CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

clawhub

Search ClawHub for plugins by default, or skills when explicitly requested; install, verify, update, uninstall, publish, or sync skills.

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

82%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 content is a well-structured, fully executable CLI reference with explicit verification and confirmation checkpoints for its destructive and install operations. Minor gains are available from consolidating repeated uninstall command variants and adding brief guidance for verification failures.

Suggestions

Consolidate the three uninstall --workdir variants into one command plus a short note on choosing the workdir (agent workspace vs. --global state dir vs. $OPENCLAW_STATE_DIR), and mention the clawhub CLI installation once.

Add one line on handling verification failure (e.g., "If verify reports issues, do not install; report the findings to the user") to close the error-recovery gap around installation.

Tighten the "Notes" section into the relevant sections so the closing miscellany does not accumulate.

DimensionReasoningScore

Conciseness

The body is lean and command-focused with almost no explanation of known concepts, but has minor redundancy: the uninstall command is repeated across three --workdir variants and "npm i -g clawhub" appears twice (Remove and Publish sections). Fits the efficient-with-minor-trims anchor rather than the every-token-earns-its-place anchor.

4 / 5

Actionability

Every section provides fully executable, copy-paste-ready commands covering common cases, including variants like "openclaw skills install my-skill --version 1.2.3", "clawhub --workdir \"$OPENCLAW_STATE_DIR\" uninstall @owner/my-skill", and "clawhub skill publish ./my-skill --version 1.2.3". Matches the fully-executable anchor.

5 / 5

Workflow Clarity

Sections are clearly sequenced (discover → install → manage → remove → publish) with explicit checkpoints: "Verify the selected skill first and report the result" before install, and the uninstall confirmation behavior is stated. It falls short of 5 because there is no error-recovery guidance (e.g., what to do when "openclaw skills verify" fails or uninstall confirmation should be declined).

4 / 5

Progressive Disclosure

The body (~103 lines) is organized into clear, well-navigable sections with no nested references and nothing that clearly belongs in a separate file, but it exceeds the simple-skill threshold: the uninstall section's repeated command variants and the catch-all "Notes" section are minor organization gaps that could be consolidated.

4 / 5

Total

17

/

20

Passed

Description

75%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 specific and comprehensive on actions with a clearly distinct niche, but lacks an explicit "Use when..." trigger clause, capping completeness, and misses a few natural synonyms. Adding overall invocation guidance would lift it substantially.

Suggestions

Add an explicit trigger clause such as "Use when the user wants to find, install, or manage OpenClaw plugins or skills, or publish/update their own skills to ClawHub".

Include natural synonyms users might say, e.g., "find or add plugins", "remove skills", and "browse the ClawHub registry", to broaden trigger coverage.

Consider naming "OpenClaw" in the description so searches mentioning the agent ecosystem also surface this skill.

DimensionReasoningScore

Specificity

"install, verify, update, uninstall, publish, or sync" lists multiple concrete actions covering the full skill lifecycle plus discovery ("Search ClawHub for plugins by default"), matching the comprehensive-coverage anchor. No meaningful coverage gap places it below 5.

5 / 5

Completeness

The "what" is explicit, but there is no "Use when..." clause or equivalent overall trigger guidance; "when explicitly requested" only distinguishes plugin vs. skill search scope, so the "when" for invoking the skill is only weakly implied. Per the judging guidelines, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural verbs users would say — "search", "install", "uninstall", "publish", "sync" — plus "plugins" and "skills". A few natural synonyms are missing (e.g., "find", "add", "remove", "browse"), so it does not reach comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Names the specific "ClawHub" registry and its ecosystem-specific lifecycle operations (publish, sync, uninstall via clawhub CLI), giving it a clear niche with distinct triggers and minimal conflict risk with generic skills.

5 / 5

Total

17

/

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/openclaw

Path

skills/clawhub/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.