Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (模仿社会洞察类文章风格) align with provided templates, SKILL.md guidance, and two helper scripts that generate openings/structures/phrases and perform local style analysis. No unrelated binaries, cloud credentials, or unrelated platform tokens are required.
Instruction Scope
SKILL.md instructs asking the user for topic/background, building structure, and using local scripts for generation/analysis. The scripts only read local templates/examples/inputs and print results; there are no directives to read arbitrary system files, environment secrets, or to transmit data externally.
Install Mechanism
No install spec is provided (instruction-only + included Python scripts). The README suggests optional pip install of commented extras; requirements.txt defaults to standard library. Running the scripts uses python3; there are no remote downloads, extract steps, or external installers.
Credentials
The skill declares no required env vars, credentials, or config paths. The code does not access environment secrets or network endpoints. Files read are the skill's own templates/examples and user-provided article files—appropriate for its purpose.
Persistence & Privilege
Skill is not always-on (always:false). It does not modify agent/system configuration or other skills, and contains no self-enabling or persistent background components.
Assessment
This skill appears coherent and self-contained: it provides templates and two Python helper scripts to generate openings/structures/phrases and to analyze text locally. Before installing or running: 1) note the source is listed as 'unknown'—if you require provenance, verify the repository/author (homepage points to a general OpenClaw repo); 2) run the scripts in an isolated environment (e.g., a sandbox or virtualenv) and inspect scripts yourself; 3) the skill reads local files you point it to (templates, examples, article files)—do not pass sensitive documents you don't want read; 4) consider ethical and copyright implications: style‑mimicry can reproduce identifiable voices or persuasive framing, so avoid impersonation and check for bias; 5) if you enable optional NLP dependencies later, review those packages before installing. Overall the package is coherent and limited in scope, but verify origin/trust and exercise the usual caution with user-provided inputs and deployment.Like a lobster shell, security has layers — review code before you run it.
latestvk976tnhw3k85fq784tj8zj3m45840d6e
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
📝 Clawdis