Przejdź do treści
Biblioteka skilli
Programowanie · Przegląd i audyt

github-pr-review

/github-pr-review

Ocenia pull request raz i zapisuje raport w JSON, z cytatami reguł lub konkretnym błędem w diffie, bez publikowania.

Licencja
Apache-2.0
Ostatnia zmiana repozytorium
13.11.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
27
Skrypty
11
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 13.11.2026, bez odwołań do wycofanych modeli i API.

Licencja

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

Co sprawdzić przed instalacją
  • 11 skryptów w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.

Skrypty: scripts/detect_pr_review.sh, scripts/lib/all.sh, scripts/lib/aws.sh, scripts/lib/common.sh, scripts/lib/csv.sh, scripts/lib/json.sh, scripts/lib/repo_paths.sh, scripts/lib/terraform.sh, scripts/lib/validation.sh, scripts/lib/yaml_map_order.py, scripts/render_review.sh

Co robi i kiedy

Ocenia pull request raz i zapisuje raport w JSON, z cytatami reguł lub konkretnym błędem w diffie, bez publikowania.

Oryginalny opis (EN)

Review a pull request once and write an evidence-backed review report (JSON) for a later step to post. Use in conversation when the user gives a PR URL or number and asks for a review. Also the L2 loop entry skill on newly opened PRs when detect JSON is supplied. Findings need a verbatim rule or criteria quote from the base commit, or a concrete bug in the diff. Never posts, approves, or edits source files; do not use to fix a PR (github-pr-revise).

Jak działa

  1. Input
  2. Output Specification
  3. Execution Scope
  4. Reference Files Guide
  5. Workflow
Sekcje z nagłówków SKILL.md, w oryginale · 70 linii, 861 słów
Podgląd SKILL.md
---
name: github-pr-review
description: >-
  Review a pull request once and write an evidence-backed review report (JSON)
  for a later step to post. Use in conversation when the user gives a PR URL or
  number and asks for a review. Also the L2 loop entry skill on newly opened
  PRs when detect JSON is supplied. Findings need a verbatim rule or criteria
  quote from the base commit, or a concrete bug in the diff. Never posts,
  approves, or edits source files; do not use to fix a PR (github-pr-revise).
license: Apache-2.0
metadata:
  author: y-miyazaki
  version: "0.1.1"
---

**UTILITY SKILL** — first-pass PR review that produces a report file; the platform renders and posts it.

## Input

- **Automation:** detect JSON from `detect_pr_review.sh` with `result.pr_number`, `result.base_sha`, `result.head_sha`, `result.changed_files`, `result.report_path`, and `result.handoff_key`. Read `agent_edit_allowed` / `agent_edit_target` / `response_language` from `## Constraints`.
- **Interactive:** PR URL or number; there is no detect JSON. Resolve SHAs with read-only `gh pr view <n> --json baseRefOid,headRefOid` (base = `baseRefOid`, head = `headRefOid`). Default: present findings in chat and write no file; when the user asks for a report file, write it to the path the user names.

## Output Specification

Report file schema and rendering: [common-output-format.md](references/common-output-format.md). Automation envelope: [category-automation-envelope.md](references/category-automation-envelope.md). Evidence and exclusion rules: [category-review-rules.md](references/category-review-rules.md).

## Execution Scope

### USE FOR:

- Reviewing the PR diff against agent instruction rules and domain review criteria that exist at the base commit
- Reporting generic correctness bugs that can be shown with a diff line and a concrete failing input or state
- Writing the review report to `result.report_path` when `agent_edit_target` is `report`

### DO NOT USE FOR:

- Fixing, committing, or pushing code (use `github-pr-revise`)
- Posting reviews or comments, approving, or requesting changes (the platform renders the report and posts one COMMENT review)
- Issue triage or lint, format, and secret scanning (hooks and CI already run these)

## Reference Files Guide

- [common-checklist.md](references/common-checklist.md) (always read)
- [common-output-format.md](references/common-output-format.md) (always read)
- [category-review-rules.md](references/category-review-rules.md) (always read)
- [category-automation-envelope.md](references/category-automation-envelope.md) (read on automation path)
- [category-pr-body-links.md](references/category-pr-body-links.md) (read when writing the report)
- `assets/report-template.json` (read when writing the report)
- `assets/review-body-template.md` (read to see how the report is rendered into the review body)
- `assets/inline-comment-template.md` (read to see how in-diff findings are rendered inline)

## Workflow

Resolve **agent_edit_allowed** before writing anything:

| Source                                | `agent_edit_allowed`                                                                                                                         |
| ------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- |
| Interactive — default                 | `false` — survey only; write no file                                                                                                         |
| Interactive — explicit apply language | `true` — user asks to write the report file in the same request                                                                              |
| Automation — `## Constraints`         | `agent_edit_allowed: true` or `agent_edit_allowed: false` from [category-automation-envelope.md](references/category-automation-envelope.md) |

When `agent_edit_allowed` is `true`, resolve `agent_edit_target`: on the **interactive** path use `report`; on the **automation** path read `agent_edit_target` from `## Constraints`. Do not branch on other caller metadata outside `## Constraints`. The report file is the only file this skill may write.

