agentleFS
dragoshontdragoshont/architrave/skills/architrave-agent-authoring/SKILL.md

architrave-agent-authoring

Skill2 starsChanged 7 days agoMITView on GitHub

Explicitly create, revise, or review an agent role when asked to author agents; not for routine use of an existing role.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    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 the repository's existing role format and target host contract.

    line 6
  2. Distinctive:

    Keep model and provider selection host-owned.

    line 14
  3. Distinctive:

    Keep shared role sources and generated registrations consistent.

    line 17
  4. Distinctive:

    Do not use this skill to assign work to an existing agent or expand a role's permissions.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Use the repository's existing role format and target host contract. Keep one clear responsibility, define non-goals, and give the role a trigger that distinguishes when it should and should not be selected.

  • Ground instructions in repository contracts and existing roles. Extend a current role rather than creating a duplicate or a new layer of supervision.
  • Request only the tools needed for the bounded responsibility. State read-only and approval boundaries; a role or skill never grants host permissions.
  • Keep model and provider selection host-owned. Do not pin model IDs, assume host-specific capabilities, or claim that a worktree is a security sandbox.
  • Match the target host's supported frontmatter, tool and registration format. Keep shared role sources and generated registrations consistent; never assume one host discovers another host's format.
  • Define acceptance in observable terms and add or update a focused fixture or check where the contract can be tested. Validate manifests and relevant host-specific role loading without treating a fixture as live-host proof.

Example: a runtime observer should be read-only by default, report source-backed observations and unavailable evidence explicitly, and never infer deployed health from a successful build.

Do not use this skill to assign work to an existing agent or expand a role's permissions; use the existing role and host authorization flow instead.

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.