skill-builder

Reviews and improves SKILL.md packages by fixing audit findings, triggers, examples, evals, token budget, release proof, safety verdicts, comparator/baseline choices, and bounded code-lens hardening. Use when the user says improve a skill, fix a skill file, review SKILL.md, raise Tessl score, reduce context cost, add skill evals, or prepare a plugin skill for release.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete commands, exact pass thresholds, and a well-sequenced gate-rerun workflow. Its weaknesses are token efficiency (repetitive release-evidence rules that belong in references) and progressive disclosure (two broken referenced paths and inlined policy detail).

Suggestions

Conciseness: Move the repetitive 'Live-private release evidence requires ...' rules and release-threshold detail out of the Validation and Execution Boundaries sections into a reference file; the skill's own Gotchas warns against crowding the entrypoint with package-specific repair details.

Progressive disclosure: Two referenced paths do not exist in the bundle (Infrastructure/references/first-principles-factory-gate.md and Plugins/skill-factory/references/tessl-knowledgeos-capsule.md) — either add these files or remove the references so navigation is not broken.

Progressive disclosure: Convert the plain-text reference paths in the References section to markdown links and keep supporting policy one level deep in those files instead of inlining it in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is terse and assumes Claude's competence (no basic-concept padding), but the Validation and Execution Boundaries sections repeat many 'Live-private release evidence requires...' rules that overlap reference policy, so it could be tightened — matching the score-2 'mostly efficient but could be tightened' anchor rather than 'every token earns its place'.	2 / 3
Actionability	It gives copy-paste-ready commands with flags ('./bin/ask skills external-review <target> --audit-level compat --json --robot', './bin/ask sdk start <skill-path> --json --robot') plus exact pass thresholds ('score >= 90 with 95+ target', 'usage >= max(0.90, baseline)'), matching the score-3 fully-executable anchor.	3 / 3
Workflow Clarity	The numbered Workflow (1–7) sequences gate-rerun feedback explicitly — 'Apply one Repair Map change ... then rerun the same gate', 'After three flat loops, stop with blocker_notes', 'On green, run final gates' — with validation checkpoints and an error-recovery loop, matching the score-3 anchor.	3 / 3
Progressive Disclosure	Section structure is good and seven local references are real and one level deep, but two referenced paths are missing from the bundle (Infrastructure/references/first-principles-factory-gate.md and Plugins/skill-factory/references/tessl-knowledgeos-capsule.md) and substantial policy is inlined rather than split out, matching the score-2 'could be better organized / content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that states concrete capabilities and provides an explicit 'Use when...' trigger clause with natural user phrasings. It is dense but every clause names a concrete action or trigger rather than vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person ('Reviews and improves SKILL.md packages by fixing audit findings, triggers, examples, evals, token budget, release proof, safety verdicts, comparator/baseline choices, and bounded code-lens hardening'), matching the score-3 anchor rather than the single-action score-2 example.	3 / 3
Completeness	It explicitly answers both 'what' (Reviews and improves SKILL.md packages...) and 'when' with an explicit 'Use when...' trigger clause, so completeness is not capped at 2 and matches the score-3 anchor.	3 / 3
Trigger Term Quality	The 'Use when the user says improve a skill, fix a skill file, review SKILL.md, raise Tessl score, reduce context cost, add skill evals, or prepare a plugin skill for release' clause gives good coverage of natural phrasings a user would actually say, beyond the score-2 'some relevant keywords' anchor.	3 / 3
Distinctiveness Conflict Risk	The SKILL.md-package repair niche with triggers tied to skill files, evals, Tessl, and plugin release is clearly distinguishable and unlikely to fire for unrelated skills, matching the score-3 'clear niche with distinct triggers' anchor.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Plugins/skill-factory/skills/code_quality_review/skill-builder/SKILL.md
Commit: 4f7075e

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.