Token导航 LogoToken导航

Agent Skill · 研究检索

implementing(implementing 搜索)

implementing 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。

implementing 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,权限为执行命令;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 42,821。

总安装 1,041周安装 33GitHub Stars 20下载 261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:implementing(implementing 搜索)
来源仓库:https://github.com/desplega-ai/ai-toolbox
仓库路径:skills/implementing
安装命令:
npx skills add https://github.com/desplega-ai/ai-toolbox --skill implementing
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/desplega-ai/ai-toolbox --skill implementing

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。

implementing 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。适用于需要根据关键词、任务场景或来源线索进行信息搜集与整理的场景。通过关键词匹配和来源仓库筛选实现信息检索,支持结合具体任务目标使用。

安装命令为 npx skills add https://github.com/desplega-ai/ai-toolbox --skill implementing。使用前需确认权限范围、维护状态,注意是否触发联网或文件读写操作。

来源仓库内路径:skills/implementing

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/desplega-ai/ai-toolbox --skill implementing;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

    它需要执行命令,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

implementing 怎么安装?

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

implementing 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。

implementing 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/desplega-ai/ai-toolbox --skill implementing;npx skills add desplega-ai/ai-toolbox --skill "implementing" 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

implementing 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。

implementing 用的人多吗?

公开数据是累计安装 1,041 次,近一周安装 33 次,下载 261 次,GitHub 20 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。

implementing 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

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 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

  • 不能接受 Skill 在你机器上执行命令的人。
  • 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
implementing

implementing 搜索 · 本页

1,04120执行命令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

Implementing

You are implementing an approved technical plan, executing it phase by phase with verification at each step. Each phase is executed as a background sub-agent via desplega:phase-running — the main session acts as an orchestrator.

Working Agreement

These instructions establish a working agreement between you and the user. The key principles are:

  1. AskUserQuestion is your primary communication tool - Whenever you need to ask the user anything (clarifications, preferences, decisions, confirmations), use the AskUserQuestion tool. Don't output questions as plain text - always use the structured tool so the user can respond efficiently.
  2. Establish preferences upfront - Ask about user preferences at the start of the workflow, not at the end when they may want to move on.
  3. Autonomy mode guides interaction level - The user's chosen autonomy level determines how often you check in, but AskUserQuestion remains the mechanism for all questions.

User Preferences

Before starting implementation (unless autonomy is Autopilot), establish these preferences:

File Review Preference - Check if the file-review plugin is available (look for file-review:file-review in available commands).

If file-review plugin is installed, use AskUserQuestion with:

QuestionOptions
"Would you like to use file-review for inline feedback on code changes during implementation?"1. Yes, open file-review for significant changes (Recommended), 2. No, I'll review changes directly

Store this preference and apply it throughout implementation.

When to Use

This skill activates when:

  • User invokes /implement-plan command
  • Another skill references **REQUIRED SUB-SKILL:** Use desplega:implementing
  • User asks to execute or implement an existing plan

Autonomy Mode

Adapt your behavior based on the autonomy mode:

ModeBehavior
AutopilotExecute all phases, pause only for manual verification or blockers
Critical (Default)Pause between phases for approval, ask when mismatches found
VerboseCheck in frequently, confirm before each major change

The autonomy mode is passed by the invoking command. If not specified, default to Critical.

Initial Setup Questions

After establishing user preferences, use AskUserQuestion to gather implementation-specific details:

1. Branch/Worktree Setup

First, check the current branch: git branch --show-current

Then check if the wts plugin is available (look for wts:wts in available skills).

If wts plugin is installed, use AskUserQuestion with these options:

QuestionOptions
"You're currently on branch <current-branch>. Where would you like to implement?"1. Continue on current branch, 2. Create a new branch, 3. Create a wts worktree

If wts plugin is NOT installed, use AskUserQuestion with:

QuestionOptions
"You're currently on branch <current-branch>. Where would you like to implement?"1. Continue on current branch, 2. Create a new branch

2. Commit Strategy

Use AskUserQuestion with these options:

QuestionOptions
"How would you like to handle commits during implementation?"1. Commit after each phase (Recommended for complex plans), 2. Commit at the end (Single commit for all changes), 3. Let me decide as I go

If "Commit after each phase" is selected:

  • After completing each phase's verification, create a commit with message: [Phase N] <phase name>
  • Use the plan's phase descriptions for commit messages

Store these preferences and apply them throughout the implementation.

Prior Learning Recall

OPTIONAL SUB-SKILL: If ~/.agentic-learnings.json exists, run /learning recall <current topic> to check for relevant prior learnings before proceeding.

