agentleFS
HeyEddi-comHeyEddi-com/heyeddi-skills/skills/heyeddi-pr-review/SKILL.md

heyeddi-pr-review

Skill0 starsChanged 3 months agoMITView on GitHub

Reviews submitted PRs using only committed changes: product fit, docs drift, engineering quality, test coverage, and pre-merge gate. Use when approving a PR, doing reviewer QA, or self-checking before requesting review. Not for replying to review comments (use heyeddi-pr-respond).

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

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

    line 79
  2. Very specific:

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

    line 87

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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, @primevue-openprops-architect
  **/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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.