Agent skill

Check Review Backlog

by ayutaz in ayutaz/piper-plus

PR 作成直後の review チェック / 全 open PR の未解決 review thread (isResolved=false) を gh api graphql で集計し、 N 日以上未対応のものを backlog として表示する。

MITAuto-check passedBackend & APIs

Install Check Review Backlog

skills CLI
$ npx skills add ayutaz/piper-plus --skill check-review-backlog -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ayutaz/piper-plus check-review-backlog --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ayutaz/piper-plus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/check-review-backlog .claude/skills/check-review-backlog && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
check-review-backlog
GitHub stars
234
Token cost
~1.2k tokens
SKILL.md length
287 words
Files
1
Skills in repo
20
Repo updated
First seen
Licence
MIT

At a glance

PR 作成直後の review チェック / 全 open PR の未解決 review thread (isResolved=false) を gh api graphql で集計し、 N 日以上未対応のものを backlog として表示する。

  • Tasks that involve Pull requests
  • SKILL.md covers 引数, 実行前の確認, 手順 and 継続監視モード, plus 3 more sections
  • Calls gh; reaches github.com
  • Tasks that involve GraphQL

What it does

Check Review Backlog is an agent skill from ayutaz/piper-plus. PR 作成直後の review チェック / 全 open PR の未解決 review thread (isResolved=false) を gh api graphql で集計し、 N 日以上未対応のものを backlog として表示する。 --pr <N で単一 PR の review 即時確認 (PR 作成 chain で発動)、 引数なしで全 PR backlog 監視。 /loop /check-review-backlog で週次監視に利用可能。 read-only (POST / mutation なし)。

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering Pull requests and GraphQL. It works with GraphQL. The repository describes itself as: Multilingual neural TTS (6 languages: JA/EN/ZH/ES/FR/PT, code supports SV) — C++, C, Rust, Go, Python, npm (WASM). VITS + Prosody, streaming, CUDA/CoreML/DirectML. pip install…. The licence is MIT.

When your agent uses it

  • Tasks that involve Pull requests
  • Tasks that involve GraphQL

Example prompts

  • “/check-review-backlog”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Bash(gh api *), Bash(gh pr list *), Bash(date *), Read, Grep

What it can do on your machine

Read from SKILL.md and the folder at commit 421d066. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(gh api *)
    • Bash(gh pr list *)
    • Bash(date *)
    • Read
    • Grep

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Check Review Backlog loads about 1.2k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 287 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ayutaz/piper-plus at commit 421d066, republished under its MIT licence (© ayutaz). 287 words, ~1,177 tokens.

Download SKILL.mdSave it as .claude/skills/check-review-backlog/SKILL.md (or your agent's skills folder).
name
check-review-backlog
description
PR 作成直後の review チェック / 全 open PR の未解決 review thread (isResolved=false) を gh api graphql で集計し、 N 日以上未対応のものを backlog として表示する。 `--pr <N>` で単一 PR の review 即時確認 (PR 作成 chain で発動)、 引数なしで全 PR backlog 監視。 `/loop /check-review-backlog` で週次監視に利用可能。 read-only (POST / mutation なし)。
allowed-tools
Bash(gh api *), Bash(gh pr list *), Bash(date *), Read, Grep
argument-hint
[--pr <N>] [--days N] [--author <login>]
disable-model-invocation
false

Unresolved Review Backlog Monitor

全 open PR を走査して、未解決 (isResolved=false) の review thread のうち N 日以上経過しているものを backlog として集計する。レビュー対応漏れの早期警告が目的。

引数

  • --pr <N> (任意): 単一 PR の review 即時確認モード。 経過日数フィルタを無視し、 全未解決 thread を表示。 /create-pr skill から PR 作成直後に自動 chain される (例: /check-review-backlog --pr 496)
  • --days N (任意): 経過日数の閾値 (デフォルト: 7 日)。 --pr 指定時は無視
  • --author <login> (任意): 特定 reviewer (例: copilot-pull-request-reviewer) のコメントに絞る

