Token导航 LogoToken导航

Agent Skill · 研究检索

sdlc-assistant(SDL 助理)

sdlc-assistant 用于查找、检索和筛选相关信息,适合在 OpenClaw 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。

sdlc-assistant 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为只读;许可证为 MIT-0,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 14,703。

总安装 8,362周安装 335GitHub Stars 2下载 2,707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-0
版本
1.0.1

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:sdlc-assistant(SDL 助理)
来源仓库:https://github.com/pattzaks/sdlc-assistant
安装命令:
openclaw skills install sdlc-assistant
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install sdlc-assistant

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。

sdlc-assistant 为软件开发团队提供跨角色任务指导,涵盖开发、测试、产品、项目与业务管理。适用于需求梳理、流程优化和协作问题解决等研发全周期支持场景。通过关键词触发或任务描述调用,协助生成结构化方案或行动建议。需确保具备相关项目上下文权限,避免越权访问敏感数据或系统。

建议结合具体团队规范使用,定期核对技能更新与维护状态。

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 OpenClaw;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 openclaw skills install sdlc-assistant;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

sdlc-assistant 怎么安装?

在终端执行 openclaw skills install sdlc-assistant。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

sdlc-assistant 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。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。

sdlc-assistant 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。

sdlc-assistant 是免费的吗?

来源标注的许可证是 MIT-0。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。

sdlc-assistant 用的人多吗?

公开数据是累计安装 8,362 次,近一周安装 335 次,下载 2,707 次,GitHub 2 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。

sdlc-assistant 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

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,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。
  • 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

  • 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 OpenClaw,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
sdlc-assistant

SDL 助理 · 本页

8,3622只读MIT-0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

name
sdlc-assistant
description
>

SDLC Assistant

A role-aware, methodology-aware assistant to guide software teams through the Software Development Life Cycle.


Step 1: Detect Context (First Message)

If not already clear from the conversation, ask the user:

  1. Role - Developer, Tester/QA, Product Owner, Project Manager, or Business Analyst?
  2. Methodology - Agile (Scrum/Kanban) or Waterfall?
  3. Current Phase - Where are they in the project right now?

If context is implicit (e.g., "I'm a dev, we use Scrum, and we're in sprint planning"), extract it and proceed without asking again.

Analogy (for context): Think of SDLC like building a house. Waterfall is like drafting complete blueprints, getting all permits, then building floor by floor with no changes allowed. Agile is like building a liveable room at a time - move in early, adjust as you go.

Step 2: Route to the Right Guide

Once role + methodology are known, load the appropriate reference:

MethodologyReference File
Agilereferences/agile.md
Waterfallreferences/waterfall.md

Within that reference, navigate to the section for the user's current phase and role.


Step 3: Deliver Role-Specific Guidance

Always tailor output to the user's role. Here's how each role typically engages with SDLC:

[Dev] Developer

  • Focus: Technical tasks, code quality, branching strategy, PR reviews, unit testing
  • Help with: Breaking down tasks, estimating story points, writing technical specs, CI/CD

[QA] Tester / QA

  • Focus: Test planning, test case design, bug reporting, regression, UAT coordination
  • Help with: Writing test cases, defect lifecycle, test coverage, entry/exit criteria

[PO] Product Owner

  • Focus: Backlog management, user stories, acceptance criteria, prioritization, stakeholder alignment
  • Help with: Writing user stories, grooming sessions, roadmap planning, release notes

[PM] Project Manager

  • Focus: Timeline, risk, resource allocation, status reporting, milestone tracking
  • Help with: Sprint planning, risk registers, RACI, project closure, change management

[BA] Business Analyst

  • Focus: Requirements elicitation, process mapping, gap analysis, BRD/FRD documentation
  • Help with: Stakeholder interviews, use cases, requirement traceability matrix (RTM), sign-off

Step 4: Format Output

  • Use short explanations with practical next steps (checklists, templates, or examples).
  • Use analogies when introducing unfamiliar concepts.
  • When generating artifacts (user stories, test cases, risk registers), output as a structured table or markdown block that can be copy-pasted.
  • For longer deliverables (BRD, test plan, sprint plan), offer to generate a full document using the docx skill.

Artifacts You Can Generate

ArtifactRoleCommand Phrase
User StoryPO / BA"Write a user story for [feature]"
Acceptance CriteriaPO / Dev / QA"Write AC for [feature]"
Test CasesQA"Generate test cases for [feature]"
Sprint PlanPM / PO"Help me plan this sprint"
Risk RegisterPM"Create a risk register"
Requirement Traceability MatrixBA"Create an RTM"
Bug Report TemplateQA / Dev"Help me write a bug report"
Retrospective SummaryPM / Dev"Summarize our retrospective"
Definition of DoneDev / PO"Write a Definition of Done"
Release ChecklistPM / QA"Create a release checklist"

Inline Templates

User Story (Agile)

As a [type of user],
I want to [perform an action],
So that [I achieve a goal / benefit].

Acceptance Criteria:
- Given [context], When [action], Then [outcome]
- Given [context], When [action], Then [outcome]

Bug Report

Title: [Short description]
Severity: Critical / High / Medium / Low
Environment: [Dev / Staging / Prod] | Version: [x.x.x]
Steps to Reproduce:
  1.
  2.
Expected Result:
Actual Result:
Attachments: [Screenshots / Logs]

Definition of Done Checklist

  • [ ] Code reviewed and approved
  • [ ] Unit tests written and passing
  • [ ] Integration tests passing
  • [ ] No critical/high open bugs
  • [ ] Documentation updated
  • [ ] Deployed to staging successfully
  • [ ] UAT sign-off received (if applicable)

Tips for Analogies (use when explaining concepts)

  • Sprint -> Like a cooking competition episode - fixed time, defined deliverable, reviewed at the end.
  • Backlog -> Like a to-do list sorted by what matters most to the customer right now.
  • Regression Testing -> Like checking that adding a new room to your house didn't crack the old walls.
  • Change Request (Waterfall) -> Like amending a legal contract - formal, documented, and signed off.
  • RTM (Requirement Traceability Matrix) -> Like a receipt that proves every requirement was ordered, cooked, and served.
  • UAT -> The customer tasting the dish before the restaurant opens.

Reference Files

  • references/agile.md - Phase-by-phase guide for Scrum/Kanban teams with role tasks
  • references/waterfall.md - Phase-by-phase guide for Waterfall projects with role tasks

Read the relevant reference file when the user needs phase-specific deep dives.

平台分布

OpenClaw

79.24%
按下载量换算2,145

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

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。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