Defame1297
0d96dc8282
New skill that creates or improves an apm hook, instruction or prompt. Its SKILL.md holds the shared procedure (dispatch on primitive, boundary gate, create-or-improve, factory-audit close); one self-contained reference per primitive carries its gate, checklist and template, drawn from the microsoft-apm research docs and ADR-0029. forge gains a route row sending a hook, instruction or prompt to primitive-author through author-routes.md, and no longer lists hooks as unroutable. factory-audit's description adds the primitive-author boundary now that the target resolves. Fixes #94 Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01KkT7RSDwDbmrM9T34b6sTi
2.9 KiB
source_keys
| source_keys | |||
|---|---|---|---|
|
Authoring an apm prompt
Reached from SKILL.md Step 1 for a prompt. Run the Gate, then write against the description
contract and the checklist, then return to SKILL.md Step 3.
Gate
This repo holds a prompt to ADR-0029, which is stricter than apm: apm calls a prompt "a callable
program", but on Claude it deploys as a command that is a skill in every respect except that it
keeps fewer frontmatter keys, apm drops disable-model-invocation so it can never be made
user-only, and Codex receives no prompts at all. A prompt that carries procedure is therefore a
worse skill on every harness.
- Reusable know-how, steps, gotchas, bundled files, or anything the model should find on its
own → a skill. Stop and hand to
skill-author; if a short steering message is still wanted afterwards, come back and write it against the new skill. - A single-intent message the user would otherwise type repeatedly, steering existing skills or
agents by name → continue. Confirm each skill or agent it names exists and is not
disable-model-invocation: true, which the model cannot invoke.
Description contract
One plain, user-facing sentence stating the action and naming the skills it steers — "Review the
current PR with gitea-prs and factory-audit, then summarise the findings." No "Use when"
trigger clause and no Not X -> Y boundary: on Claude the description is model-visible, and a
trigger clause invites the router to pick the wrapper over the skills it wraps. 250 characters at
most.
Checklist
Copy assets/templates/name.prompt.md.template and drop .template only on the final path.
Must:
- The path is
.apm/prompts/<name>.prompt.md, directly in that directory, not a symlink.<name>is a safe path segment and unique across.apm/prompts/and the package root; it becomes the Copilot filename and the Claude/commandname. descriptionis present and non-empty, per the contract above.- Every
input:name matches^[A-Za-z][\w-]{0,63}$, written in the object form- pr_number: "The PR to review". Never copy apm's published- name: pr_number/description: …example: apm reads the map's keys, so it produces the argumentsnameanddescription. - Every
${input:x}in the body is declared ininput:, and every declared name is used. Withoutinput:, no${input:…}may appear — it would reach Claude unrewritten. - Frontmatter keys stay within
description,allowed-tools,model,argument-hintandinput. Claude drops everything else with only a warning.
Should:
- Spell keys in kebab-case —
allowed-tools,argument-hint— not the camelCase aliases. - Omit
argument-hintwheninput:is set; apm synthesises<a> <b>from the input names. - Keep one intent per prompt, and write the body as second-person instructions.