Sign inGet started

Reviews code changes since a fixed point along two axes—adherence to coding standards and faithfulness to the originating spec—and reports both side by side.

Lift—not yet benchmarked
90
Trustsecurity · quality · license · upkeep
Scan Saferisk 0/100
LicenseMITserved via MCP

What it does

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".

#code-review#git#standards#spec-compliance#pull-requests

Quality judgment

completeness
8.0/10
clarity
8.5/10
trigger quality
7.0/10
examples
5.5/10
structure
9.0/10
overall
8.0/10

A well-engineered skill: precise process steps (pin ref, validate before spawning, parallel sub-agents, verbatim aggregation), a substantive embedded smell baseline with override rules, and a clear rationale for the two-axis design. It loses points only for lacking a worked example of a final report and slightly vague fallback behavior when the tracker isn't set up.

Files (3)

agents/openai.yaml · 0.1 KBLICENSE · 1.0 KBSKILL.md · 6.5 KB