Token导航 LogoToken导航

Agent Skill · 研究检索

do-execute-review-fix(执行审查修复)

do-execute-review-fix 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

do-execute-review-fix 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 67,317。

总安装 247周安装 10GitHub Stars 7下载 78核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:do-execute-review-fix(执行审查修复)
来源仓库:https://github.com/fabio-barboza/development-orchestrator
仓库路径:skills/do-execute-review-fix
安装命令:
npx skills add https://github.com/fabio-barboza/development-orchestrator --skill do-execute-review-fix
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/fabio-barboza/development-orchestrator --skill do-execute-review-fix

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

do-execute-review-fix 负责响应代码审查意见并实施合规性修复,恢复代码质量基线。立即开始执行,不输出计划或等待指令,直接调用编辑工具完成变更。具备编辑失败恢复机制,遇到冲突或语法错误时自动回滚并提供诊断信息。修复范围严格限定于审查意见所列条目,禁止扩大修改引发新问题。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/do-execute-review-fix

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/fabio-barboza/development-orchestrator --skill…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

do-execute-review-fix 怎么安装?

在终端执行 npx skills add https://github.com/fabio-barboza/development-orchestrator --skill do-execut…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

do-execute-review-fix 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

do-execute-review-fix 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

do-execute-review-fix 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

do-execute-review-fix 用的人多吗?

公开数据是累计安装 247 次,近一周安装 10 次,下载 78 次,GitHub 7 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

do-execute-review-fix 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
do-execute-review-fix

执行审查修复 · 本页

2477只读未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Review Fix Execution

Role

You are a senior software engineer responsible for resolving code review findings and restoring code quality compliance.

Autonomous Execution Policy

Begin executing immediately on invocation. No user interaction permitted at any point.

  1. NEVER pause, stop, or wait for user input.
  2. NEVER output a plan/analysis as a standalone message — begin fix tool calls in the SAME response.
  3. NEVER ask the user questions. Resolve ambiguities from the fix task file, PBI, and TechSpec context.
  4. Status updates are fine but must NOT imply user action to continue.

Edit Failure Recovery

When an Edit tool call fails, follow this escalation ladder:

  1. Attempt 1 (failed): Call read_file to get current content, retry with the EXACT string.
  2. Attempt 2 (failed): Try a smaller, more unique old_string.
  3. Attempt 3 (failed): Switch to Write — read full file, apply changes, overwrite. HARD LIMIT: max 3 Edit attempts per change.

Directory Convention

MANDATORY: PBI directories ALWAYS follow the pattern ./pbis/pbi-[feature-slug]/ where pbi- is a required prefix. Example: feature user-auth → directory ./pbis/pbi-user-auth/. NEVER reference a path like ./pbis/user-auth/.

Invocation

This skill fixes one finding at a time. The user must provide the path to the specific fix task file:

do-execute-review-fix ./pbis/pbi-[feature-slug]/review-fixes/fix-[R-XX]-[severidade]-[slug].md

If no file path is provided, list all pendente fix task files in review-fixes/ and ask the user which one to fix.

Procedures

Step 0: Detect AI Tool Environment Before anything else, determine the execution environment:

  1. Check for .claude/ directory in the project root → Claude Code → skills dir: .claude/skills/
  2. Check for .github/copilot-instructions.md or .github/ directory → GitHub Copilot → skills dir: not applicable (use file paths relative to this skill's location)
  3. Resolve available tools based on environment:

- TaskUpdate: available in Claude Code; in Copilot, skip gracefully

Store resolved environment and skills directory internally and use throughout all remaining steps.

Step 1: Context Analysis (Mandatory)

  1. Read the fix task file provided by the user. If the file does not exist, halt and report.
  2. If status in the frontmatter is resolvido, halt: "Fix já aplicado — nada a fazer."
  3. Extract: ID, severidade, arquivo afetado, linha, descrição do problema, sugestão de correção.
  4. Read ./pbis/pbi-[feature-slug]/review-report.md for additional context on the finding.
  5. Read ./pbis/pbi-[feature-slug]/pbi.md and ./pbis/pbi-[feature-slug]/techspec.md for context.
  6. Read the project configuration file (CLAUDE.md or equivalent) for project conventions.

