CtrlK
BlogDocsLog inGet started
Tessl Logo

find-skills

Search and discover OpenClaw skills from various sources. Use when: user wants to find available skills, search for specific functionality, or discover new skills to install.

60

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./configs/microservice/bff-service/configs/agent-skills/clawhub/find-skills-skill/SKILL.md

The canonical home for this skill is find-skills in UnicomAI/wanwu

SKILL.md
Quality
Evals
Security

Quality

Content

67%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, actionable discovery guide with concrete commands and clear routing. Its main weakness is token efficiency: redundant command examples and generic best-practice tips inflate the body without adding capability Claude lacks.

Suggestions

Collapse the three "Search Strategies" subsections into a single block showing `npx clawhub search "<keyword>"` with a few argument variants (`--sort installs`, `--sort stars`), instead of repeating the same command nine times.

Trim generic Best Practices and Installation Tips that Claude already knows (e.g. "Check for updates regularly", "Read documentation", "Test thoroughly") and keep only skill-specific guidance.

Add a short "Which source to try first" decision note (e.g. ClawHub first, then the directories, then GitHub) to give the discovery flow an explicit sequence.

DimensionReasoningScore

Conciseness

The body is mostly scannable lists, but it pads repeated near-identical `npx clawhub search` command blocks across three subsections and includes generic advice ("Check for updates regularly", "Read documentation", "Test thoroughly") that Claude already knows, so it could be tightened.

3 / 5

Actionability

It provides concrete, copy-paste-ready commands (`npx clawhub search "keyword"`, `npx clawhub browse`, `--sort installs`) and direct URLs for each source, with only minor gaps such as no example output and a couple of referenced commands shown without full syntax.

4 / 5

Workflow Clarity

As a simple single-purpose skill it is well organized with clear When-to-Use / When-NOT-to-Use routing and a small numbered troubleshooting sequence, though it lacks an explicit decision flow for which source to try first.

4 / 5

Progressive Disclosure

Section structure is clear and a single file is appropriate for a guide of this kind (no bundle files exist), but the long inline "Common Skill Categories" catalog is reference-like content that could be split out, leaving minor organization gaps.

4 / 5

Total

15

/

20

Passed

Description

78%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.

A strong, well-formed description that clearly states both capability and trigger conditions in third person. It is mostly distinct and complete, with only minor gaps in action specificity and synonym coverage.

DimensionReasoningScore

Specificity

Names the domain ("OpenClaw skills") and two actions ("Search and discover") but the actions are near-synonyms and coverage is not comprehensive, matching the anchor that names a domain with 1-2 concrete actions.

3 / 5

Completeness

It explicitly answers both what ("Search and discover OpenClaw skills from various sources") and when ("Use when: user wants to find available skills, search for specific functionality, or discover new skills to install") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger phrases are present ("find available skills", "search for specific functionality", "discover new skills to install"), giving good keyword coverage, though a few natural variants (e.g. "browse skills") are missing so it stops short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

It has a clear niche (skill discovery) with distinct triggers, but the broad phrase "search for specific functionality" creates minor overlap risk with general web-search skills, keeping it just below a 5.

4 / 5

Total

16

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
UnicomAI/wanwu
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.