SKILLEMALL.ai
GitHub ↗ RU Sign in

AC watcha-finder

Find, evaluate, and recommend AI products using the watcha.cn platform API. Use this skill whenever the user asks about AI tools, AI products, AI apps, or wants to discover/compare/evaluate AI products in China or globally. Also use when the user mentions watcha, watcha.cn, or wants product recommendations for specific use cases (e.g., "what's a good AI coding tool?", "find me an AI video generator", "哪个AI写作工具好用"). This skill knows how to search, filter, read reviews, and cross-reference with web sources to give well-rounded product assessments — not just popularity rankings.

modbender/skill-library-mcp Agent Skills author: modbender MIT 2 files body ≈ 1 874 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Find, evaluate, and recommend AI products using the watcha.cn platform API. Use this skill whenever the user asks about AI tools, AI products, AI apps, or…

As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

AnalyzerSoftware developmentMedia and videotype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
96/100
safety, quality, tests
Safety 60%
100
Quality 40%
89
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 0

    ✓ No critical or high findings

    Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 57/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 1 mutating operations with no state check
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 85Steps. 41 steps, 2 vague phrases
    • 100Failures and branches. 2 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1874 tokens
    • medium 3 test cases, all positive: not one "should refuse" or "should ask first"

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 3 example trigger phrases
    • +3Description length 582: enough signal without eating the budget
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 41 items
    • +4Has examples (6 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.