実行前の確認

  • 現在時刻 (UTC): !date -u +"%Y-%m-%dT%H:%M:%SZ"
  • 引数: $ARGUMENTS

手順

フェーズ 0: モード判定

$ARGUMENTS を解析:

  • --pr <N> を含む: 単一 PR モード (PR 作成直後の auto chain 用)。 フェーズ 1 を skip、 フェーズ 2 を該当 PR 1 件で実行、 フェーズ 3 (日数フィルタ) を skip、 フェーズ 4 で「PR #N の未解決 thread 全件」レポート
  • それ以外: backlog 監視モード (週次運用)。 全 open PR を走査
フェーズ 1: Open PR 一覧取得 (backlog モードのみ)
bash
gh pr list --state open --json number,title,createdAt,updatedAt --limit 50

各 open PR について、フェーズ 2 を実行する。

フェーズ 2: 未解決 thread の集計

各 PR について、GraphQL で未解決 review thread + 最初のコメントを取得:

bash
gh api graphql -f query='
query($pr: Int!) {
  repository(owner: "ayutaz", name: "piper-plus") {
    pullRequest(number: $pr) {
      title
      reviewThreads(first: 50) {
        nodes {
          id
          isResolved
          comments(first: 1) {
            nodes {
              databaseId
              path
              line
              body
              createdAt
              author { login }
              url
            }
          }
        }
      }
    }
  }
}' -F pr=<PR_NUMBER> --jq '.data.repository.pullRequest | {
  title,
  unresolved: [.reviewThreads.nodes[] | select(.isResolved == false) | .comments.nodes[0]]
}'
フェーズ 3: 経過日数フィルタリング

各 thread の createdAt (ISO8601) と現在時刻を比較し、days_old >= --days のものを抽出:

python
# 概念 pseudocode (実際は bash + jq + date で実装)
from datetime import datetime, timezone
now = datetime.now(timezone.utc)
threshold_days = int(args.days or 7)
for thread in unresolved_threads:
    created = datetime.fromisoformat(thread["createdAt"].replace("Z", "+00:00"))
    days_old = (now - created).days
    if days_old >= threshold_days:
        backlog.append({**thread, "days_old": days_old})

--author 指定時は comment.author.login == args.author で更に絞る。

フェーズ 4: 集計レポート

backlog を以下の形式で表示 (経過日数の降順):

text
## Review Backlog (>= <N> days unresolved)

| PR | Title | Reviewer | path:line | Days | URL |
|----|-------|----------|-----------|------|-----|
| #489 | feat: ... | Copilot | src/foo.py:42 | 21 | https://github.com/.../discussion_r... |
| #501 | fix: ...  | human   | docs/bar.md:10 | 9  | https://github.com/.../discussion_r... |
| ... | ...     | ...     | ...           | ... | ...                                  |

Total: <N> threads across <M> PRs

### 統計
- Copilot bot: <n> threads (<x%>)
- Human reviewers: <n> threads (<x%>)
- 最古: PR #<N>, <days> 日経過

backlog が空の場合: OK: 全 open PR で <N> 日以上未対応の review thread はありません。

フェーズ 5: 推奨アクション
状況推奨
backlog ≥ 5 件該当 PR の owner に /reply-review <PR> 実行を促す。Copilot ノイズが多ければ --skip-copilot-style 併用
30 日以上の thread あり該当 PR の状態を確認 (draft / stale / abandoned)。close / resolve 判断を促す
Copilot bot 比率 ≥ 60%/reply-review <PR> --skip-copilot-style を案内
単一 PR で 10+ unresolvedその PR の review 状況が悪化中。優先対応

継続監視モード

text
/loop /check-review-backlog          # 自動 pace (週次目安)
/loop 24h /check-review-backlog      # 24 時間ごと
/loop /check-review-backlog --days 3  # 3 日閾値で監視

