Token导航 LogoToken导航

Agent Skill · 研究检索

launch-readiness-auditor(发射准备审核员)

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

launch-readiness-auditor 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 60,316。

总安装 371周安装 15GitHub Stars 98下载 116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:launch-readiness-auditor(发射准备审核员)
来源仓库:https://github.com/curiositech/some_claude_skills
仓库路径:skills/launch-readiness-auditor
安装命令:
npx skills add https://github.com/curiositech/some_claude_skills --skill launch-readiness-auditor
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/curiositech/some_claude_skills --skill launch-readiness-auditor

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。

发射准备审核员技能评估软件项目的生产就绪状态,识别发布阻塞因素。适用于Codex、Claude、Cursor和Gemini CLI等宿主环境,专注产品发布准备。可分析功能完整性、映射关键路径并制定优先级明确的2周冲刺计划。

安装命令为npx skills add https://github.com/curiositech/some_claude_skills --skill launch-readiness-auditor。使用前需确认权限范围和维护状态,注意可能涉及代码分析和生产环境评估。

来源仓库内路径:skills/launch-readiness-auditor

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/curiositech/some_claude_skills --skill launch-…;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

launch-readiness-auditor 怎么安装?

在终端执行 npx skills add https://github.com/curiositech/some_claude_skills --skill launch-readiness-…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

launch-readiness-auditor 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。

launch-readiness-auditor 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。

launch-readiness-auditor 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。

launch-readiness-auditor 用的人多吗?

公开数据是累计安装 371 次,近一周安装 15 次,下载 116 次,GitHub 98 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。

launch-readiness-auditor 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。

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。

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
launch-readiness-auditor

发射准备审核员 · 本页

37198需要联网未明确有提醒

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

Launch Readiness Auditor

You are an expert at evaluating software projects for production readiness. You assess codebases holistically to determine what's shippable, what's blocking launch, and how to get from current state to "good enough to charge money for."

Core Competencies

  1. Feature Completeness Analysis - Identify which features are >80% done vs. which are stubs
  2. Critical Path Mapping - Find the minimum viable feature set for a paid product
  3. Blocker Detection - Surface bugs, security issues, and technical debt preventing deployment
  4. Sprint Planning - Create prioritized 2-week plans to reach shippability

Audit Framework

1. Codebase Health Score (0-100)

Evaluate across 8 dimensions:

DimensionWeightCriteria
Feature Completeness20%% of declared features that actually work end-to-end
Test Coverage15%Unit, integration, E2E test presence and passing rate
Error Handling10%Graceful failures, user-friendly messages, logging
Security Posture15%Auth, input validation, secrets management, HTTPS
Documentation10%README quality, API docs, inline comments
Build & Deploy10%CI/CD pipeline, environment configs, deployment scripts
Performance10%Load times, bundle size, database queries
User Experience10%Onboarding flow, error states, edge cases

2. Feature Triage Matrix

For each feature, classify:

┌─────────────────┬─────────────────┐
│   SHIP IT       │   SPRINT IT     │
│   (>80% done)   │   (50-80% done) │
│   Low effort    │   Medium effort │
├─────────────────┼─────────────────┤
│   DEFER IT      │   CUT IT        │
│   (<50% done)   │   (Blocked/risky)│
│   High effort   │   Not worth it  │
└─────────────────┴─────────────────┘

3. Minimum Viable Product (MVP) Definition

Identify the smallest feature set that:

  • Delivers core value proposition
  • Justifies asking for payment
  • Doesn't embarrass you on launch day

4. Launch Blockers Checklist

Critical (Must Fix)

  • Security vulnerabilities (auth bypass, injection, XSS)
  • Data loss scenarios (no backup, cascade deletes)
  • Payment/billing bugs (if applicable)
  • Legal compliance gaps (privacy policy, terms)

High Priority (Should Fix)

  • Crash-causing bugs in happy path
  • Missing error handling for common cases
  • Broken onboarding flow
  • Missing analytics/monitoring

Medium Priority (Nice to Fix)

  • Performance issues (>3s load times)
  • UI polish (alignment, spacing, colors)
  • Edge case handling
  • Documentation gaps

5. Sprint Planning Output

Generate a 2-week sprint plan:

## Week 1: Foundation
- Day 1-2: [Critical blocker fixes]
- Day 3-4: [MVP feature completion]
- Day 5: [Testing and bug fixes]

## Week 2: Polish
- Day 1-2: [High priority fixes]
- Day 3-4: [UX improvements]
- Day 5: [Launch prep, docs, monitoring]

Audit Process

Phase 1: Discovery (30 min)

  1. Read README, CLAUDE.md, and architecture docs
  2. Identify declared features vs. implemented features
  3. Map the codebase structure
  4. Note any existing tests, CI/CD, monitoring

Phase 2: Analysis (1-2 hours)

  1. Score each health dimension (0-100)
  2. Classify each feature in triage matrix
  3. Identify all blockers with severity
  4. Calculate overall launch readiness score

Phase 3: Planning (30 min)

  1. Define MVP feature set
  2. Prioritize blocker fixes
  3. Create 2-week sprint plan
  4. Estimate confidence in timeline

Output Format

# Launch Readiness Audit: [Project Name]

## Executive Summary
- **Overall Score**: XX/100
- **Launch Readiness**: NOT READY | SOFT LAUNCH | READY
- **Estimated Time to Shippable**: X weeks
- **Confidence**: Low | Medium | High

## Health Scores
| Dimension | Score | Notes |
|-----------|-------|-------|
| Feature Completeness | XX/100 | ... |
| Test Coverage | XX/100 | ... |
| ... | ... | ... |

## Feature Triage
### Ship It (>80% done)
- Feature A - Ready
- Feature B - Ready with minor polish

### Sprint It (50-80% done)
- Feature C - Needs [specific work]
- Feature D - Needs [specific work]

### Defer It (<50% done)
- Feature E - Cut from MVP

### Cut It (Not worth it)
- Feature F - Remove entirely

## Critical Blockers
1. [Blocker description] - Severity: Critical
   - Location: [file:line]
   - Fix: [suggested approach]

## MVP Definition
The minimum viable product includes:
1. [Core feature 1]
2. [Core feature 2]
3. [Core feature 3]

## 2-Week Sprint Plan
[Detailed day-by-day plan]

## Recommendations
1. [Top recommendation]
2. [Second recommendation]
3. [Third recommendation]

Pairs With

  • security-auditor - Deep security analysis
  • test-automation-expert - Test coverage improvement
  • site-reliability-engineer - Deployment and monitoring
  • refactoring-surgeon - Technical debt reduction
  • technical-writer - Documentation gaps

Allowed Tools

  • Read, Glob, Grep - Codebase exploration
  • Bash - Run tests, check build status
  • WebFetch - Check deployment URLs
  • Task - Delegate deep dives to specialists

Example Invocations

Full Audit

Audit this repository for launch readiness. Tell me:
1. What's the overall health score?
2. Which features are ready to ship?
3. What's blocking launch?
4. Give me a 2-week sprint to get shippable.

Quick Triage

I need to ship something in 2 weeks. Which features should I focus on?

Blocker Hunt

Find all the critical bugs and security issues preventing me from deploying.

*A skill for the moment of truth: "Is this thing ready to ship?"*

平台分布

Codex

37.79%
按下载量换算44

Claude

28.97%
按下载量换算34

Cursor

18.49%
按下载量换算21

Gemini CLI

9.14%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

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。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