AGENT SKILL

review-queue

review-queue, the open pull requests of a repository as a table in the order to review them. Use whenever the user asks which pull requests are open, which one to review next, or in which order to review them.

License 许可
MIT
所属仓库
renefatuaki/skills
最近更新
2026-11-11
Stars
★ 0
Forks
0

01 前言 Front Matter

name
review-queue
description
review-queue, the open pull requests of a repository as a table in the order to review them. Use whenever the user asks which pull requests are open, which one to review next, or in which order to review them.
allowed-tools
Bash(node ${CLAUDE_SKILL_DIR}/scripts/review-queue.mts)

02 资源文件 2

03 SKILL.md 正文

Shows the open pull requests of a repository as one table in the order to review them, each linked, with every stack in one piece.

Steps

  1. Run the script. Run scripts/review-queue.mts with Node 24 or newer, which runs TypeScript directly. It reads the repository of the current directory.

    node ${CLAUDE_SKILL_DIR}/scripts/review-queue.mts
    
  2. Show the table. Your reply is the script's output verbatim and nothing else, no sentence before or after it. When the script fails, reply with its error.

04 同仓库更多 Skills

renefatuaki
renefatuaki/skills

why

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

★ 0
renefatuaki
renefatuaki/skills

tdd

Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.

★ 0
renefatuaki
renefatuaki/skills

swarm

Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.

★ 0
renefatuaki
renefatuaki/skills

show-me-your-work

Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.

★ 0
renefatuaki
renefatuaki/skills

interrogate

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.

★ 0
renefatuaki
renefatuaki/skills

how

Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.

★ 0