agentleFS
Sign inStart free
hebertzhuhebertzhu/agent-foundry/skills/creating-skills/SKILL.md

creating-skills

Skill0 starsChanged 8 months agoMITView on GitHub

用于创建或重构 skill 本身：当主任务是编写 `SKILL.md`、frontmatter、目录结构、命名、bundled resources，或把 skill 迁移到当前 Codex / 本地 skills 约定时使用。Prefer `skill-creator` for eval 循环、benchmark 驱动迭代或 trigger 准确率优化。

30 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use building-chatgpt-apps, building-chat-interfaces and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • mjunaidcaSkill

    building-chatgpt-apps

    Guides creation of ChatGPT Apps with interactive widgets using OpenAI Apps SDK and MCP servers. Use when building ChatGPT custom apps with visual UI components, embedded widgets, or rich interactive experiences. Covers widget architecture, MCP server setup with FastMCP, response metadata, and Developer Mode configuration. NOT when building standard MCP servers without widgets (use building-mcp-servers skill instead).

    Also in 4 projects that use this

  • mjunaidcaSkill

    building-chat-interfaces

    Build AI chat interfaces with custom backends, authentication, and context injection. Use when integrating chat UI with AI agents, adding auth to chat, injecting user/page context, or implementing httpOnly cookie proxies. Covers ChatKitServer, useChatKit, and MCP auth patterns. NOT when building simple chatbots without persistence or custom agent integration.

    Also in 4 projects that use this

  • +10 more from mjunaidca

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 28 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Call out what evidence would change the recommendation.

    line 16
  2. Distinctive:

    Keep the output concise, reusable, and easy to operationalize.

    line 17
  3. Distinctive:

    Keep examples generic, privacy-safe, and portable across hosts.

    line 21
  4. Distinctive:

    Do not spend time benchmarking before the skill structure is coherent.

    line 24

“Common” is measured: kept by at least 6 in 10 of the 28 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

creating-skills

Intent

  • 用于创建或重构 skill 本身：当主任务是编写 SKILL.md、frontmatter、目录结构、命名、bundled resources，或把 skill 迁移到当前 Codex / 本地 skills 约定时使用。Prefer skill-creator for eval 循环、benchmark 驱动迭代或 trigger 准确率优化。

Default operating pattern

  1. Clarify the decision that actually matters for the user right now.
  2. Compare serious options and explain the trade-offs in plain language.
  3. Recommend one default path and explain why it wins.
  4. Call out what evidence would change the recommendation.
  5. Keep the output concise, reusable, and easy to operationalize.

Pack fit

  • Included in: skill-authoring
  • Keep examples generic, privacy-safe, and portable across hosts.

Boundary

  • Do not spend time benchmarking before the skill structure is coherent.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free