Skip to content

MVPavan/via / .claude/skills/code-review

code-review

Verified

Use for substantive code review or to verify and act on review findings. Routine final diff inspection is not a separate review workflow.

FileKindSize
SKILL.mdskill md3.1 KB
agents/openai.yamlconfig42 B
references/feedback.mdmarkdown1.1 KB
references/review-contract.mdmarkdown1.6 KB

references/review-contract.md

View on GitHub
# Dispatched review contract

Inputs: mode, brief/requirements path, implementation report, scoped diff package,
binding constraints, output path. For re-review also include the finding list and
fix-delta package. Follow the code-review entrypoint's evidence and scope rules.

Initial spec and quality verdicts remain distinct when those roles are dispatched
separately. A combined reviewer covers both explicitly. Re-review covers every
listed finding regardless of its original role.

## Spec output

```text
Verdict: COMPLIANT | ISSUES_FOUND
Unverified requirements: <items and needed evidence, or none>
Issues: <severity, file:line, missing/extra/misunderstood requirement and impact>
Checks and limitations: <actual evidence>
```

A missing brief limits compliance claims; an unrelated failed check is not an
automatic Critical code defect. Report each limitation at its actual consequence.

## Quality output

```text
Verdict: APPROVE | WARNING | BLOCK — <reason>
Issues: <Critical / Important / Minor; file:line, trigger and impact>
Checks and limitations: <actual evidence>
```

## Re-review output

```text
Finding verdicts: <ID — ADDRESSED | NOT ADDRESSED; file:line evidence>
New breakage in fix diff: <severity and evidence, or none>
Out-of-scope observations: <nonblocking follow-ups, or none>
Verdict: all addressed, no new Critical/Important | findings remain open
Checks and limitations: <actual evidence>
```

A reviewer may report that a finding was incorrect; the coordinator records that
ruling and its evidence separately from an implemented fix. Uncertain findings
remain explicitly unresolved. Do not demand edits solely to make a verdict green.
planning-and-task-breakdownaddyosmani/agent-skillsBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
screenpipethedotmack/claude-memSearch screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
contact-widgetnexu-io/open-designSelf-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies.Stars: 108kUpdated Claude CodeCodexVerifiedInstall
meeting-notesnexu-io/open-designMeeting notes page — title bar with attendees, agenda checklist, decisions block, action items table with owners + dates, and a "next meeting" footer. Use when the brief mentions "meeting notes", "minutes", "1:1 notes", "all-hands recap", or "会议纪要".Stars: 108kUpdated Claude CodeCodexVerifiedInstall