Token导航 LogoToken导航

Agent Skill · 研究检索

task(任务管理)

task 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。

task 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,权限为接触敏感数据;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 55,255。

总安装 489周安装 21GitHub Stars 2下载 171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:task(任务管理)
来源仓库:https://github.com/laststance/skills
仓库路径:skills/task
安装命令:
npx skills add https://github.com/laststance/skills --skill task
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/laststance/skills --skill task

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。

task 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。适用于任务管理、工作流协调等项目管理场景。通过关键词输入触发搜索,返回结构化结果列表供进一步处理。安装前需确认权限范围和维护状态,注意可能涉及联网和数据读取操作。

task 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/task

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/laststance/skills --skill task;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

    它需要接触敏感数据,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

task 怎么安装?

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

task 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。

task 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

task 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。

task 用的人多吗?

公开数据是累计安装 489 次,近一周安装 21 次,下载 171 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。

task 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

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 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

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 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
task

任务管理 · 本页

4892接触敏感数据未明确有提醒

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

Task — Systematic Implementation Workflow

Standard 5-phase workflow for all implementation tasks with built-in quality gates.

<essential_principles>

Serena Think Checkpoints (Mandatory)

Call the following Serena tools at the specified points. Never skip them.

CheckpointToolWhenPurpose
Adherence Gatemcp__serena__think_about_task_adherenceBefore each code edit in Phase 3Confirm still aligned with original task
Completion Gatemcp__serena__think_about_whether_you_are_doneBefore exiting Phase 4 (Verify)Confirm all work is truly complete

After Phase 1 and again after Phase 2, do a short information sufficiency self-check in prose (requirements understood, relevant code located, plan covers acceptance criteria and verification). If gaps remain, gather more context before continuing—do not rely on a removed Serena tool.

Introspection Markers (Always Active)

Use these markers throughout all phases to make reasoning visible:

  • 🤔 Reasoning — "🤔 The error suggests a missing dependency"
  • 🎯 Decision — "🎯 Choosing approach A over B because..."
  • ⚡ Performance — "⚡ This query may cause N+1"
  • 📊 Quality — "📊 Checking consistency with existing patterns"
  • 💡 Insight — "💡 This pattern can be reused for..."

Safety Rules

  • Before destructive operations (delete, overwrite, reset): Always confirm with user
  • Before code edits: Call think_about_task_adherence
  • Never auto-commit: Phase 5 waits for user instruction to commit/push
  • Quality gate required: Phase 4 must pass before Phase 5

</essential_principles>

Phase 1: Investigate

Understand the task and gather context.

  1. Parse task requirements from user input
  2. Read relevant code files (Grep, Read, Serena symbolic tools)
  3. Check external libraries with Context7 if needed
  4. Identify existing patterns and conventions
  5. Information sufficiency self-check — Confirm you understand the task, have seen the relevant code paths, and know project conventions well enough to plan. If not, keep reading or ask the user before Phase 2.

Tools: Grep, Read, Glob, mcp__serena__find_symbol, mcp__serena__get_symbols_overview, mcp__context7__query-docs

Phase 2: Plan

Break down the task and design the approach.

  1. Create task breakdown with TodoWrite
  2. Identify parallelizable steps: Plan: 1) Parallel [Read A, B] → 2) Edit → 3) Parallel [Test, Lint]
  3. Save plan to Serena Memory: mcp__serena__write_memory("plan_<topic>", content)
  4. Plan completeness self-check — Confirm the plan and todos cover acceptance criteria, edge cases, and how you will verify the change. Revise the plan if anything important is missing.

Output: TodoWrite entries with clear acceptance criteria per step.

Phase 3: Implement

Execute the plan with continuous adherence checks.

For each implementation step:

  1. Mark TodoWrite item as in-progress
  2. 🔶 think_about_task_adherence — Still on track?
  3. Edit code (Edit, Write)
  4. Use introspection markers (🤔🎯⚡📊💡) to explain reasoning
  5. Mark TodoWrite item as complete

Rules:

  • No // TODO: implement later — write working code
  • No mock objects outside tests
  • Follow existing code patterns and conventions
  • Confirm with user before destructive operations

Phase 4: Verify

Run quality checks and validate correctness.

Standard Verification (always)

Run in parallel where possible:

# Parallel execution
pnpm lint &
pnpm typecheck &
pnpm test &
pnpm build &
wait

If any check fails → investigate root cause → fix in Phase 3 → re-verify.

--frontend-verify (when flag is provided)

Visual verification across platforms. Auto-detect platform from package.json:

DependencyPlatformPreflightVerification Tool
*(default)*Webkill-port <port> && pnpm devagent-browser (open --headed, snapshot -i, screenshot)
electronElectronpnpm electron:dev/electron skill (agent-browser based Electron operation)
expo / react-nativeMobilemcp__ios-simulator__open_simulatoriOS Simulator MCP (screenshot, ui_tap, ui_swipe)
commander / inquirer / oclifCLIshell sessionShellwright MCP (TUI/CLI operation and output verification)

Frontend Verify Workflow:

  1. Preflight: Start dev server / app, confirm MCP connection
  2. Scenario creation: Design test scenarios based on changes, save to Serena Memory
  3. Execute: Run each scenario, take screenshot after each step
  4. Judge: All pass → continue. Any fail → return to Phase 3

Authentication for Frontend Verify

When verifying authenticated apps (SaaS dashboards, admin panels, OAuth-protected pages), use agent-browser's auth persistence:

StrategyCommandUse Case
state save/loadagent-browser state save auth.jsonSession cookies + localStorage. Best for most web apps
--profile <dir>agent-browser open <url> --profile./browser-dataFull Chromium user data dir. Best for complex OAuth (Google, GitHub SSO)
auth saveagent-browser auth save <name> --url <login-url>Encrypted credential store. Best for CI/shared environments

OAuth Flow:

  1. agent-browser open <login-url> --headed (must be headed for OAuth redirects)
  2. Complete OAuth manually or via snapshot -i + fill + click
  3. agent-browser state save auth.json to persist session
  4. Future runs: agent-browser state load auth.json before navigating to app

Security:

  • Add auth.json, browser-data/ to .gitignore
  • auth save uses AES-256-GCM encryption via AGENT_BROWSER_ENCRYPTION_KEY env var
  • State files auto-expire after 30 days
  • Use --headed for initial OAuth setup (redirects require visible browser)

Completion Gate

🔶 think_about_whether_you_are_done — Is everything truly complete?

Phase 5: Complete

Report results and wait for user instruction.

  1. Present verification summary to user:

- What was changed (files, functions) - Test results - Screenshots (if --frontend-verify)

  1. Update TodoWrite — mark all items complete
  2. ⏸️ Wait for user instruction to commit/push
  3. On user confirmation: git commit && git push

Quick Reference

/task fix the login button styling
/task add dark mode support --frontend-verify
/task refactor the API error handling

Phase Flow Diagram

[Investigate] → 🔶 info gate
     ↓
  [Plan] → 🔶 info gate
     ↓
[Implement] → 🔶 adherence gate (per edit)
     ↓
 [Verify] → 🔶 completion gate
     ↓
[Complete] → ⏸️ wait for user → commit/push

平台分布

Codex

35.46%
按下载量换算61

Claude

30.28%
按下载量换算52

Cursor

19.37%
按下载量换算33

Gemini CLI

9.1%
按下载量换算16

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

可疑

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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