agentleFS
a-novel-kita-novel-kit/stack/.agents/skills/register-ai-agent/SKILL.md

register-ai-agent

Skill2 starsChanged 5 days agoMITView on GitHub

Verify and register a GitHub-linked AI co-author through a PR. Use only for a missing identity reported by attribute-ai-commits or an explicit registration request.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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:

    Search official provider documentation, official repositories, and GitHub for the agent's canonical co-author identity.

    line 15
  2. Distinctive:

    Verify the candidate programmatically:

    line 22
  3. Very specific:

    If diligent official-source research finds no valid identity, add an unavailable entry with aliases, status, reason, evidence, and …

    line 41
  4. Very specific:

    Update the registry as_of date and validate it:

    line 44
  5. Very specific:

    Commit the change, push it, and open a PR.

    line 50
  6. Distinctive:

    Use the new verified identity only after its registry entry exists on the branch.

    line 55

≈ “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

Register AI Agent

Register only the current missing agent. Never guess another provider's account or use another provider's bot. The registry review is the trust boundary.

Discover and verify

  1. Search official provider documentation, official repositories, and GitHub for the agent's canonical co-author identity.
  2. Require evidence that the exact email resolves to the expected provider-controlled account:
    • A numeric users.noreply.github.com address must contain the matching GitHub account ID and login.
    • A provider-domain address needs a public proof commit where GitHub's rendered author mapping links that email to the expected account.
  3. Verify the candidate programmatically:

    node <skill-dir>/scripts/verify-coauthor.mjs \
      --agent <agent> \
      --label '<display label>' \
      --github-login '<login>' \
      --email '<email>' \
      [--proof-commit '<github-commit-url>']

The command exits 0 only when the identity resolves to the expected GitHub account. It emits a registry-ready verified entry and stores rendered proof hashes in validated fragments so secret scanners do not mistake public commit IDs for credentials.

Update the registry

  1. On successful verification, add the emitted entry to the sibling attribute-ai-commits/references/providers.json registry.
  2. If diligent official-source research finds no valid identity, add an unavailable entry with aliases, status, reason, evidence, and checked_at. Do not use a syntactically plausible but unlinked email.
  3. Update the registry as_of date and validate it:

    node <skills-dir>/attribute-ai-commits/scripts/coauthor-registry.mjs validate
  4. Commit the change, push it, and open a PR. Include it in the current feature PR when one already exists; otherwise use a dedicated docs/skills/register-<agent> PR. The registry lives in a-novel-kit/stack, which takes PRs only from its writers (check-access). Without Write there, report the verified entry to the developer and commit without the trailer.
  5. Use the new verified identity only after its registry entry exists on the branch. Never rewrite already-published commits merely to add attribution.

Existing registry entries are durable memory and are intentionally not rechecked during ordinary commits. Correct or retire one only through another reviewed registry change.

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.