agentleFS
Sign inStart free
EllAchEEllAchE/skill-observability/skills/create-skill/SKILL.md

create-skill

Skill0 starsChanged 3 months agoMITView on GitHub

Create a focused agent skill with deterministic applicability, concise SKILL.md instructions, reusable scripts or references only when justified, and validation against the surrounding skill inventory. Use when the user asks to create, scaffold, add, or define a new skill.

142 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use review-bugbot, migrate-to-skills 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.
  • 0mlkrizzz655335vSkill

    review-bugbot

    缺陷导向代码审查。用 Bugbot 子代理找 bug。

    Also in 5 projects that use this

  • 32103210Skill

    migrate-to-skills

    Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when you want to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.

    Also in 8 projects that use this

  • 32103210Skill

    update-cursor-settings

    Modify Cursor/VSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.

    Also in 8 projects that use this

  • PandelisZSkill

    update-cli-config

    View and modify Cursor CLI configuration settings in ~/.cursor/cli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.

    Also in 7 projects that use this

  • yawningwhaleAISkill

    build-premium-website

    Build a premium, animated marketing website (React + Vite + Tailwind + GSAP) for any industry. Use when the user asks to "build a website", "make a landing page for [business]", "build a marketing site", or wants a high-end animated company website. Adapts color, copy, services, and signature animation to the industry.

    Also in 6 projects that use this

  • yawningwhaleAISkill

    instantly-campaign

    Create a new Instantly cold-email campaign in the proven 5-email structure of the user's top-performing campaign (~16% reply rate). Use when the user wants to launch a new outbound campaign, write a cold email sequence, create an Instantly campaign, draft outreach for a new service or niche, or set up a sales sequence.

    Also in 5 projects that use this

  • +1 more from 32103210

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 132 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before writing, confirm all of the following:

    line 10
  2. Very specific:

    No existing skill already owns the workflow.

    line 17
  3. Very specific:

    Create skills/<name>/SKILL.md with YAML frontmatter containing name and a description that says both what the skill does and when it …

    line 30
  4. Distinctive:

    Keep the body imperative and concise.

    line 32
  5. Distinctive:

    Test every bundled script on synthetic or non-sensitive fixtures.

    line 37
  6. Distinctive:

    Run the target repository's skill validator.

    line 38
  7. Distinctive:

    Follow the target repository's review and delivery conventions.

    line 42
  8. Very specific:

    Do not create extra README, changelog, or installation files inside an individual skill folder.

    line 44

“Common” is measured: kept by at least 6 in 10 of the 132 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

Create Skill

Preconditions

Before writing, confirm all of the following:

  1. The requested workflow is repeatable and carries non-obvious procedure, domain knowledge, or deterministic tooling. Put one-off prose in documentation instead.
  2. The skill has a checkable applicability condition and a recognizable user goal.
  3. The target skill root is known. Use the repository's local skills/ directory when requested; otherwise ask before writing to a personal skill store.
  4. No existing skill already owns the workflow. Search the target inventory's SKILL.md names and descriptions before choosing a new name.

Author

  1. Gather concrete trigger examples, expected inputs, successful outputs, stopping conditions, and actions that require approval.
  2. Choose a short verb-led name using lowercase letters, digits, and hyphens. Keep it under 64 characters and make the folder name identical.
  3. Plan only reusable resources:
    • scripts/ for deterministic operations that would otherwise be rewritten;
    • references/ for optional domain detail;
    • assets/ for templates copied into outputs.
  4. Create skills/<name>/SKILL.md with YAML frontmatter containing name and a description that says both what the skill does and when it triggers.
  5. Keep the body imperative and concise. Start with a deterministic precondition, then state the ordered workflow, outputs, failure paths, safety boundaries, and explicit approval gates for destructive or externally visible actions.
  6. Link every optional resource directly from SKILL.md. Avoid nested reference chains and duplicate prose.
  7. Test every bundled script on synthetic or non-sensitive fixtures.
  8. Run the target repository's skill validator. Fix structural errors, duplicate names, folder mismatches, and broken relative links.
  9. Forward-test complex skills with a realistic raw task when safe. Do not give the tester the intended answer or diagnosis.
  10. Follow the target repository's review and delivery conventions.

Do not create extra README, changelog, or installation files inside an individual skill folder. The skill should stand on its SKILL.md and directly used resources.

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