review

Analyze the available skill set and recommend candidate groups that could be consolidated into sub-skill bundles. Read-only — proposes a plan, does not move files.

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 ./packages/agent-core-v2/src/app/skillCatalog/builtin/sub-skill/review/SKILL.md

Quality

Content

85%

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

The content is a concise, well-structured read-only workflow with clear sequencing and an explicit stop/handoff boundary, well-suited to a simple sub-skill. The only weaker dimension is actionability, which stays instructional because the task is inherently a planning/analysis step rather than one that yields executable commands.

Dimension	Reasoning	Score
Conciseness	At ~42 lines the body is lean and assumes Claude's competence — it states the task, lists a 6-step process, criteria, and an example without explaining what sub-skills or skill registries are, so every token earns its place.	3 / 3
Actionability	It gives concrete-ish steps (list inventory, categorize by domain, detect coupling, flag granularity, propose structures with parent/children/has-sub-skill) but no executable commands or copy-paste-ready artifacts — guidance is instructional rather than command-level, fitting the 'some concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	A clearly numbered 6-step sequence with an explicit stop/validation checkpoint ('Output a summary report... stop. Do not edit any file') and a defined handoff boundary to sub-skill.consolidate; the read-only constraint itself acts as the validation gate for this batch/proposal operation.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the body is under 50 lines with well-organized sections (When to use, Process, Criteria, Example output format); per the rubric's simple-skill note this warrants a 3 with just well-organized sections and no nested references.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 is specific, third-person, and clearly scoped to a read-only proposal step with good distinctiveness from sibling skills. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which leaves the 'when to use' answer only implied and caps completeness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to review, reorganize, or audit their skill inventory, or evaluate whether a new skill should become a sub-skill of an existing parent.'

Broaden trigger terms toward natural user phrasings such as 'group my skills', 'organize skills', or 'tidy up the skill set' to improve trigger-term coverage.

Keep the read-only/non-mutating promise since it is the key differentiator from sub-skill.consolidate.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Analyze the available skill set and recommend candidate groups that could be consolidated into sub-skill bundles' — and specifies the read-only deliverable ('proposes a plan, does not move files'), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly answers 'what' (analyze and recommend consolidation groups) but 'when' is only implied via the capability statement; there is no explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Contains some natural terms a user might say ('review', 'reorganize', 'audit', 'sub-skill bundles') but lacks common phrasings users would naturally invoke (e.g. 'group skills', 'organize my skills', 'tidy up skills'), so coverage is partial rather than comprehensive.	2 / 3
Distinctiveness Conflict Risk	It carves a clear niche — proposing sub-skill consolidation read-only, distinct from the 'consolidate' step that actually moves files — and its triggers ('review, reorganize, or audit the skill inventory') are unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: MoonshotAI/kimi-code
Path: packages/agent-core-v2/src/app/skillCatalog/builtin/sub-skill/review/SKILL.md
Commit: 77618e3

Reviewed: 2 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.