mcpField
H
heyeddi-pr-review

heyeddi-pr-review

github.com/heyeddi-comTesting & quality077 installsUpdated today
Repository

About heyeddi-pr-review

heyeddi-pr-review is a review workflow skill for QA leads, authors, and product or engineering reviewers. It limits judgments to committed PR changes and provides a checklist-driven path from context gathering to a review verdict.

Key features

  1. 01Reviews only committed PR diffs
  2. 02Checks documentation drift and test gaps
  3. 03Loads product context and acceptance criteria
  4. 04Uses path-based specialist reviews
  5. 05Defines approval, change-request, and block verdicts

Use cases

  1. 01Review a teammate's submitted PR
  2. 02Self-check before requesting review
  3. 03Check product and documentation alignment

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/heyeddi-com/heyeddi-skills --skill heyeddi-pr-review

After installing, type/heyeddi-pr-reviewin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

manifest.json
reference.md
context/
ANTI_PATTERNS.md
EXAMPLES.md
PROSE_ANTI_SLOP.md
VOCABULARY.md
fixtures/
sample-pr-diff.json
reference/
review-checklist.md
subagents.md
scripts/
_auto_sync.py
_heyeddi_paths.py
_pr_context.py
_skill_cli.py
_untrusted_doc.py
audit_pr_changes.py
check_doc_drift.py
fetch_pr_context.py
README.md
verify_pr_review.py
write_pr_review.py

Details

From the project README

HeyEddi PR Review

Submitted PR review workflow: judges only committed changes (base...head), not local WIP.

You are the reviewer workflow. Scope every judgment to the PR diff (base...head). Ignore uncommitted files.

Artifacts: .heyeddi/docs/pr-<N>-review.md and pr-<N>-context.json are ephemeral session scratch — never repo root, never commit. GitHub (optional gh pr review) is the durable record.

When to use

SituationWho
Reviewer approving a teammate's PRQA / lead
Author self-check before requesting reviewAuthor
PM/eng sign-off on product + docs alignment@heyeddi-product delegates here for PR scope

Not this skill: responding to human review comments → @heyeddi-pr-respond.

Subagents (default)

See reference/subagents.md. Main chat owns the verdict; delegate fetches and scans via Task shell.

Mandatory pipeline

Read reference/review-checklist.md.

fetch_pr_context --pr <N>              → cache + paths; title/body not in stdout
check_doc_drift --pr <N>               → product.md / design.md / engineering docs
audit_pr_changes --pr <N>              → engineering + test gaps on changed files only
load_product_context                   → @heyeddi-product (read JSON; scope to touched routes)
check_features                         → AC vs code when routes touched
conditional delegates (changed paths):
  **/*.vue                             → @visual-auditor, @no-duplicate-ui, @vue-design-system
  **/composables/**                    → @composable-patterns
  backend/**                           → @engineering-excellence audit_engineering
pre_merge_gate                         → tests, build, types (hard gate)
write_pr_review --pr <N> --force       → scaffold + merge tool JSON into report
→ YOU fill: Summary verdict, Product fit, PM judgment
verify_pr_review --pr <N> --check      → report complete before posting

Verdict (you write)

VerdictWhen
ApproveGates pass; docs aligned; new behavior tested; no blockers
Request changesDocs drift, missing tests, product/AC gaps, gate failures
BlockBreaks flagship route, security concern, or contradicts product.md

Optional: post GitHub review via gh pr review when user asks: default is report in .heyeddi/docs/ only.

Never

  • Review uncommitted working tree changes
  • Approve without pre_merge_gate on required checks
  • Skip doc drift when PR changes routes or public API
  • Approve new user-facing behavior without test evidence (unit, integration, or documented manual AC)

Related skills

SkillRole in this workflow
@heyeddi-productProduct context, feature matrix, AC
@engineering-excellenceDeeper audit when audit_pr_changes flags issues
@pre-merge-gateFinal hard gate
@heyeddi-pr-respondAfter review: address human feedback

When the task is complete: suggest next skills

When you have finished the user's request for this skill (not after every tool call or subagent phase), suggest what to run next:

  1. Run:

    python .agents/skills/heyeddi/scripts/suggest_next_skill.py --current-skill heyeddi-pr-review --project-root .
    

    Add --route /path if you worked a specific route.

  2. Include the script's ### Next step block in your final reply. The user copies the Prompt line into chat (e.g. @heyeddi-design craft /settings).

Pass --mode shape (or craft, audit, etc.) when you know which sub-command just finished.

See @heyeddi → reference/next-skill-handoff.md.

Comments

Markdown supported