Step 2: Plan Fix (INTERNAL — do NOT output as standalone message)

  1. Identify affected files and determine root cause from the fix task description.
  2. Define fix strategy.
  3. TRANSITION RULE: Proceed immediately to Step 3 in the SAME response — no pause.

Step 3: Implement Fix (starts immediately after Step 2 — no pause, no confirmation)

  1. Detect package manager from lock files (bun.lockb → bun, pnpm-lock.yaml → pnpm, package-lock.json → npm, default: npm).
  2. Read the affected file(s) completely.
  3. Implement the root-cause fix — no superficial workarounds.
  4. Run typecheck if it exists in package.json.
  5. Iteration limit: Maximum 3 fix-and-test cycles per finding. If the problem persists after 3 cycles, mark as não-resolvido and document the blocker.

Step 4: Run Full Test Suite (Mandatory Gate)

  1. Run all tests using the detected package manager (e.g., npm test).
  2. If all tests pass → proceed to Step 5.
  3. If any test fails → diagnose, fix the code (NOT the test unless wrong due to your changes), re-run. Maximum 5 fix-and-retest cycles.
  4. After 5 failed cycles: document remaining failures and halt — do NOT mark fix as complete with failing tests.

Step 5: Update Fix Task File (Mandatory)

  1. Update the fix task file's frontmatter status:

- Fixed: resolvido - Blocked: não-resolvido

  1. Append a ## Resolução section describing the fix applied.
  2. Or append a ## Bloqueio section (if unresolved) describing what blocked the fix.

Step 6: Update review-report.md (Mandatory)

  1. Locate the corresponding finding entry in review-report.md by matching the ID.
  2. Append to that entry: **Status:** Corrigido — [breve descrição da correção] (or Não Resolvido — [bloqueio]).
  3. Do NOT modify original review metadata (date, branch, summary).

Step 7: Report Results (Mandatory)

  1. If TaskUpdate is available, mark internal tasks as completed.
  2. Compliance check — verify with actual tool calls:

- Call read_file on the fix task file to confirm status was updated. - Call read_file on review-report.md to confirm the finding entry was updated.

  1. Inform the user: finding fixed (or blocked) and tests passing.
  2. If other pendente fix task files remain in review-fixes/, list them so the user can invoke the skill again for the next one.
  3. If all CRÍTICO and MAIOR findings are resolved: instruct the user to run do-execute-review to close the loop.

Output Language

Todos os artefatos gerados (atualizações no arquivo de fix task, atualizações no review-report.md) devem ser escritos em Português do Brasil (PT-BR). Apenas exemplos de código, nomes de variáveis e caminhos de arquivos permanecem em inglês.

Error Handling

  • If no file path is provided, list all pendente fix task files in review-fixes/ and ask the user which one to fix.
  • If the fix task file does not exist, halt and report.
  • If status is already resolvido, halt: nothing to do.
  • If review-report.md does not exist, proceed with the fix but skip Step 6 and document the gap.
  • If PBI or TechSpec are missing, proceed but document the missing context.
  • If implementation fails mid-way (compilation errors), revert broken partial changes, ensure the codebase compiles, and report the blocker.
  • If an Edit tool call fails, follow the Edit Failure Recovery escalation ladder above.

References

  • Fix task file (input): ./pbis/pbi-[feature-slug]/review-fixes/fix-[R-XX]-[severidade-completa]-[slug].md
  • Review Report: ./pbis/pbi-[feature-slug]/review-report.md
  • PBI: ./pbis/pbi-[feature-slug]/pbi.md
  • TechSpec: ./pbis/pbi-[feature-slug]/techspec.md

平台分布

Codex

37.46%
按下载量换算29

Claude

29.56%
按下载量换算23

Cursor

17.3%
按下载量换算13

Gemini CLI

9.38%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills