Token导航 LogoToken导航

Agent Skill · 研究检索

apply-all-findings(应用所有调查结果)

apply-all-findings 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。

apply-all-findings 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,权限为需要联网;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 55,410。

总安装 480周安装 20GitHub Stars 6下载 160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
MIT

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:apply-all-findings(应用所有调查结果)
来源仓库:https://github.com/troykelly/claude-skills
仓库路径:skills/apply-all-findings
安装命令:
npx skills add https://github.com/troykelly/claude-skills --skill apply-all-findings
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/troykelly/claude-skills --skill apply-all-findings

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。

用于查找、检索和筛选相关信息。apply-all-findings 属于研究检索类 Skill,可作为该场景下的辅助能力补充。适合根据关键词快速定位候选结果。通过 GitHub 安装,需确认权限和维护状态。可能触发联网或文件读写,建议提前评估风险。

适用于 Codex、Claude、Cursor 和 Gemini CLI。

来源仓库内路径:skills/apply-all-findings

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/troykelly/claude-skills --skill apply-all-find…;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

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

apply-all-findings 怎么安装?

在终端执行 npx skills add https://github.com/troykelly/claude-skills --skill apply-all-findings。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

apply-all-findings 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。

apply-all-findings 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

apply-all-findings 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

apply-all-findings 用的人多吗?

公开数据是累计安装 480 次,近一周安装 20 次,下载 160 次,GitHub 6 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。

apply-all-findings 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 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
apply-all-findings

应用所有调查结果 · 本页

4806需要联网MIT通过

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

Apply All Findings

Overview

Address EVERY finding from code review. Findings are either FIXED or DEFERRED with tracking issues.

Core principle: Minor issues accumulate into major problems.

The rule: If it was worth noting, it's worth tracking.

ABSOLUTE REQUIREMENT: Every finding results in ONE of:

  1. Fixed in this PR (verified)
  2. Tracking issue created (linked in review artifact)

There is NO third option. "Won't fix without tracking" is NOT permitted.

Why All Findings

Minor Issues Compound

1 unclear variable name +
1 missing null check +
1 inconsistent style +
1 outdated comment =
Confusing, fragile code

Selective Fixing Creates Precedent

"This minor issue can wait" →
"That minor issue can wait too" →
"We don't fix minor issues" →
Technical debt mountain

Thoroughness Builds Quality Culture

Every finding addressed →
High standards maintained →
Quality becomes habit

The Process

Step 1: Gather All Findings

From comprehensive-review, you have:

### Findings

1. [Critical] SQL injection in findUser()
2. [Major] N+1 query in getOrders()
3. [Minor] Variable 'x' should be renamed
4. [Minor] Missing JSDoc on helper()
5. [Minor] Inconsistent quote style

Step 2: Create Checklist

Every finding becomes a todo:

- [ ] Fix SQL injection in findUser()
- [ ] Fix N+1 query in getOrders()
- [ ] Rename variable 'x' to descriptive name
- [ ] Add JSDoc to helper()
- [ ] Fix quote style to use single quotes

Step 3: Address Systematically

Work through the list. For each finding:

If Fixable:
  1. Fix the issue
  2. Verify the fix
  3. Check off the item
  4. Move to next finding
If Not Fixable in This PR:
  1. Verify valid deferral reason (see deferred-finding skill)
  2. Create tracking issue with full documentation
  3. Add tracking issue to review artifact
  4. Mark as DEFERRED (not unaddressed)
  5. Move to next finding
# Create tracking issue for deferred finding
gh issue create \
  --title "[Finding] [Description] (from #123)" \
  --label "review-finding,depth:1" \
  --body "[Full deferred-finding template]"

# Create spawned-from label if needed
gh label create "spawned-from:#123" --color "C2E0C6" 2>/dev/null || true
gh issue edit [NEW_ISSUE] --add-label "spawned-from:#123"

Step 4: Verify All Complete

Before considering done:

# Re-run linting
pnpm lint

# Re-run tests
pnpm test

# Re-run type check
pnpm typecheck

All checks must pass.