Getting Started

When given a plan path:

  1. Read the plan completely
  2. Check for existing checkmarks (- [x])
  3. Set plan status to status: in-progress by editing the frontmatter status field. This signals to progress-tracking hooks which plan is active.
  4. Read files fully - never use limit/offset parameters
  5. Think deeply about how the pieces fit together
  6. Create a todo list to track progress
  7. Start implementing if you understand what needs to be done

If no plan path provided, ask for one.

Implementation Philosophy

Plans are carefully designed, but reality can be messy. Your job is to:

  • Follow the plan's intent while adapting to what you find
  • Implement each phase fully before moving to the next
  • Verify your work makes sense in the broader codebase context
  • Update checkboxes in the plan as you complete sections

When things don't match the plan exactly, think about why and communicate clearly.

Handling Mismatches

If you encounter a mismatch (and autonomy mode is not Autopilot):

  • STOP and think deeply about why the plan can't be followed
  • Use AskUserQuestion to present the issue and get direction:
QuestionOptions
"Issue in Phase [N]: Expected [what the plan says], Found [actual situation]. Why this matters: [explanation]. How should I proceed?"1. Adapt plan to match reality, 2. Proceed as originally planned, 3. Stop and discuss

In Autopilot mode, use best judgment and document decisions in comments.

Verification Approach

Each phase is executed via a background sub-agent running desplega:phase-running:

  1. Read the phase overview in the main session (minimal context usage)
  2. Spawn a desplega:phase-running agent in background with plan path + phase number:

- Use the Agent tool with run_in_background: true - Pass the plan path and phase number as context

  1. Wait for agent completion — you'll be notified when it finishes
  2. Review the agent's report — check status (completed/blocked/failed), changed files, verification results
  3. Check QA spec status — If the phase agent reports QA: pending, present the QA spec's test scenarios to the user and offer:

- Execute QA now (→ invoke desplega:qa with plan path + phase context) - Skip QA for this phase - If QA: passed, note it and proceed. If QA: n/a, proceed normally.

  1. Handle manual verification with the user — present the manual verification items from the phase
  2. Proceed to next phase after user confirms

The implementing skill is an orchestrator — it coordinates phases, handles human checkpoints, and manages cross-phase decisions, but delegates actual implementation work to phase-runner sub-agents.

Pause for Human Verification (if not Autopilot or executing multiple phases)

Phase [N] Complete - Ready for Manual Verification

Automated verification passed:
- [List automated checks that passed]

Please perform the manual verification steps listed in the plan:
- [List manual verification items from the plan]

Let me know when manual testing is complete so I can proceed to Phase [N+1].

If instructed to execute multiple phases consecutively, skip the pause until the last phase.

Do not check off manual testing items until confirmed by the user.

If You Get Stuck

When something isn't working as expected:

  1. Make sure you've read and understood all relevant code
  2. Consider if the codebase has evolved since the plan was written
  3. Present the mismatch clearly and ask for guidance (unless Autopilot)
  4. Use sub-tasks sparingly for targeted debugging

Resuming Work

If the plan has existing checkmarks:

  • Trust that completed work is done
  • Pick up from the first unchecked item
  • Verify previous work only if something seems off

Learning Capture

OPTIONAL SUB-SKILL: If significant insights, patterns, gotchas, or decisions emerged during this workflow, consider using desplega:learning to capture them via /learning capture. Focus on learnings that would help someone else in a future session.

Completing Implementation

When all phases are complete and verified:

  1. Set the plan frontmatter status field to completed.
  2. Ensure automated verification checkboxes are updated.
  3. Leave manual verification checkboxes unchecked until the user confirms completion.
  4. Offer post-implementation auditing: "Would you like me to run /verify-plan for a post-implementation audit, then /review for a final quality check?"

Remember: You're implementing a solution, not just checking boxes. Keep the end goal in mind.

Review Integration

If the file-review plugin is available and the user selected "Yes" during User Preferences setup:

  • After significant code changes in each phase, invoke /file-review:file-review <changed-file-path> for inline human comments
  • Process feedback with file-review:process-review skill before moving to the next phase
  • If user selected "No" or autonomy mode is Autopilot, skip this step

平台分布

Claude Code

27.13%
按下载量换算71

OpenCode

25.21%
按下载量换算66

Codex

20.5%
按下载量换算54

Antigravity

12.8%
按下载量换算33

Gemini CLI

8.35%
按下载量换算22

windsurf

3.88%
按下载量换算10

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/desplega-ai/ai-toolbox --skill implementing;npx skills add desplega-ai/ai-toolbox --skill "implementing" 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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