Keyword Velocity Tracker
v1.0.0Calculate literature growth velocity and acceleration to assess research.
⭐ 0· 57·0 current·0 all-time
byAIpoch@aipoch-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (calculate literature growth velocity/acceleration) matches the included Python implementation (scripts/main.py) and the SKILL.md usage. Requested libraries (numpy, scipy) are appropriate for numerical analysis. Minor inconsistency: SKILL.md mentions scipy but requirements.txt omits it and includes stdlib modules (dataclasses, enum) unnecessarily.
Instruction Scope
SKILL.md instructs the agent to validate inputs, run the packaged script, and produce bounded outputs. The instructions only reference running the local script and editing an in-file CONFIG block; they do not ask the agent to read unrelated system files, access external endpoints, or exfiltrate secrets.
Install Mechanism
No install spec is present (instruction-only with an included script). This minimizes install-time risk — execution is local Python. The included files are visible so there is no hidden download-from-URL behavior.
Credentials
No environment variables, credentials, or config paths are required. The skill does not request unrelated secrets or cloud credentials.
Persistence & Privilege
Skill does not request always:true and does not declare modifications to other skills or system-wide configuration. Autonomous invocation is allowed by platform default but is not combined with elevated privileges or credential access.
Assessment
This package appears coherent and local-only: review scripts/main.py yourself (it is included) and run python -m py_compile scripts/main.py to verify. Note the small mismatch between SKILL.md (mentions scipy) and requirements.txt; install numpy (and scipy if you plan to use smoothing/advanced math) in a sandbox environment. Before running on sensitive systems, run the script on sample data to confirm output and check for any unexpected file writes or network calls (there are no obvious network calls in the visible code). If you need stronger assurance, run the script in an isolated container and inspect/grep the source for os, subprocess, socket, requests, or similar imports first.Like a lobster shell, security has layers — review code before you run it.
latestvk971wn4xmxfshcnm18r7nyesb983mse8
License
MIT-0
Free to use, modify, and redistribute. No attribution required.