MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Skill 全生命周期管理：创建 → 反思优化 → 评测 → 成熟度判断 → 发布到市场 → 检索多版本 → 选择/安装 → 融合迭代 → 卸载。触发场景：(1) 用户要求创建/修改 skill (2) 发现可提取为 skill 的重复模式 (3) skill 执行出错或用户纠正后需要反思改进 (4) 用户要求发布/搜索/安装/合并社区 skill (5) 反思后自动检查成熟度并建议发布
Install Skill Dev
$ npx skills add hao-cyber/skill-evolution --skill skill-dev -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hao-cyber/skill-evolution skill-dev --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "skill-dev" agent skill from https://github.com/hao-cyber/skill-evolution/tree/master into .claude/skills/skill-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-dev", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hao-cyber/skill-evolution --skill skill-dev -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hao-cyber/skill-evolution skill-dev --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "skill-dev" agent skill from https://github.com/hao-cyber/skill-evolution/tree/master into .agents/skills/skill-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-dev", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hao-cyber/skill-evolution --skill skill-dev -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hao-cyber/skill-evolution skill-dev --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "skill-dev" agent skill from https://github.com/hao-cyber/skill-evolution/tree/master into .cursor/skills/skill-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-dev", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hao-cyber/skill-evolution --skill skill-dev -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hao-cyber/skill-evolution skill-dev --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "skill-dev" agent skill from https://github.com/hao-cyber/skill-evolution/tree/master into .gemini/skills/skill-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-dev", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install hao-cyber/skill-evolution skill-devInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add hao-cyber/skill-evolution --skill skill-dev -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "skill-dev" agent skill from https://github.com/hao-cyber/skill-evolution/tree/master into .github/skills/skill-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-dev", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hao-cyber/skill-evolution --skill skill-dev -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hao-cyber/skill-evolution skill-dev --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "skill-dev" agent skill from https://github.com/hao-cyber/skill-evolution/tree/master into .opencode/skills/skill-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-dev", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
skill-dev- GitHub stars
- 158
- Token cost
- ~930 tokens
- SKILL.md length
- 428 words
- Files
- 24 (incl. scripts, references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Skill 全生命周期管理：创建 → 反思优化 → 评测 → 成熟度判断 → 发布到市场 → 检索多版本 → 选择/安装 → 融合迭代 → 卸载。触发场景：(1) 用户要求创建/修改 skill (2) 发现可提取为 skill 的重复模式 (3) skill 执行出错或用户纠正后需要反思改进 (4) 用户要求发布/搜索/安装/合并社区 skill (5) 反思后自动检查成熟度并建议发布
- Agent Workflows work in your project
- SKILL.md covers Core Principles, Routing, When NOT to Create a Skill and Script Design, plus 1 more section
- Runs Python scripts from its folder
What it does
Skill Dev is an agent skill from hao-cyber/skill-evolution. Skill 全生命周期管理：创建 → 反思优化 → 评测 → 成熟度判断 → 发布到市场 → 检索多版本 → 选择/安装 → 融合迭代 → 卸载。触发场景：(1) 用户要求创建/修改 skill (2) 发现可提取为 skill 的重复模式 (3) skill 执行出错或用户纠正后需要反思改进 (4) 用户要求发布/搜索/安装/合并社区 skill (5) 反思后自动检查成熟度并建议发布
Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. The skill folder holds 26 other files, including scripts and reference files (for example `CONTRIBUTING.md`, `README.md` and `ROADMAP.md`).
It sits in Agent Workflows. The repository describes itself as: Self-evolving AI skill framework — skills that learn from execution, reflect on failures, and autonomously improve themselves. The licence is MIT.
When your agent uses it
- Agent Workflows work in your project
Example prompts
- “/skill-dev”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 942603e. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 4 files in scripts/ (Python, from the files we listed), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Skill Dev loads about 930 tokens when it runs, and up to ~6.7k if it reads all its reference files. Until then it costs about 51 tokens; SKILL.md has 428 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from hao-cyber/skill-evolution at commit 942603e, republished under its MIT licence (© hao-cyber). 428 words, ~930 tokens.
Download SKILL.mdSave it as
.claude/skills/skill-dev/SKILL.md (or your agent's skills folder). This skill also uses 23 other files; get the full folder from GitHub.- name
- skill-dev
- description
- Skill 全生命周期管理：创建 → 反思优化 → 评测 → 成熟度判断 → 发布到市场 → 检索多版本 → 选择/安装 → 融合迭代 → 卸载。触发场景：(1) 用户要求创建/修改 skill (2) 发现可提取为 skill 的重复模式 (3) skill 执行出错或用户纠正后需要反思改进 (4) 用户要求发布/搜索/安装/合并社区 skill (5) 反思后自动检查成熟度并建议发布
Skill Dev
Full lifecycle management for AI agent skills: create, reflect, evaluate, publish, search, install, merge, review, and uninstall.
Core Principles
Concise is Key
The context window is a shared resource. Only add context Claude doesn't already have. Challenge each piece: "Does Claude really need this?" Prefer concise examples over verbose explanations.