使用例

text
# 7 日以上未対応の thread を一覧 (デフォルト)
/check-review-backlog

# 3 日以上に閾値を厳しく
/check-review-backlog --days 3

# Copilot コメントのみ
/check-review-backlog --author copilot-pull-request-reviewer

# 週次監視
/loop /check-review-backlog

注意事項

  • read-only: 本 skill は POST/mutation を一切行わない。集計と表示のみ
  • rate limit: 50 open PR × GraphQL query で ~50 req、GitHub API 制限 (5000/h) 内
  • タイムゾーン: createdAt は UTC。日数計算は UTC 基準
  • fork PR: 外部 contributor の fork PR も含む
  • draft PR: 集計対象 (draft でも review コメントが付くため)
  • 集計結果は scrollable な table で、ユーザが目視で優先度判定する想定

期待効果

  • レビュー対応漏れの可視化 (memory feedback_copilot_stale_review の延長線上)
  • /reply-review 実行のトリガとして利用 (どの PR を優先対応すべきか判断材料)
  • 長期 unresolved の発見 → PR の active/abandoned 判定を促進

© ayutaz, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/check-review-backlog of ayutaz/piper-plus.

Open the folder on GitHubat commit 421d066

Compare with similar skills

Check Review Backlog next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Check Review Backlog compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Check Review Backlog this skillayutaz/piper-plus234—~1.2kAutomated safety check: PassMIT
Flow Next Resolve PRgmickel/flow-next709—~1.1kAutomated safety check: PassMIT
Review PR Commentslatitude-dev/latitude-llm4.7k—~2.6kAutomated safety check: PassMIT
GitHub Opsdaymade/claude-code-skills1.4k—~3.8kAutomated safety check: PassMIT
Flow Next Resolve PRgmickel/flow-next709—~1.1kAutomated safety check: PassMIT
Gh QueueLanternOps/breeze132—~5kAutomated safety check: PassAGPL-3.0

Similar skills

  • Flow Next Resolve PR

    gmickel/flow-next

    Resolve PR review feedback. An agent skill from gmickel/flow-next.

    709 GitHub stars~1.1k tokensUpdated today
    Backend & APIsAuto-check passed
  • Review PR Comments

    latitude-dev/latitude-llm

    Triages a PR with GitHub CLI: loads issue-level and inline review feedback (gh pr view, gh api REST, gh api graphql as appropriate), walks items in order, replies in the correct thread, optional…

    4.7k GitHub stars~2.6k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • GitHub Ops

    daymade/claude-code-skills

    Operates GitHub via gh CLI and REST/GraphQL — PRs, issues, Actions, repos, collaborators, org permissions, 2FA — with explicit target, authorization, and independent readback.

    1.4k GitHub stars~3.8k tokensUpdated today
    Backend & APIsAuto-check passed
  • Flow Next Resolve PR

    gmickel/flow-next

    Resolve PR review feedback — fetch unresolved threads, triage, dispatch per-thread resolver agents, validate, commit, reply + resolve via GraphQL.

    709 GitHub stars~1.1k tokensUpdated today
    Backend & APIsAuto-check passed
  • Gh Queue

    LanternOps/breeze

    A skill your agent uses when reviewing, triaging, or managing the incoming GitHub backlog on the Breeze repo — PRs, Discussions, AND Issues.

    132 GitHub stars~5k tokensUpdated today
    DevelopmentAuto-check passed
  • Reply To PR Threads

    tobihagemann/turbo

    Draft, confirm, and post replies to GitHub PR review threads.

