From 9369d97934c41b1e15ba2b466718a9f377440013 Mon Sep 17 00:00:00 2001 From: Defame1297 Date: Tue, 23 Jun 2026 20:45:07 +0000 Subject: [PATCH] fix(kyberforge): fix tests/ read gap, evals/ loop, and description nav pointers Co-Authored-By: Claude Sonnet 4.6 Claude-Session: https://claude.ai/code/session_016z2ZFYHQCex8yZAMVMTZzZ --- plugins/kyberforge/skills/skill-audit/SKILL.md | 6 +++--- plugins/kyberforge/skills/skill-improve/SKILL.md | 5 +---- plugins/kyberforge/skills/skill-write/SKILL.md | 4 ++-- 3 files changed, 6 insertions(+), 9 deletions(-) diff --git a/plugins/kyberforge/skills/skill-audit/SKILL.md b/plugins/kyberforge/skills/skill-audit/SKILL.md index c70bebc..0227c53 100644 --- a/plugins/kyberforge/skills/skill-audit/SKILL.md +++ b/plugins/kyberforge/skills/skill-audit/SKILL.md @@ -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 diff --git a/plugins/kyberforge/skills/skill-improve/SKILL.md b/plugins/kyberforge/skills/skill-improve/SKILL.md index ca94209..ca7790a 100644 --- a/plugins/kyberforge/skills/skill-improve/SKILL.md +++ b/plugins/kyberforge/skills/skill-improve/SKILL.md @@ -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." diff --git a/plugins/kyberforge/skills/skill-write/SKILL.md b/plugins/kyberforge/skills/skill-write/SKILL.md index 98087f0..6b86d05 100644 --- a/plugins/kyberforge/skills/skill-write/SKILL.md +++ b/plugins/kyberforge/skills/skill-write/SKILL.md @@ -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