CtrlK
BlogDocsLog inGet started
Tessl Logo

wechat-search

Search WeChat Official Account articles using OpenClaw's web search, Tavily API, and web fetch capabilities with compliance-focused design.

58

Quality

66%

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/wechat-search/SKILL.md
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 body provides concrete, executable CLI examples and a clearly sequenced fallback workflow in a well-organized single file. Its main weakness is redundancy between the Features, Strategy Details, and Compliance sections, which inflates length without adding actionable detail.

Suggestions

Collapse the 'Features' three-layer bullet list since the same strategy is fully described in 'Search Strategy Details' — keep Features to one line per feature.

Merge the 'Compliance & Ethics' bullets into the relevant Layer descriptions to avoid restating robots.txt, rate-limiting, and User-Agent twice.

Add a brief explicit verification step (e.g. 'confirm results are recent WeChat OA articles, not search-engine noise') to make the fallback workflow's checkpoints explicit.

DimensionReasoningScore

Conciseness

The body is mostly efficient and does not over-explain basics, but the 'Features' list restate the three-layer strategy that is detailed again in 'Search Strategy Details', and the 'Compliance & Ethics' section repeats robots.txt/rate-limit/User-Agent points already made in Layer 3 and the config.

3 / 5

Actionability

Concrete, copy-paste-ready bash commands with flags and a complete config JSON example are provided, though the internal API/HTML-parsing logic is described abstractly rather than shown as executable code.

4 / 5

Workflow Clarity

The three-layer fallback sequence (Brave → Tavily → direct fetch) with retry/fallback handling is clearly ordered; the skill is read-only so the destructive/batch validation cap does not apply, but explicit result-verification checkpoints are only implicit.

4 / 5

Progressive Disclosure

A single well-organized SKILL.md with clear section headers and no bundle files; structure is good, though at ~95 lines some inline content (redundant Features vs Strategy Details, Future Enhancements) could be trimmed to tighten navigation.

4 / 5

Total

15

/

20

Passed

Description

66%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 clearly states what the skill does and names its concrete methods, but it lacks any explicit 'when to use' trigger guidance, which limits completeness. Trigger coverage is good but misses common Chinese synonyms users would naturally say.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when searching WeChat Official Account (微信公众号) articles or when the user mentions 公众号, WeChat posts, or 微信文章.'

Include Chinese synonyms (公众号, 微信文章) alongside 'WeChat Official Account articles' to broaden natural trigger coverage.

Consider tightening 'with compliance-focused design' — it is borderline fluff that does not add a concrete capability.

DimensionReasoningScore

Specificity

Names the domain ('WeChat Official Account articles') and lists three concrete search methods ('OpenClaw's web search, Tavily API, and web fetch capabilities'), giving several specific actions with only minor coverage gaps.

4 / 5

Completeness

The 'what' is clear (search WeChat OA articles via three layered APIs), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Includes natural terms like 'WeChat Official Account articles' and 'search', but omits common synonyms users would say (e.g. '公众号', 'WeChat posts', '微信文章'), so a few natural terms are missing.

4 / 5

Distinctiveness Conflict Risk

The WeChat Official Account article niche is mostly distinct with clear triggers, though there is minor overlap risk with general web-search skills.

4 / 5

Total

15

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.