Step 5: Update Review Artifact

After all findings addressed, update artifact in issue comment:

  1. All FIXED findings marked ✅ FIXED
  2. All DEFERRED findings have tracking issue # linked
  3. "Unaddressed: 0" in summary
  4. "Review Status: COMPLETE"

Addressing by Type

Critical/Major Findings

These require code changes:

// Finding: SQL injection in findUser()
// Before
return db.query(`SELECT * FROM users WHERE username = '${username}'`);

// After
return db.query('SELECT * FROM users WHERE username = ?', [username]);

Minor: Naming

// Finding: Variable 'x' should be renamed
// Before
const x = users.filter(u => u.active);

// After
const activeUsers = users.filter(user => user.isActive);

Minor: Documentation

// Finding: Missing JSDoc on helper()
// Before
function helper(data: Data): Result {

// After
/**
 * Transforms raw data into the expected result format.
 *
 * @param data - Raw data from the API
 * @returns Transformed result ready for display
 */
function helper(data: Data): Result {

Minor: Style

// Finding: Inconsistent quote style
// Before
const name = "Alice";
const greeting = 'Hello';

// After (using project standard: single quotes)
const name = 'Alice';
const greeting = 'Hello';

Handling Deferrals

Valid Deferral Reasons

ReasonExampleRequires
Out of scopeArchitectural changeTracking issue
External dependencyInfrastructure changeTracking issue
Breaking changeMajor version bumpTracking issue
Separate concernIndependent featureTracking issue

NOT Valid Deferral Reasons

ExcuseRealityAction
"It's minor"Minor compoundsFix now
"Takes too long"Debt takes longerFix now
"Good enough"Never enoughFix now
"Not important"Then why note it?Fix now
"Do it later"Without tracking? No.Fix or create issue

Deferral MUST Create Issue

ABSOLUTE: No deferral without tracking issue.

# WRONG - Deferred without tracking
"We'll fix the SQL injection later"  # NO

# RIGHT - Deferred with tracking
gh issue create --title "[Finding] SQL injection in findUser (from #123)" ...
# Then link #456 in review artifact

Verification

After addressing all findings:

Run All Checks

# Linting
pnpm lint

# Type checking
pnpm typecheck

# Tests
pnpm test

# Build
pnpm build

Review the Diff

git diff

Verify:

  • All findings addressed
  • No unrelated changes
  • Tests updated if behavior changed

Self-Review Again

Quick pass through 7 criteria to ensure fixes didn't introduce new issues.

Checklist

Before moving on from review:

  • All critical findings addressed
  • All major findings addressed
  • All minor findings addressed
  • Any deferred finding has tracking issue created
  • Tracking issues linked in review artifact
  • All automated checks pass
  • Fixes reviewed for correctness
  • No new issues introduced
  • Review artifact updated with final status
  • "Unaddressed: 0" confirmed

Common Pushback (Rejected)

PushbackResponse
"We can fix minors later"Without tracking? No. Create issue or fix now.
"This is slowing us down"Debt slows you down more.
"It's not important"Then why was it noted?
"Good enough"Good enough is never enough.
"The reviewer is being picky"Attention to detail is valuable.

Integration

This skill is called by:

  • issue-driven-development - Step 10

This skill follows:

  • comprehensive-review - Generates the findings

This skill uses:

  • deferred-finding - For creating tracking issues

This skill ensures:

  • No accumulated minor issues
  • Consistent quality standards
  • Complete reviews, not partial
  • All deferrals tracked in GitHub

平台分布

Claude Code

30.96%
按下载量换算50

Antigravity

22.41%
按下载量换算36

Gemini CLI

16.44%
按下载量换算26

OpenCode

12.79%
按下载量换算20

Cursor

7.4%
按下载量换算12

kiro-cli

3.97%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。

继续浏览同类 Skills