CtrlK
BlogDocsLog inGet started
Tessl Logo

sub-skill

Discover and reorganize the skill inventory into hierarchical sub-skill bundles. Use when the user asks to review, group, or consolidate skills into a parent bundle.

71

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-structured, concise container skill with a clear gated workflow and good navigation to its sub-skills. The main gap is actionability: it describes the orchestration flow but defers the concrete execution details to the sub-skills.

Suggestions

Add a brief note on how the user-approval checkpoint is obtained (e.g., present the review proposal and wait for explicit confirmation) so the validation gate is fully actionable.

Include one concrete pointer to what 'consolidate' actually does mechanically (e.g., the directory moves or backup command) rather than fully deferring it, so a reader can act without loading the sub-skill first.

Clarify how 'sub-skill.review' produces its proposal (e.g., output format or where the candidate groupings are shown) to raise actionability toward fully executable guidance.

DimensionReasoningScore

Conciseness

The body is lean with no padding or explanation of concepts Claude already knows; every section (When to use, Sub-skills, flow note) earns its place, matching the score-3 anchor.

3 / 3

Actionability

It gives a concrete flow and an explicit safety rule ('Never run consolidate without an explicit go-ahead'), but the actual mechanics of reviewing and consolidating are deferred to the sub-skills with no executable detail here, leaving key details missing like the score-2 anchor.

2 / 3

Workflow Clarity

A clear two-step sequence (review then consolidate) with an explicit approval checkpoint for the destructive consolidate step and a stated backup safety measure; the simple-skills carve-out permits a 3 for this clean, gated flow, and validation is present so it is not capped at 2.

3 / 3

Progressive Disclosure

Under 50 lines with well-organized sections and one-level-deep, clearly signaled sub-skill references (sub-skill.review, sub-skill.consolidate), matching the score-3 guidance for compact skills with no deeply nested references.

3 / 3

Total

11

/

12

Passed

Description

90%

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 description: it concisely states what the skill does and when to use it with natural, multiple trigger terms and a distinct niche. Its only weakness is modest action specificity, naming just two verbs.

DimensionReasoningScore

Specificity

Names the domain ('skill inventory', 'sub-skill bundles') and two actions ('Discover and reorganize'), but the actions are limited and not comprehensive, matching the score-2 anchor rather than the multi-action score-3 example.

2 / 3

Completeness

It states both what ('Discover and reorganize the skill inventory into hierarchical sub-skill bundles') and when ('Use when the user asks to review, group, or consolidate skills'), with an explicit trigger clause, matching the score-3 anchor exactly.

3 / 3

Trigger Term Quality

The 'Use when the user asks to review, group, or consolidate skills into a parent bundle' clause supplies several natural terms a user would actually say, giving good coverage; it is not merely a single keyword like the score-2 example.

3 / 3

Distinctiveness Conflict Risk

The meta-niche of reorganizing the skill inventory into parent bundles has distinct triggers unlikely to fire for ordinary skills; it is clearly distinguishable rather than the somewhat-overlapping score-2 case.

3 / 3

Total

11

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
MoonshotAI/kimi-code
Reviewed

Table of Contents

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.