Regression Story Builder
v1.0.0基于历史问题生成回归测试故事集、风险等级和优先级。；use for regression, testing, qa workflows；do not use for 宣称已经执行测试, 跳过高风险路径.
⭐ 0· 81·0 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 (generate regression stories, risk and priority) align with the included resources and the script. Required binary (python3) and local resources (spec.json, template.md) are appropriate. The script implements structured brief generation and light auditing features which fit the skill's stated modes.
Instruction Scope
SKILL.md instructs the agent to produce structured output or optionally run the included script: python3 scripts/run.py --input <...> --output <...>. The script reads files and directories given as input and can run several audit modes (structured_brief, directory_audit, csv_audit, pattern_audit, skill_audit). This is expected, but be aware that if an operator supplies a large or sensitive directory path as --input the script will read many text files (including .md, .py, .json, .yaml, .sh, etc.). The SKILL.md itself emphasizes read-only/dry-run behavior and not executing tests; the code does not attempt remote calls or execute external code.
Install Mechanism
No install spec or external downloads. The skill is instruction-only plus a local Python script that relies on the standard library. No package registry or remote extract/install steps are present.
Credentials
The skill requests no environment variables or credentials. The only runtime requirement is python3. The script scans files for 'secret-like' patterns but sanitizes matched snippets before printing; it does not attempt to read environment variables or secret stores.
Persistence & Privilege
always:false and no install hooks. The skill does not modify other skills or system-wide agent settings. It can write output files only if the user supplies an --output path (and will obey --dry-run). Autonomous invocation is permitted by default (normal), but the skill itself does not request elevated privileges or permanent presence.
Assessment
This skill appears to be what it says: a local, read-only oriented tool to produce regression-story drafts and lightweight audits. Before running it: 1) Prefer running the script against specific, scoped input files (e.g., a bug-summary file) rather than large directories or system folders to avoid accidental exposure of unrelated files. 2) Inspect scripts/run.py (already included) if you handle sensitive data—the script reads files and can summarize them. 3) Use --dry-run or run locally in an isolated environment if unsure. 4) The skill does not access network or request credentials, but do not provide real secrets in inputs; the script will scan for secret-like patterns and will redact matches in its output.Like a lobster shell, security has layers — review code before you run it.
latestvk9798pb9m6k78awj4se4tww17983eej2
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🔁 Clawdis
OSmacOS · Linux · Windows
Binspython3