skill-improve

Improve a skill using a test-fix-retest loop. Runs static checks, proposes targeted fixes, rewrites the skill, re-tests, and keeps or reverts based on score change.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-improve/SKILL.md

Quality

Content

92%

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

The body is a concise, highly actionable, well-sequenced workflow with strong validation feedback loops and a destructive-change revert path. Its only weakness is progressive disclosure: it is a single monolithic file with no content split out despite being well over the simple-skill line count.

Suggestions

Move the static-check diagnostic table (Check 1-7 gaps) and the category-check examples into a bundled reference (e.g. references/diagnostics.md) referenced one level deep from Phase 3, keeping the main flow lean.

Extract the catalog/category lookup logic and example category gaps into a references file so the core test-fix-retest loop stays as a concise overview.

Consider moving the Phase 2b/Phase 3 category-handling detail behind a clearly signaled reference, preserving the simple-skill workflow-clarity score while improving file organization.

Dimension	Reasoning	Score
Conciseness	Lean procedural prose across 7 phases with no concept explanation or padding ('Count of FAILs', exact stop messages, before/after display templates), matching the score-3 'every token earns its place' anchor; not 2 because there is no unnecessary explanation to trim.	3 / 3
Actionability	Provides concrete paths (`.claude/skills/[name]/SKILL.md`), exact commands (`/skill-test static [name]`, `git checkout -- ...`), literal failure messages, and copy-paste display templates, matching 'fully executable/specific examples'; not 2 because guidance is complete rather than pseudocode, and reliance on the invoked /skill-test is appropriate for an orchestration skill.	3 / 3
Workflow Clarity	A 7-phase sequence with an explicit feedback loop (baseline -> fix -> retest -> verdict), an ask-before-write confirmation gate, and a git-checkout revert for the destructive write, matching 'clear sequence with explicit validation steps and feedback loops'; not 2 because checkpoints are explicit, not implicit.	3 / 3
Progressive Disclosure	A single ~146-line monolithic SKILL.md with no bundle files and no external references; sections are well-organized but content like the category/catalog logic and diagnostic tables is inline rather than split out, matching 'some structure but content that should be separate is inline'; not 3 because it exceeds the simple-skill threshold without file splitting, and not 1 because references are not deeply nested.	2 / 3
	Total	11 / 12 Passed

Description

60%

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

The description conveys concrete actions and a clear purpose but omits any 'Use when...' trigger guidance, which caps completeness and weakens trigger-term quality and distinctiveness. It is specific on the 'what' but silent on the 'when'.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers, e.g. 'Use when a skill fails /skill-test or when you want to raise a skill's static/category check score.'

Mirror natural terms users would say ('skill failing checks', 'improve a skill score', 'fix skill warnings') instead of only task-internal jargon like 'test-fix-retest loop' and 'score change'.

Sharpen distinctiveness from /skill-test by framing this skill as the remediation/rewrite step that consumes /skill-test's output.

Dimension	Reasoning	Score
Specificity	Quotes 'test-fix-retest loop', 'Runs static checks', 'proposes targeted fixes', 'rewrites the skill', 're-tests', and 'keeps or reverts based on score change' — a list of multiple concrete actions matching the score-3 anchor; not score 2 because the actions are comprehensive rather than partial.	3 / 3
Completeness	Clearly answers 'what' (the improvement loop) but has no 'Use when...' trigger clause, so per the guidelines a missing explicit trigger caps completeness at 2; not 1 because the 'what' is strong, not 3 because 'when' is absent.	2 / 3
Trigger Term Quality	No natural user-facing trigger terms; relies on task-internal jargon ('test-fix-retest loop', 'static checks', 'score change') rather than phrasings a user would actually say, matching 'some relevant keywords but missing common variations'; not 3 due to absent natural-language coverage and not 1 because the terms are domain-relevant, not generic.	2 / 3
Distinctiveness Conflict Risk	Has a specific niche (skill improvement tied to score change) but 'improve a skill' could overlap with /skill-test and lacks explicit triggers to disambiguate, matching 'somewhat specific but could still overlap'; not 1 (not generic) and not 3 (no distinct trigger phrasing).	2 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/skill-improve/SKILL.md
Commit: 984023d

Reviewed: 3 days 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.