fix(kyberforge): apply audit findings across skill factory trio

- skill-audit: promote internal-working gotcha to ## Gotchas section;
  narrow cross-plugin path check to exclude tests/ (dev-only, repo-level
  deps are expected); require tests/README.md to declare that dependency
- skill-write/skill-improve: reorder descriptions to lead with "Use when..."
  for consistency with skill-audit and the agentskills.io spec trigger pattern
- skill-write: add tests/README.md with self-contained bats setup instructions;
  remove cross-skill reference to skill-audit's tests/README.md

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-06-23 19:48:20 +00:00
parent 193c40106d
commit 60d1f0852c
5 changed files with 54 additions and 20 deletions

View File

@@ -16,6 +16,10 @@ metadata:
category: factory category: factory
--- ---
## Gotchas
- Do not output PASS/FAIL per check while auditing — gather findings internally and surface them only in the Step 4 report. Narrating each check as you go is the default failure mode here.
## Step 1 — Structural validation ## Step 1 — Structural validation
```bash ```bash
@@ -30,7 +34,7 @@ Read every file in the skill directory: `SKILL.md`, `README.md` (if present), al
## Step 3 — Qualitative audit ## Step 3 — Qualitative audit
Work through each dimension internally. Do not output PASS/FAIL per check — this is internal working. Collect findings only; report them in Step 4. Cite file and line number for every finding. Work through each dimension internally. Collect findings only; report them in Step 4. Cite file and line number for every finding.
### Description ### Description
@@ -69,7 +73,8 @@ Check each pattern is appropriate and correctly formed:
- No non-spec files at the skill root (e.g. META.md, extra config files outside permitted directories) - No non-spec files at the skill root (e.g. META.md, extra config files outside permitted directories)
- Optional directories contain real content — not just unfilled placeholder READMEs - Optional directories contain real content — not just unfilled placeholder READMEs
- `README.md` present and accurately describes the skill and its files - `README.md` present and accurately describes the skill and its files
- No cross-plugin path references — paths using `../`, `../../`, or absolute repo paths (e.g. `plugins/kyberforge/skills/...`) break when the plugin is installed to a cache; flag any found - No cross-plugin path references in SKILL.md, scripts/, references/, or assets/ — paths using `../`, `../../`, or absolute repo paths (e.g. `plugins/kyberforge/skills/...`) break when the plugin is installed to a cache; flag any found
- `tests/` is exempt from the cross-plugin path check — test files are dev-only and may reference repo-level test infrastructure (e.g. a shared `tests/test_helper/`). This dependency must be declared in `tests/README.md`; flag if tests exist but `tests/README.md` is absent or does not document the dependency
### Formatting ### Formatting

View File

@@ -1,15 +1,15 @@
--- ---
name: skill-improve name: skill-improve
description: > description: >
Apply evidence-based improvements to an existing skill. Use when the user Use when the user says "improve this skill", "fix this skill based on
says "improve this skill", "fix this skill based on feedback", "apply these feedback", "apply these audit findings", or "update the skill based on this
audit findings", or "update the skill based on this grill output". Also use grill output". Also use when the user provides inline feedback about a skill's
when the user provides inline feedback about a skill's behavior and wants it behavior and wants it applied, or when a grill session, eval run, or audit has
applied, or when a grill session, eval run, or audit has produced findings produced findings the user wants acted on — even if they don't say "improve"
the user wants acted on — even if they don't say "improve" explicitly. Do explicitly. Applies evidence-based improvements to an existing skill. Do not
not use when the user wants a read-only review only — use /skill-audit use when the user wants a read-only review only — use /skill-audit instead.
instead. Do not use when no improvement signals are present in the Do not use when no improvement signals are present in the conversation or
conversation or referenced files. referenced files.
allowed-tools: Bash Read Write Edit allowed-tools: Bash Read Write Edit
metadata: metadata:
category: factory category: factory

View File

@@ -36,7 +36,8 @@ This skill produces its best output when you arrive with rich context:
| `assets/templates/references/README.md` | Placeholder for reference docs | | `assets/templates/references/README.md` | Placeholder for reference docs |
| `assets/templates/assets/README.md` | Placeholder for static assets | | `assets/templates/assets/README.md` | Placeholder for static assets |
| `assets/templates/tests/README.md` | Placeholder for test files | | `assets/templates/tests/README.md` | Placeholder for test files |
| `tests/new-skill.bats` | Bats test suite for new-skill.sh — requires bats-support and bats-assert in the repo root's `tests/test_helper/` (see skill-audit's `tests/README.md` for setup) | | `tests/new-skill.bats` | Bats test suite for new-skill.sh |
| `tests/README.md` | Setup instructions for bats-support and bats-assert test dependencies |
## Placement ## Placement

View File

@@ -1,14 +1,14 @@
--- ---
name: skill-write name: skill-write
description: > description: >
Author a new skill following the agentskills.io specification — scaffold the Use when the user wants to create a new skill from scratch, says "write a skill
directory structure from annotated templates, fill in SKILL.md and supporting for X", "build a skill that does Y", or "create a SKILL.md for Z", or wants to
files, then validate the result. Use when the user wants to create a new skill make a workflow repeatable or shareable as a reusable command. Authors a new
from scratch, says "write a skill for X", "build a skill that does Y", or skill following the agentskills.io specification — scaffolds the directory
"create a SKILL.md for Z", or wants to make a workflow repeatable or shareable structure from annotated templates, fills in SKILL.md and supporting files, then
as a reusable command. Performs best when preceded by a grill session and validates the result. Performs best when preceded by a grill session and domain
domain research. Do not use to update an existing well-formed skill, write research. Do not use to update an existing well-formed skill, write evals, or
evals, or author agent definition files. author agent definition files.
allowed-tools: Bash Read Write allowed-tools: Bash Read Write
metadata: metadata:
category: factory category: factory

View File

@@ -0,0 +1,28 @@
# tests/
Test files for scripts bundled with this skill.
## Dependencies
Tests require [bats-support](https://github.com/bats-core/bats-support) and
[bats-assert](https://github.com/bats-core/bats-assert). The test files load
helpers from the repo root's `tests/test_helper/`.
From the repo root:
```bash
git clone https://github.com/bats-core/bats-support tests/test_helper/bats-support
git clone https://github.com/bats-core/bats-assert tests/test_helper/bats-assert
```
Run all tests for this skill (from the repo root):
```bash
bats plugins/kyberforge/skills/skill-write/tests/
```
## Files
| File | Purpose |
|------|---------|
| `new-skill.bats` | Bats test suite for `scripts/new-skill.sh` |