CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

clawhub-featured

Prepare evidence-based ClawHub Featured recommendations or apply explicitly authorized Featured changes through existing audited staff commands.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-5

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

The body is an exemplar of lean, high-constraint operational writing: exact commands, explicit validation and authorization gates, correct handling of untrusted catalog data, and a clean split of the destructive-change procedure into a single real reference file. No significant weaknesses were found in any dimension.

DimensionReasoningScore

Conciseness

The body is lean and operational throughout — e.g. "Saved reports expire after 24 hours", "Search matches are separate context; they are neither installs nor evidence of unique users" — with no explanation of concepts Claude already knows and no padding. Every token carries a constraint or instruction, matching 'lean and efficient; assumes Claude's competence; every token earns its place'.

5 / 5

Actionability

Guidance is fully executable and copy-paste ready: exact CLI invocations ("bun run admin -- search-insights --view recommendations --artifact-kind plugin --json", "search-insights --report-id <id> --json"), concrete HTTP GETs with sort and limit parameters, and a specified brief format (catalog, identity, listing link, one reason, evidence period, report IDs, Management link). The common cases are covered by specific examples, matching the top anchor.

5 / 5

Workflow Clarity

The five-step sequence is clearly ordered (locate CLI/auth → read catalogs → analyze report → discovery context → return brief) with explicit checkpoints: "verify it identifies that listing", "a stale report needs refresh before promotion review", "Report errors or incomplete evidence remain explicit", and resume handling ("Resume an in-flight report with search-insights --report-id <id>"). Validation for the destructive membership-change workflow is fully present (dry-run then --apply, read-back of listing/shelf/audit, inspect-before-retry in references/promotion.md), so the destructive-operation cap does not apply — matching 'clear sequence with explicit validation steps; feedback loops for error recovery'.

5 / 5

Progressive Disclosure

The body is a concise overview of both modes with the detailed promotion procedure appropriately split into a single, well-signaled, one-level-deep reference: "Read [references/promotion.md](references/promotion.md) for an explicitly authorized item change or complete-set publication" (verified to exist and match its purpose). Sections are clear and navigation is easy, matching 'clear overview with well-signaled one-level-deep references; content appropriately split'.

5 / 5

Total

20

/

20

Passed

Description

57%Weight 40%Scale 1-5

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 precise, honest, and highly distinctive within its niche, with two clearly stated concrete capabilities in third person. Its main weakness is the complete absence of 'when to use this' trigger guidance and of natural synonyms (promote, curate, spotlight), which leaves a user or model unsure when to invoke it.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g. 'Use when the user asks for ClawHub Featured recommendations, wants to feature/promote a specific plugin or skill, or requests an authorized change to the Featured selection.'

Include natural synonyms users would say — promote, curate, spotlight, highlight — so the description matches phrasings beyond 'Featured'.

Briefly name the primary deliverable (a curation brief with evidence periods and report IDs) so the 'what' covers the skill's main output.

DimensionReasoningScore

Specificity

"Prepare evidence-based ClawHub Featured recommendations or apply explicitly authorized Featured changes through existing audited staff commands" names the domain plus exactly two concrete actions (prepare recommendations, apply authorized changes), matching the '1-2 concrete actions, but not comprehensive' anchor. It is not a 4 because it omits other covered actions (reading insight reports, producing a curation brief, discovery context reads), and not a 2 because the actions named are concrete and precisely qualified rather than generic.

3 / 5

Completeness

The 'what' is clear (prepare evidence-based recommendations or apply explicitly authorized Featured changes), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines. It is not a 4 because 'when' is entirely absent rather than merely implicit; not a 2 because the 'what' is specific, not vague.

3 / 5

Trigger Term Quality

Relevant keywords are present ("ClawHub", "Featured", "recommendations", "staff commands"), but common variations a user might naturally say — promote, curate, spotlight, highlight, feature an item — are absent. This fits 'some relevant keywords but missing common variations or synonyms'; it is above 2 (the core domain terms are the natural ones) but below 4 (several natural synonyms missing).

3 / 5

Distinctiveness Conflict Risk

"ClawHub Featured" plus "audited staff commands" defines a clear platform-specific niche with distinct triggers; virtually no other skill would collide with these terms. This matches the 'clear niche with distinct triggers; minimal conflict risk' anchor exactly.

5 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

openclaw/clawhub

Path

.agents/skills/clawhub-featured/SKILL.md

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.