config/ai/claude/claudecode/skills/review/SKILL.md
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/PRD 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".
npx skillsauth add pixelastic/oroshi reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Two-axis review of the diff between HEAD and a fixed point the user supplies:
Both axes run as parallel sub-agents so they don't pollute each other's context, then this skill aggregates their findings.
Choose the diff command based on what the user supplied:
| User supplied | Diff command | Commit log |
|---|---|---|
| Nothing | git status --short; git diff HEAD (all uncommitted changes — staged + unstaged) | none (no commits to list) |
| Single commit / branch / tag | git diff <fixed-point>...HEAD (three-dot, merge-base comparison) | git log <fixed-point>..HEAD --oneline |
| Commit range a..b or a...b | git diff <a>..<b> (pass through as-is) | git log <a>..<b> --oneline |
Look for the originating spec, in this order:
#123, Closes #45, GitLab !67, etc.).docs/, specs/, or .scratch/ matching the branch name or feature.Anything in the repo that documents how code should be written. Common locations:
CLAUDE.mdCONTRIBUTING.mdCONTEXT.md, CONTEXT-MAP.md, per-context CONTEXT.md filesSTYLE.md, STANDARDS.md, STYLEGUIDE.md, or similar at the repo root or under docs/docs/adr/ (architectural decisions are standards){language}-writer skills.editorconfig, eslint.config.*, prettier.config.* (machine-enforced standards — note them but don't re-check what tooling already checks)Collect the list of files. The Standards sub-agent will read them.
Send a single message with two Agent tool calls. Use the general-purpose subagent for both.
Standards sub-agent prompt — include:
Spec sub-agent prompt — include:
If the spec is missing, skip the Spec sub-agent and note this in the final report.
Present the two reports under ## Standards and ## Spec headings, verbatim or lightly cleaned. Do not merge or rerank findings — the two axes are deliberately separate so the user can see them independently.
End with a one-line summary: total findings per axis, and the worst single issue (if any) flagged.
A change can pass one axis and fail the other:
Reporting them separately stops one axis from masking the other.
tools
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
tools
Break a plan, spec, or PRD into independently-grabbable issues using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
documentation
Use when user says "sidequest" or "handoff" — compact conversation context into a document for a fresh agent to pick up.
development
Use when the user wants to nail down domain terms, resolve terminology ambiguities, or build a shared language for a module or repo. Drills vocabulary one question at a time and writes to the project GLOSSARY.md.