1. Automation: read detect JSON; if `skip: true` or `status: error`, report the reason and stop without writing a report. Interactive: resolve the PR from the user's URL or number and its SHAs with `gh pr view <n> --json baseRefOid,headRefOid`.
2. Confirm the PR's intent: read the PR title and body, linked Issues, and any related spec or design document. Record the result for `premises`.
3. Read the PR diff with `gh pr diff`. Read each changed file at base with `git show <base_sha>:<path>` (never from the checked-out tree, which may be the PR head), and the head version with `gh api` / `gh pr diff`. On the automation path the working tree is the base checkout, so opening files there is equivalent.
4. Collect applicable rules: read applicable instruction files (nested and path-scoped included) from the base commit with `git show <base_sha>:<path>`, and domain review criteria matching each changed file type, also from base. Domain criteria are ID-tagged items in review references that exist in the consumer repository at the base commit (for example installed review skills' `references/category-*.md`); this skill ships none of its own. When none exist for a file type, use only `rule` and `bug` evidence for that file. Never read rules from the PR head.
5. Draft findings limited to the three evidence kinds in [category-review-rules.md](references/category-review-rules.md). Exclude pre-existing problems and every item in the "do not report" list.
6. Drop findings you cannot support with evidence, and findings with low confidence.
7. Decide the response language per [Response language](references/category-review-rules.md#response-language). Automation: write the report as JSON to `result.report_path` following `assets/report-template.json`, and copy `head_sha` and `base_sha` from detect `result.head_sha` / `result.base_sha`; a missing or stale `head_sha` makes the platform refuse to post. Interactive: when `agent_edit_allowed` is `false`, present the findings in chat and write no file; when `agent_edit_allowed` is `true`, write the same JSON to the path the user names, with `head_sha` / `base_sha` from `gh pr view`.
8. Do not post. Do not run `gh pr review`, `gh pr comment`, `gh api` write calls, or any engine `--comment` option. `gh` is read-only here.

### Error Handling

| Condition                                  | Severity    | Action                                                                  |
| ------------------------------------------ | ----------- | ----------------------------------------------------------------------- |
| Detect `status: error`                     | Fatal       | Stop; write no report                                                   |
| Detect `skip: true`                        | Info        | Report skip reason; write no report                                     |
| `agent_edit_allowed: false`                | Info        | Survey only; write no file                                              |
| `agent_edit_target` not `report`           | Recoverable | Survey only; note expected `agent_edit_target: report`                  |
| PR intent cannot be read (body, Issue)     | Recoverable | Record `none` in `premises`; keep only findings that stand on their own |
| Quote cannot be found verbatim at base     | Recoverable | Drop the finding; do not paraphrase                                     |
| User asks to fix or implement the feedback | Info        | Do not edit files; point to `github-pr-revise` and stop                 |
Pliki w paczce (27)
  • SKILL.md 8 KB
  • eval.yaml 1 KB
  • assets/inline-comment-template.md 1 KB
  • assets/report-template.json 1 KB
  • assets/review-body-template.md 3 KB
  • evals/tasks/github-pr-review-basic.yaml 1 KB
  • evals/tasks/github-pr-review-no-evidence-suppressed.yaml 1 KB
  • evals/tasks/github-pr-review-pre-existing-excluded.yaml 1 KB
  • evals/tasks/github-pr-review-rule-citation.yaml 1 KB
  • evals/tasks/github-pr-review-skip-detect.yaml 1 KB
  • evals/tasks/github-pr-review-trigger-negative.yaml 1 KB
  • references/category-automation-envelope.md 3 KB
  • references/category-pr-body-links.md 1 KB
  • references/category-review-rules.md 4 KB
  • references/common-checklist.md 2 KB
  • references/common-output-format.md 4 KB
  • scripts/detect_pr_review.sh 16 KB
  • scripts/render_review.sh 29 KB
  • scripts/lib/all.sh 1 KB
  • scripts/lib/aws.sh 31 KB
  • scripts/lib/common.sh 9 KB
  • scripts/lib/csv.sh 4 KB
  • scripts/lib/json.sh 8 KB
  • scripts/lib/repo_paths.sh 16 KB
  • scripts/lib/terraform.sh 13 KB
  • scripts/lib/validation.sh 14 KB
  • scripts/lib/yaml_map_order.py 8 KB

Wersje

RepozytoriumWynikLicencja
Ta strona · y-miyazaki/terraform-aws-base100Apache-2.0
joe-broadhead/opencode-github100MIT
fvadicamo/dev-agent-skills100MIT
rossoctl/repoman95Apache-2.0

Migawka bazy z 13.11.2026 · wersja paczki 56bab75b2ca8 (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 100review-pr
    Przegląda istniejący pull request na GitHubie i publikuje komentarze inline w jego diffie, gdy zmiany są już na otwartym PR.
  • 100github-pr-revise
    Stosuje uwagi z recenzji do pull requesta GitHub; zmiany wykonuje dopiero wtedy, gdy poprosisz o nie.
  • 90github-pr-revise
    Wdraża uwagi człowieka z przeglądu do pull requesta, gdy użytkownik poda numer lub adres PR i treść poprawek.
  • 90review-pr
    Przegląda pull request z GitHuba wskazany numerem lub adresem URL.
  • 95revdeck
    Przegląda merge request lub pull request lokalnie, domyka uwagi recenzentów albo ocenia cudzą zmianę w gałęzi lub diffie.
  • 100review
    Prowadzi pełny code review pull requesta na GitHubie pod kątem jakości, bezpieczeństwa, błędów i dobrych praktyk.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.