agentleFS
tunahanaliozturktunahanaliozturk/atelier/skills/writing-agents/SKILL.md

writing-agents

Skill1 starsChanged 5 months agoMITView on GitHub

Use when no registered agent covers a task, to scaffold a new specialist agent that follows the capability schema.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    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. Distinctive:

    When capability-routing returns a fallback (no agent fits), scaffold a new specialist rather than forcing a poor match.

    line 8
  2. Very specific:

    Create agents/<name>.md with frontmatter that follows docs/schemas/capability-schema.md: name, description (one line: what it does and when …

    line 14
  3. Distinctive:

    Write a short body: who the agent is, exactly what it does, and that it works only to the assigned task and reports back concisely.

    line 18
  4. Very specific:

    Verify it loads: node hooks/session-start.mjs must list the new agent with no registry load skipped line (the registry validates layer, …

    line 20

“Common” is measured: kept by at least 6 in 10 of the 4 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

Writing Agents

When capability-routing returns a fallback (no agent fits), scaffold a new specialist rather than forcing a poor match.

  1. Name the gap: what layer and task_kinds does the uncovered task need? Confirm the layer is one of orchestration, backend, frontend, infra, data, docs, review.
  2. Create agents/<name>.md with frontmatter that follows docs/schemas/capability-schema.md: name, description (one line: what it does and when to pick it), capabilities (list), layer, task_kinds (list), and optional model and color. Keep each value on a single line.
  3. Write a short body: who the agent is, exactly what it does, and that it works only to the assigned task and reports back concisely.
  4. Verify it loads: node hooks/session-start.mjs must list the new agent with no registry load skipped line (the registry validates layer, non-empty task_kinds, and unique names).
  5. Re-route the task with capability-routing; the new agent should now be the pick. Record the addition in the mission decision log.

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.