Build custom peer-review skills for specific research areas, problem families, and method combinations using OpenReview evidence. Use when Codex needs a comp...
Security Analysis
medium confidenceThis skill coherently builds research-review skills from public OpenReview data, with disclosed Python commands and scoped local file generation, and no artifact-backed malicious behavior.
The stated purpose matches the artifacts: it fetches public OpenReview evidence, synthesizes review patterns, and generates a child reviewer skill. Users should notice that it creates reusable skill artifacts, not just a one-off review.
The workflow asks the agent to plan queries, run retrieval, synthesize evidence, and package a generated skill. The instructions include guardrails such as not fabricating evidence, treating precedent as non-authoritative, and excluding raw/private data.
There is no install spec; execution is via included Python helper scripts. One referenced validation helper, quick_validate.py, is not present in the supplied manifest, so users should verify any external validator before running it.
No credentials or privileged access are requested. Network access to OpenReview and local file writes are expected for the stated purpose and are generally scoped by user-provided output paths.
The skill intentionally creates persistent child skill folders, but the included generator validates child skill names, keeps output under the chosen output directory, and refuses to overwrite an existing skill directory.
Guidance
This appears safe to install for its stated purpose. Before using it, be aware that it can run Python scripts, contact OpenReview, write local evidence and child-skill files, and create a persistent review-response bank. Review generated outputs before packaging or publishing them, and verify any validation command that is not included with the skill.
Latest Release
v1.0.1
- No user-visible changes; version updated without file modifications. - Functionality, workflow, and documentation remain unchanged.
Popular Skills
Published by @c-narcissus on ClawHub