    408 GitHub stars~941 tokensUpdated yesterday
    Backend & APIsAuto-check passed

More from ayutaz/piper-plus

All 20 skills in this repo
  • Skill Health

    ayutaz/piper-plus

    .claude/skills//SKILL.md の frontmatter / referenced script 実在 / trigger 衝突 / .claude/hooks/.sh の executable+shebang を検査する meta-skill。

    234 GitHub stars~626 tokensUpdated yesterday
    Auto-check passed
  • Bump Deps

    ayutaz/piper-plus

    ORT / openjtalk / ruff のような cross-runtime に canonical sync が必要な依存関係を 1 コマンドで bump する read-mostly skill。

    234 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • Check Cross Runtime

    ayutaz/piper-plus

    Python canonical (src/pythonrun/piperplus/, src/python/pipertrain/, src/python/g2p/piperplusg2p/) を変更した PR で、 ONNX I/O 以外の追随漏れ (phonemizer / config schema / CLI flag / data 形式 / API 変更) を 7 ランタイム +…

    234 GitHub stars~3.5k tokensUpdated yesterday
    Auto-check passed
  • Check Loanword

    ayutaz/piper-plus

    ZH-EN code-switching loanword の同期と forward-compat を 1 コマンドで検査。zhenloanword.json を編集したり 5 ランタイムのいずれかに新規エントリを追加する前後に呼ぶ。Python source を canonical とし、Rust×2 / Go / C / WASM / C++ の 6 mirror + Python…

    234 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Check New Runtime Asset

    ayutaz/piper-plus

    新規データアセット (JSON/TOML) を追加した PR で「7 箇所の package metadata 更新が全て揃っているか」を 1 コマンドで確認。MANIFEST.in / pyproject package-data / Cargo features / npm files / C Content / Android assets / SPM resources の更新漏れを…

    234 GitHub stars~964 tokensUpdated yesterday
    Auto-check passed
  • Check PR Ready

    ayutaz/piper-plus

    PR 作成前の最終チェックリスト (lint/test/docs/CHANGELOG/未コミット確認)。/precheck の拡張版で、ドキュメント整合性も検証します。

    234 GitHub stars~687 tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Check Review Backlog

What does Check Review Backlog do?

PR 作成直後の review チェック / 全 open PR の未解決 review thread (isResolved=false) を gh api graphql で集計し、 N 日以上未対応のものを backlog として表示する。. Check Review Backlog is an agent skill from ayutaz/piper-plus.

When should I use Check Review Backlog?

Check Review Backlog fits situations like: tasks that involve Pull requests; tasks that involve GraphQL.

How do I install Check Review Backlog in Claude Code?

Run `npx skills add ayutaz/piper-plus --skill check-review-backlog -a claude-code`. Or copy the skill folder (.claude/skills/check-review-backlog in ayutaz/piper-plus) into .claude/skills/check-review-backlog in your project. Claude Code loads it when a task matches its description.

How do I install Check Review Backlog in Codex?

Run `npx skills add ayutaz/piper-plus --skill check-review-backlog -a codex`. Or copy the skill folder (.claude/skills/check-review-backlog in ayutaz/piper-plus) into .agents/skills/check-review-backlog in your project. Codex loads it when a task matches its description.

Can I use Check Review Backlog in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ayutaz/piper-plus --skill check-review-backlog -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/check-review-backlog, .gemini/skills/check-review-backlog, .github/skills/check-review-backlog and .opencode/skills/check-review-backlog in your project.

What does Check Review Backlog need to run?

Going by SKILL.md and its folder, Check Review Backlog needs the command-line tools its instructions call (gh). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash(gh api *), Bash(gh pr list *), Bash(date *), Read, Grep.

Does Check Review Backlog access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Check Review Backlog safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Check Review Backlog use?

Check Review Backlog is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Check Review Backlog use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Check Review Backlog?

Skills that share tags, products or a category with Check Review Backlog: Flow Next Resolve PR (gmickel/flow-next, 709 stars), Review PR Comments (latitude-dev/latitude-llm, 4.7k stars), GitHub Ops (daymade/claude-code-skills, 1.4k stars) and Flow Next Resolve PR (gmickel/flow-next, 709 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Check Review Backlog?

ayutaz (a GitHub user) maintains it in ayutaz/piper-plus, which has 234 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 10, 2026.

Source: ayutaz/piper-plus on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.