agentleFS
Sign inStart free
asmamestasmamest/Nexus-Skills/templates/SKILL.md

example-skill

Skill1 starsChanged 17 days agoMITView on GitHub

Describe what this skill does and when an agent should use it.

We split this skill into the rules it gives an agent

11 rules. 0 are common, 11 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 38 edited versions we read keep these.

  • 11

    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:

    Use this skill when:

    line 14
  2. Distinctive:

    Do not use it when the task falls outside its scope.

    line 19
  3. Distinctive:

    Never invent missing requirements, test results, or project facts.

    line 30
  4. Distinctive:

    Verify the result using relevant tests or checks.

    line 38
  5. Distinctive:

    Never claim that a check passed unless it was actually performed.

    line 54
  6. Distinctive:

    Document relevant safety requirements, permissions, and side effects.

    line 58
  7. Distinctive:

    Do not expose secrets or sensitive data.

    line 60
  8. Distinctive:

    Do not perform destructive actions without appropriate authorization.

    line 61
  9. Distinctive:

    Do not introduce dependencies without a clear reason.

    line 62
  10. Distinctive:

    Ask for confirmation before consequential actions when required.

    line 63
  11. Distinctive:

    Remove or adapt rules that are irrelevant to this particular skill.

    line 65

“Common” is measured: kept by at least 6 in 10 of the 38 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

Example Skill

Purpose

Describe the engineering problem this skill solves and the outcome it should produce.

When to use

Use this skill when:

  • The user requests a specific, relevant engineering task.
  • The current project context matches the skill's intended purpose.

Do not use it when the task falls outside its scope.

Inputs and assumptions

Identify:

  • Required inputs and project context.
  • Assumptions the workflow relies on.
  • Constraints, dependencies, and limitations.
  • Information that must be clarified before proceeding.

Never invent missing requirements, test results, or project facts.

Workflow

  1. Inspect the existing project and understand the requirements.
  2. Identify the relevant files, tools, dependencies, and constraints.
  3. Choose an approach appropriate to the task.
  4. Execute the necessary steps while following existing project conventions.
  5. Verify the result using relevant tests or checks.
  6. Report the outcome, limitations, and any remaining work.

Adapt these steps to the specific task. Avoid unnecessary actions.

Quality checks

Define how to determine whether the task was completed successfully.

Include relevant checks such as:

  • Correctness and completeness.
  • Unit, integration, or regression tests.
  • Error handling and edge cases.
  • Security and performance considerations, where relevant.

Never claim that a check passed unless it was actually performed.

Safety and constraints

Document relevant safety requirements, permissions, and side effects.

  • Do not expose secrets or sensitive data.
  • Do not perform destructive actions without appropriate authorization.
  • Do not introduce dependencies without a clear reason.
  • Ask for confirmation before consequential actions when required.

Remove or adapt rules that are irrelevant to this particular skill.

Examples

Example 1: Typical use

Describe a realistic request and the expected approach or outcome.

Example 2: Edge case

Describe an important boundary condition and how the workflow should handle it.

References

List relevant authoritative documentation or supporting files, if needed.

Limitations

Describe known limitations, unsupported cases, or situations requiring human review.

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