agentleFS
Sign inStart free
p10ns11yp10ns11y/skills/author-workflow-skill/SKILL.md

author-workflow-skill

Skill2 starsChanged 40 days agoMITView on GitHub

Create a new project SKILL.md for a repeatable workflow. Use when user asks to add a skill for vulnerabilities, package upgrades, audits, supply-chain checks, or any named agent workflow.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Commit secrets or environment-specific paths — use {REPO_ROOT} placeholders

    line 32
  2. Very specific:

    Ask user to invoke /skill-name on the next matching task.

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Author a workflow skill

When to use

User requests: "Add a SKILL.md for …", "create a skill to …", or describes a repeatable procedure worth attaching on demand.

Steps

  1. Glob existing .cursor/skills/ and .agents/skills/ — match naming and frontmatter style.
  2. Read 1–2 existing SKILL.md files in the repo for tone and section layout.
  3. Draft skill with:
    • YAML name + description (third person; include trigger phrases)
    • Formal-first body (optional dense header per formal/AppGenMathPhyLang.kernel.md; English in (parentheses) where a symbol may confuse)
    • When to use / skip — bullet triggers
    • Steps — ordered, tool-friendly; one diagram if state machine/DAG
    • Done when — verifiable exit criteria (commands/artifacts)
    • references/english-*.md — full plain English; agent loads only if formal SoT is insufficient
  4. Write under .agents/skills/<name>/SKILL.md (or project convention path).
  5. Optionally add a routing rule (.mdc) telling the agent when to suggest attaching the skill.
  6. Meet QUALITY.md — no tool-name-only stubs.

Do not

  • Paste long policy essays — skills are procedures, not style guides
  • Dual-load formal + full English by default (token waste)
  • Duplicate an existing skill — extend or link instead
  • Commit secrets or environment-specific paths — use {REPO_ROOT} placeholders
  • Ship distill “evidence: turn N” archaeology as a skill

Validate

Ask user to invoke /skill-name on the next matching task; compare tool pattern to gold sessions (Read → research → Shell verify).

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