fix(kyberforge): fix tests/ read gap, evals/ loop, and description nav pointers
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016z2ZFYHQCex8yZAMVMTZzZ
This commit is contained in:
@@ -8,8 +8,8 @@ description: >
|
||||
checks plus qualitative review of description quality, body discipline, formatting,
|
||||
file structure, and internal consistency. Produces a compact findings report
|
||||
(findings only, no PASS noise) with Why and Fix per finding, suitable for agent
|
||||
handoff to /skill-improve or human auditability. Do not use to run evals, fix
|
||||
application code bugs, or perform general code review unrelated to skill quality.
|
||||
handoff to /skill-improve or human auditability. Do not use to fix application
|
||||
code bugs or perform general code review unrelated to skill quality.
|
||||
Do not use when the user wants improvements applied — use /skill-improve instead.
|
||||
allowed-tools: Bash Read
|
||||
metadata:
|
||||
@@ -30,7 +30,7 @@ Note any structural FAILs — they will appear in the report as a `### Structure
|
||||
|
||||
## Step 2 — Read all skill files
|
||||
|
||||
Read every file in the skill directory: `SKILL.md`, `README.md` (if present), all files in `scripts/`, `references/`, and `assets/`. Skip binary files only. Do not skip text files — internal consistency checks require the full picture.
|
||||
Read every file in the skill directory: `SKILL.md`, `README.md` (if present), all files in `scripts/`, `references/`, `assets/`, and `tests/`. Skip binary files only. Do not skip text files — internal consistency checks require the full picture.
|
||||
|
||||
## Step 3 — Qualitative audit
|
||||
|
||||
|
||||
@@ -29,7 +29,6 @@ If the skill dir is missing, ask for it. If no signals are present, stop: "This
|
||||
Signals can come from anywhere in the conversation or referenced files:
|
||||
- Grill session output (most common predecessor in the factory sequence)
|
||||
- `/skill-audit` findings (PASS/FAIL/SUGGESTION punch list)
|
||||
- Eval assertion failures (grading.json, benchmark.json)
|
||||
- Human feedback (feedback.json, inline in conversation, PR or issue comments)
|
||||
- Session context describing what went wrong
|
||||
|
||||
@@ -41,7 +40,7 @@ Group signals by **root cause**, not symptom. Ask: "What single gap in the skill
|
||||
|
||||
```text
|
||||
Example:
|
||||
- Eval fails because output format is wrong
|
||||
- Session context: output format is wrong on every run
|
||||
- Audit finding: no output template defined
|
||||
- User feedback: "I always have to ask it to format the output"
|
||||
→ Root cause: SKILL.md has no output format specification → one fix: add an output template
|
||||
@@ -72,5 +71,3 @@ If a signal points to a script or reference file, edit that file directly rather
|
||||
## Step 5 — Validate and close
|
||||
|
||||
Run `/skill-audit` on the skill directory. Resolve any FAIL findings before considering the improvement complete.
|
||||
|
||||
If the skill has no `evals/` directory, note it after the audit: "No evals found — consider adding an `evals/` directory with assertion-based test cases to give future improvement cycles quantitative signals to work from."
|
||||
|
||||
@@ -7,8 +7,8 @@ description: >
|
||||
skill following the agentskills.io specification — scaffolds the directory
|
||||
structure from annotated templates, fills in SKILL.md and supporting files, then
|
||||
validates the result. Performs best when preceded by a grill session and domain
|
||||
research. Do not use to update an existing well-formed skill, write evals, or
|
||||
author agent definition files.
|
||||
research. Do not use to update an existing well-formed skill — use /skill-improve
|
||||
instead. Do not use to author agent definition files.
|
||||
allowed-tools: Bash Read Write
|
||||
metadata:
|
||||
category: factory
|
||||
|
||||
Reference in New Issue
Block a user