Taxonomy Normalizer
v1.0.0统一不同团队、不同表里的分类体系，保留别名映射与废弃词。；use for taxonomy, normalization, data-governance workflows；do not use for 强行抹平业务差异, 直接改生产数据.
⭐ 0· 72·0 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 (taxonomy normalization, mapping, dry-run oriented) match the included assets and the bundled script. The only required binary is python3 which is appropriate for a Python script-based skill. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md limits activity to producing structured, reviewable outputs and suggests running the local script or using local template/spec files when execution isn't available. The runtime instructions do not ask the agent to read unrelated system state or transmit results externally. They do allow scanning of provided files/directories (intended for audit), which is coherent with the skill purpose.
Install Mechanism
No install spec; this is an instruction-only skill with a bundled Python script. Nothing is downloaded from external URLs and there are no extract/install steps. This is a low-risk distribution model consistent with the stated intent.
Credentials
No environment variables, credentials, or config paths are required. The included script operates on files/paths provided by the user and does not contact external endpoints. Note: the script can read many local file types (e.g., .md, .py, .js, .sh, .csv) to produce reports, which is appropriate for auditing but means it can surface secrets present in those files.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request elevated or persistent platform privileges and does not modify other skills' configs. The script can write an output file only when the user supplies an output path (and respects --dry-run), which matches the stated 'do not auto-change production' guidance.
Assessment
This skill appears coherent and low-risk for its stated purpose, but take normal precautions before running it: (1) Inspect scripts yourself (scripts/run.py is included) and run in a safe/test environment first. (2) Use --dry-run or redirect output to a temporary file before applying any suggested changes. (3) Avoid pointing the tool at directories containing unredacted secrets or sensitive PII—the script will read and summarize many file types and may surface sensitive values in reports. (4) Confirm you trust the skill source before giving it large or production directories to scan. If you need networked or automated writes to external systems, require additional review and explicit safeguards—this skill is intended to produce reviewable suggestions, not to change production systems.Like a lobster shell, security has layers — review code before you run it.
latestvk97awk8tyakp5674r0mww540a983f61x
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🧩 Clawdis
OSmacOS · Linux · Windows
Binspython3