Skip to content

wtcooper/ai-review

v0.1.0MIT

Guided security review of an AI capability: scope it, gather vendor evidence, model the threats, set your own acceptance criteria, and compile the report. Measures and records; never decides.

ai-review

Guided security review of an AI capability. These skills scope the review, gather evidence, model the threats, help your organisation write its own acceptance criteria, and compile the report. They measure and record; they never decide.

SkillWhat it does
review-scopeInterview the requester and write review.json: what is being enabled, where, with what data and permissions.
review-evidenceHarvest vendor cards, published scores and documented limits, each with its source and provenance. Includes the open-weights scan harvest.
review-threat-modelThreats for this subject type, and a test plan that sorts each threat into: covered by a catalogued benchmark, needs a custom probe, design review only, or uncovered.
review-criteriaWalk the organisation through writing its own acceptance criteria. Never proposes a value; the shipped template is empty.
review-reportCompile evidence, results (validity flags first) and uncovered threats. Shows your criteria beside results only if you supplied them; decision fields are left blank.

Install

The plugin follows Agent Plugins 1.0.0: a root plugin.json and one folder per skill under skills/. Any client that loads Agent Plugins can load this directory.

Claude Code:

/plugin marketplace add wtcooper/ai-security-evals
/plugin install ai-review@ai-security-evals

Each skill is also self-contained: copying its folder into any agent's skills directory works.