feat: implement issue 0017 — factory/write-eval bootstrap skill

Adds write-eval, the first factory meta-skill. Produces eval.yaml test
files for skills following the two-section schema (trigger_tests +
output_tests) with provider-agnostic string assertions and show-plan-
then-merge-on-rerun behaviour. Hand-written bootstrap — subsequent
skills will use write-eval to produce their own evals.

Also tightens skill-implementation-workflow.md step 5b: per-section
options walk-through is now a named gate before writing, separate from
the synthesis grill. LESSONS.md entry added.

HITL behavioral test pending.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-05-17 17:52:02 +00:00
parent c705a38809
commit 83715018eb
7 changed files with 286 additions and 18 deletions

View File

@@ -92,8 +92,16 @@ Write the `description:` frontmatter field first. Test it against three cases be
Do not proceed to the body until all three pass.
**b. SKILL.md** (sub-agent)
Spawn a write agent to produce the SKILL.md using `write-skill` (or hand-write for bootstrap skills). The agent receives: trigger description, synthesis grill decisions, upstream content to incorporate, authoring standard (see below).
**b. Per-section options walk-through**
Before writing anything, walk through each body section with the human. For each section:
- State what content is proposed and which upstream source it comes from
- Present alternatives where upstream sources offered different approaches
- Get explicit confirmation (or redirection) before moving to the next section
Do not write the SKILL.md until the human has confirmed every section. The synthesis grill decisions cover the eval schema and gating questions; this step covers how upstream content maps to each SKILL.md section. These are separate conversations — do not collapse them.
**c. SKILL.md** (sub-agent)
Once all sections are confirmed, spawn a write agent to produce the SKILL.md using `write-skill` (or hand-write for bootstrap skills). The agent receives: trigger description, per-section decisions from step b, upstream content to incorporate, authoring standard (see below).
**c. `source:` and `references:` fields**
Populate after upstream review. Two distinct fields: