Skill Routing Benchmark
v1.0.0测试多个 Skill 描述是否会路由冲突，并生成正例、反例与负向触发语句。；use for skills, routing, benchmark workflows；do not use for 只给模糊建议, 忽略高度相近的 skill.
⭐ 0· 102·0 current·0 all-time
byvx：17605205782@52yuanchangxing
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description, SKILL.md, README, resources/spec.json, template, and scripts/run.py all align: the bundle is a local tool to analyze skill descriptions, find routing conflicts, and generate example prompts. Required binary is only python3 and no credentials/config paths are requested — this is proportionate for the stated purpose.
Instruction Scope
SKILL.md explicitly tells the agent to either run the included script (python3 scripts/run.py) or synthesize output using the local spec/template. The script reads files from the provided input path (scanning many text file types) and produces structured reports. This stays within the described scope, but it does read arbitrary files from the supplied directory/input: avoid passing directories containing sensitive data or system configuration. The SKILL.md includes sensible safety boundaries (dry-run, audit-first, do not execute high-risk commands).
Install Mechanism
No install spec; this is an instruction-only skill with an included Python script that runs under the system python3. There are no downloads, external package installs, or archive extraction steps in the bundle — low install risk.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The runtime script operates on files supplied as input and does not embed network endpoints or request secrets.
Persistence & Privilege
always is false and the skill does not request persistent system-level presence or modify other skills. It does not include steps to permanently change agent configuration. Autonomous invocation is allowed (platform default) but not combined with broad privileges.
Assessment
This skill appears coherent and low-risk: it runs a local Python script to analyze skill descriptions and produce structured reports. Before running: (1) review scripts/run.py yourself (it is included and readable); (2) avoid pointing the tool at directories or files that contain secrets or sensitive system configs — it will read and sample text files; (3) use the --dry-run and/or run in a sandboxed environment the first time; (4) verify outputs before copying or using them in any automated publish/workflow. There are no required credentials or network downloads in the bundle. If you need to be extra cautious, inspect the repo locally and run the script on a small, non-sensitive sample input first.Like a lobster shell, security has layers — review code before you run it.
latestvk9718z15x6w97cz9qmrwvf1p0983987c
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🚦 Clawdis
OSmacOS · Linux · Windows
Binspython3