Degrees of Freedom
Match specificity to the task's fragility:
- High freedom (text instructions): Multiple approaches valid, context-dependent decisions
- Medium freedom (pseudocode/scripts with params): Preferred pattern exists, some variation OK
- Low freedom (specific scripts): Operations fragile, consistency critical, exact sequence required
Routing
Local lifecycle (no registry needed):
- Creating/structuring a skill (directory layout, SKILL.md format, progressive disclosure, verification) → 读取
references/structure.md - Reflecting after skill failure (trigger signals, reflect process, impact scan, escalation) → 读取
references/reflect-mode.md - 评测 skill prompt (eval、跑回归、检查 prompt 改动效果) → 读取
references/eval-mode.md - Checking skill maturity (after reflect, after successful runs, "成熟了吗", "该发布了吗") → 读取
references/maturity.md
Registry lifecycle (public registry built-in, works out of the box):
- Publishing a skill ("publish", "发布 skill", "开源这个 skill") → 读取
references/publish.md - Searching/installing ("search skill", "有没有XX的skill", "安装 skill") → 读取
references/search.md - Reviewing a skill ("review", "评价 skill", "打分") → use
scripts/review.py - Merging skill variants ("merge", "合并版本", "融合") → 读取
references/merge.md - Uninstalling a skill ("uninstall", "删除 skill", "卸载") → use
scripts/uninstall.py --name <skill> --yes
When NOT to Create a Skill
Don't build for hypothetical future needs. Skip if ANY apply:
- Used only once — just do it inline
- A one-line CLAUDE.md rule covers it — just edit CLAUDE.md directly instead
- No reusable script AND no non-obvious knowledge — Claude already knows how
- An existing skill handles 80%+ of the use case — extend it instead
Show full SKILL.md (171 more words)Show less
Script Design
Tool design matters more than prompt design. When a skill has scripts/, invest in quality:
- Token-light output: Print only what the caller needs.
--verbosefor debugging only. - Greppable errors: All errors start with
ERROR:with key details on same line. - Self-documenting: Support
--helpwith one-liner description and parameter list. - Clear parameter names: Use intuitive names (
--document-id, not--did). - Absolute paths: Accept and output absolute paths.
- Exit codes: 0 = success, non-zero = failure.
- Design for agents, not humans: Output structured data, not formatted text.
- Progressive disclosure: Truncated output must include total data size and how to see more. JSON: add
total/has_more/page_token. Text: append(N chars total)+ stderrHINT:with continuation command.
Writing Guidelines
- Do include: non-obvious procedures, domain specifics, gotchas from real failures
- Don't include: things Claude already knows, verbose explanations, auxiliary docs
- Keep SKILL.md ≤150 lines (routing layer); move scenario details to references/
- Challenge each line: "Would removing this cause Claude to make mistakes?" If not, cut it.
- Prefer examples over explanations: One concrete pair teaches more than a paragraph
© hao-cyber, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 23 other files (scripts, references) in the repository root of hao-cyber/skill-evolution.
- SKILL.md
- .env.example
- .gitignore
- CONTRIBUTING.md
- LICENSE
- README.md
- ROADMAP.md
- references/eval-mode.md
- references/maturity.md
- references/merge.md
- references/publish.md
- references/reflect-mode.md
- references/search.md
- references/structure.md
- scripts/audit.py
- scripts/install.py
- scripts/lib/__init__.py
- scripts/lib/supabase.py
- … and 6 more
Open the folder on GitHubat commit 942603e
Compare with similar skills
Skill Dev next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Skill Dev this skillhao-cyber/skill-evolution | 158 | — | ~930 | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 38k | 10 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Using Superpowersfarm-fe/farm | 5.6k | 36 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 297k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Skill CreatorAzure/azqr | 796 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
- Official
Hook Development for Claude Code Plugins
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
Using Superpowers
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
- Official
Skill Creator
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
- Official
Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Related
Categories
Questions about Skill Dev
What does Skill Dev do?
Skill 全生命周期管理：创建 → 反思优化 → 评测 → 成熟度判断 → 发布到市场 → 检索多版本 → 选择/安装 → 融合迭代 → 卸载。触发场景：(1) 用户要求创建/修改 skill (2) 发现可提取为 skill 的重复模式 (3) skill 执行出错或用户纠正后需要反思改进 (4) 用户要求发布/搜索/安装/合并社区 skill (5) 反思后自动检查成熟度并建议发布. Skill Dev is an agent skill from hao-cyber/skill-evolution.
When should I use Skill Dev?
Skill Dev fits situations like: agent Workflows work in your project.
How do I install Skill Dev in Claude Code?
Run `npx skills add hao-cyber/skill-evolution --skill skill-dev -a claude-code`. Or copy the skill folder (the hao-cyber/skill-evolution repository) into .claude/skills/skill-dev in your project. Claude Code loads it when a task matches its description.
How do I install Skill Dev in Codex?
Run `npx skills add hao-cyber/skill-evolution --skill skill-dev -a codex`. Or copy the skill folder (the hao-cyber/skill-evolution repository) into .agents/skills/skill-dev in your project. Codex loads it when a task matches its description.
Can I use Skill Dev in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hao-cyber/skill-evolution --skill skill-dev -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-dev, .gemini/skills/skill-dev, .github/skills/skill-dev and .opencode/skills/skill-dev in your project.
What does Skill Dev need to run?
Going by SKILL.md and its folder, Skill Dev needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Skill Dev access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Skill Dev safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Skill Dev use?
Skill Dev is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Skill Dev use?
About 930 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.7k tokens, read only when the agent opens those files.
What are the alternatives to Skill Dev?
Skills that share tags, products or a category with Skill Dev: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Skill Dev?
hao-cyber (a GitHub user) maintains it in hao-cyber/skill-evolution, which has 158 GitHub stars. The repository was last updated on February 25, 2026.
Source: hao-cyber/skill-evolution on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.