skills/preview/SKILL.md
AI screening review for PRs - preliminary check before human review. Do NOT use for deep multi-reviewer code quality audits (use /audit instead).
npx skillsauth add thkt/claude-config previewInstall 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.
$ARGUMENTS (URL, number, or empty → detect from current branch)| Step | Action |
| ---- | ------------------------------------------------------------------------------------------------------------ |
| 1 | Identify PR: gh pr view $ARGUMENTS --json number,title,body,labels,files,url (fallback: omit $ARGUMENTS) |
| 2 | Abort if no PR found or working tree is dirty (git status --porcelain) |
| 3 | Checkout PR: gh pr checkout $PR |
| 4 | Gather PR context in parallel (see below) |
| 5 | Read each changed file in full, including code outside the diff hunks |
| 6 | Review per process: overview → per-file → dependency impact → findings |
| 7 | Output structured screening report |
# Metadata
gh pr view --json title,body,labels,files,url $PR
# Diff
gh pr diff $PR
# Existing comments
gh pr view --comments $PR
# Inline comments
gh api repos/{owner}/{repo}/pulls/{number}/comments \
--jq '.[] | {file: .path, user: .user.login, comment: .body}'
Never include author in gh output fields.
| Label | Meaning | Severity |
| -------- | ------------------------------- | -------- |
| [must] | Requires fix before merge | High |
| [want] | Should fix, not blocking | Medium |
| [imo] | Personal opinion, take or leave | Low |
| [ask] | Question needing clarification | - |
| [nits] | Minor style/formatting issue | Low |
| [info] | Context sharing, no action | - |
| Rule | Detail |
| --------------- | ---------------------------------------------------------------------------------- |
| Format | [label] <observed behavior or risk>. <suggestion>. (file:line) |
| Concise | 3 lines for [imo]/[nits]/[info]; up to 5 for [must]/[want] with evidence |
| Respectful | Acknowledge effort, avoid commands |
| Suggestive | "Consider..." not "This is wrong" |
| Author-targeted | Comments may be posted verbatim - calibrate detail for the PR author |
## PR Screening Report
### Overview
{Background and purpose in 2-3 sentences}
### Changes Summary
| File | Change Summary |
| ---- | -------------- |
### Dependency Impact
{Affected files, regression risk}
---
### Requires Action
{`[must]` and `[want]` findings with file:line}
### Awareness
{`[imo]`, `[ask]`, `[nits]`, `[info]` items with file:line}
---
### Proposed Review Comments
{Grouped by file, with labels}
| Rule | Detail | | ------------------ | ---------------------------------------------------------------------- | | No auto-post | Never post comments to PR automatically | | Abort on dirty | If uncommitted changes exist, warn and abort | | Speed over depth | This is screening, not full audit | | Verify before flag | Before [ask]/[want]+, trace the issue to a reachable runtime call site |
| Topic | File | | ---------------- | -------------------------------------------------- | | Review Checklist | ${CLAUDE_SKILL_DIR}/references/review-checklist.md |
tools
Internal helper for /think Step 11. Renders SOW.md + Spec.md as an integrated Astro view and returns a dev server URL.
development
Extract repository spec while detecting bugs, spec gaps, and consistency drift via dual-purpose documentation. OUTCOME.md-axis question-driven exploration with ephemeral output. Do NOT use for code review (use /audit or /polish), feature implementation (use /code), planning only (use /think), or single-bug fix (use /fix).
development
Discover undocumented design decisions and challenge each candidate via critic-design before promotion. Rank by impact and reversibility, produce ADR promotion candidates. Treat each candidate as a position arguing for ADR status, not a fact to be filed. Pairs with audit-adr-drift, which scans existing ADRs for drift against code.
development
Scan ADR Decision sections against current code and report drift with modification direction and priority. Do NOT use for repos without ADRs (use audit-adr-gaps instead).