扩成 HTML/PPT 演示、生成 Clawd 动画、整理 Vibe Coding PRD、写中文长文并审校降 AI 味、协作写公众号并完成排版发布。
每个 skill 都尽量回答清楚三件事：**什么时候触发、应该怎么做、做到什么程度才算完成**。
这个仓库收录的 skills 遵循三个原则：
1. **按真实场景归类** — 首页只保留清晰入口，同类能力放在一起 2. **description 是触发器，不是介绍** — 把隐性意图、口语化说法、中英文同义词都写进去 3. **规则要能落到交付** — 明确执行流程、确认节点、验证方式和最终产物
---
## 📦 已收录 Skills
| 分类入口 | 包含 Skill | 用途 | 状态 | |---|---|---|---| | HTML 首页 / 演示 | [`HTMLHero.skill`](./skills/HTMLHero.skill)<br>[`HTMLPPT.skill`](./skills/HTMLPPT.skill) | 生成第一页 Hero，并扩展成一套 HTML/PPT 演示文稿 | ✅ | | Clawd 动画 | [`clawd-animation`](./skills/clawd-animation)<br>[`clawd-animation-lite`](./skills/clawd-animation-lite) | 像素风动画生成器，包含完整版和轻量版 | ✅ | | 经验记忆 | [`self-improving-agent`](./skills/self-improving-agent) | 会话结束时提取经验教训到 `.learnings/` 暂存区，人工审核后才入长期记忆 | ✅ | | Vibe 创作 | [`vibe-coding-prd`](./skills/vibe-coding-prd)<br>[`vibe-writing`](./skills/vibe-writing) | 整理可执行 PRD，并创建、改写或审校保留作者声音的中文内容 | ✅ | | 公众号工作流 | [`wechat-coauthor`](./skills/wechat-coauthor)<br>[`wechat-formatter`](./skills/wechat-formatter)<br>[`wechat-publisher`](./skills/wechat-publisher) | 写作协作、微信排版、封面素材上传、草稿创建与发布 | ✅ |
---
## 🚀 使用方式
```bash # 1. 克隆仓库 git clone https://github.com/YiShu5/claude-skills.git
# 2. 把想用的 skill 文件夹复制到 Claude Code 的 skills 目录 cp -r claude-skills/skills/clawd-animation ~/.claude/skills/
# 3. 在 Claude Code 中直接对话触发，无需额外配置 ```
> Windows 用户路径示例：`C:\Users\<你>\.claude\skills\`
---
## 🌱 分支约定
- `master` — 稳定版本，经过验证的 skills - `feat/<skill-name>` — 新 ski
Frameworks & Tools
Decision snapshot
recent repository activity
Audit snapshot
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the audit before production use.
Growth loop
Scenario-led draft for Claude Skills, ready for a manual X post.
Most agents can draft slides. The hard part is choosing the right deck workflow. Claude Skills helps agents turn briefs, docs, or research notes into editable deck workflows. 131 stars https://www.openagentskill.com/skills/yishu5-claude-skills?ref=x #AIAgents
Listing + install path for Claude Skills: https://www.openagentskill.com/skills/yishu5-claude-skills?ref=x Install: npx skills add YiShu5/claude-skills
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This community indexed listing is attributed to YiShu5 but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/yishu5-claude-skills)
[](https://www.openagentskill.com/skills/yishu5-claude-skills)
[](https://www.openagentskill.com/skills/yishu5-claude-skills/audit)
[](https://www.openagentskill.com/skills/yishu5-claude-skills)YiShu5✓
@yishu5
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Review then install
Grill With Docs
A relentless interview that pressure-tests a plan against the codebase, sharpens domain language, and updates CONTEXT.md and ADRs when decisions become durable.
164.7K stars · 0 installsCode Review
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
168.6K stars · 0 installsTo Spec
Turn the current conversation and codebase context into a structured implementation spec, then publish it to the configured project issue tracker.
164.7K stars · 0 installsTo Tickets
Break a plan, spec, or conversation into independently actionable tracer-bullet tickets with explicit blocking relationships.
176.7K stars · 0 installs