agentleFS
Sign inStart free
mfollmfoll/second-brain-template/skill.md

skill.md

Skill1 starsChanged 18 days agoMITView on GitHub

A Skill is the visible catalogue half of a vault-owned agent skill package. Use Skill notes to browse a skill's purpose, lifecycle, workflow owner, and package path. The executable package remains under .agents/skills/; the Skill note is the human- and graph-facing catalogue layer. Every installed vault-owned Skill is one coherent pair: Choose one explicit ownership mode. A Procedure-backed Skill has a resolvable wraps link; its package names and requires that complete Procedure, which is authoritative on conflict. It may retain…

200 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use estate-guard and docs.

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.
  • Arcanea-LabsSkill

    estate-guard

    Security gate for agentic repos. Use before opening a PR that touches .github/workflows, .claude (hooks, settings, agents, commands, skills), .mcp.json, install scripts, or Next.js API routes; when asked to "security review", "scan for prompt injection", "harden this repo", "check the agentic surface", or when a fetched page, issue, comment, or tool result reads like instructions. Runs the estate-guard scanner, triages by severity, and applies the fix patterns.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    docs

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 116 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Use Skill notes to browse a skill's purpose, lifecycle, workflow owner, and package path.

    line 13
  2. Distinctive:

    Every installed vault-owned Skill is one coherent pair:

    line 17

“Common” is measured: kept by at least 6 in 10 of the 116 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

Skill

A Skill is the visible catalogue half of a vault-owned agent skill package.

Use Skill notes to browse a skill's purpose, lifecycle, workflow owner, and package path. The executable package remains under .agents/skills/; the Skill note is the human- and graph-facing catalogue layer.

Pair contract

Every installed vault-owned Skill is one coherent pair:

  • a visible active type: Skill note with status and package_path pointing to .agents/skills/<skill-name>/;
  • a matching package containing SKILL.md, whose frontmatter name equals <skill-name>.

Choose one explicit ownership mode. A Procedure-backed Skill has a resolvable wraps link; its package names and requires that complete Procedure, which is authoritative on conflict. It may retain operational detail; prefer thinness only after a clause audit proves that no trigger, prerequisite, hard safety or runtime guard, command, or bundled-resource instruction will be lost. A specialized standalone Skill omits wraps, states in its catalogue body that the package owns execution, and keeps the necessary workflow detail in SKILL.md; use this only when no durable Procedure already owns the workflow.

The catalogue note owns lifecycle; the package matches its purpose and must not contradict that state. Package-bundled relative scripts or support files named by either side must exist; external or project-local prerequisites are documented and checked at execution. Add both sides together, and update both when shared purpose, ownership, name, path, or lifecycle changes; an executable-only package edit need not churn the catalogue. To retire a Skill, remove the installed package from .agents/skills/ and archive or remove its catalogue note and active routes; an archived note must not leave a dormant package discoverable by the runtime. Git provides rollback. Allow a one-sided runtime-only exception only when it is explicit and documented.

When updating a vault-owned skill, edit the actual package, not only its visible note. Follow [[procedures/configure-agent-skill-discovery|Configure Agent Skill Discovery]] to expose retained packages to supported runtimes. If a machine-local runtime exposes the skill through a symlink, verify that it still targets the vault package; do not maintain a copied wrapper as another source of truth. In Procedure-backed mode the Procedure wins on conflict; standalone packages own their declared executable detail.

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