Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计通过

do

Agent Skill

do 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。

总安装

356

周安装

15

GitHub Stars

60

下载量

125
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:do(做)
来源仓库:https://github.com/doodledood/manifest-dev
仓库路径:skills/do
安装命令:
npx skills add https://github.com/doodledood/manifest-dev --skill do
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/doodledood/manifest-dev --skill do

简介

do 执行 Manifest 文件中的交付物,确保满足验收标准。

  • 适用于项目管理流程,结合过程指引与全局不变量验证。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。
  • 自动适应现实偏差,但需人工介入处理异常或边界冲突。
  • 需确认 Manifest 格式正确,避免因输入错误导致执行失败。
  • do 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

/do - Manifest Executor

Goal

Execute a Manifest: satisfy all Deliverables' Acceptance Criteria while following Process Guidance and using Approach as initial direction (adapting when reality diverges), then verify everything passes (including Global Invariants).

Why quality execution matters: The manifest front-loaded the thinking—criteria are already defined. Your job is implementation that passes verification on first attempt. Every verification failure is rework.

Input

$ARGUMENTS = manifest file path (REQUIRED), optionally with execution log path and --mode <level>

If no arguments: Output error "Usage: /do [log-file-path] [--mode efficient|balanced|thorough]"

Execution Mode

Resolve mode from (highest precedence first): --mode argument → manifest mode: field → default thorough.

Invalid mode value → error and halt: "Invalid mode ''. Valid modes: efficient | balanced | thorough"

If mode is not thorough: read references/BUDGET_MODES.md for routing rules, escalation logic, and parallelism overrides. Follow those rules for the remainder of this /do run.

Existing Execution Log

If input includes a log file path (iteration on previous work): treat it as source of truth. It contains prior execution history. Continue from where it left off—append to the same log, don't restart.

Principles

PrincipleRule
ACs define successWork toward acceptance criteria however makes sense. Manifest says WHAT, you decide HOW.
Approach is initial, not rigidApproach provides starting direction, but plans break when hitting reality. Adapt freely when you discover better patterns, unexpected constraints, or dependencies that don't work as expected. Log adjustments with rationale.
Target failures specificallyOn verification failure, fix the specific failing criterion. Don't restart. Don't touch passing criteria.
Verify fixes firstAfter fixing a failure, confirm the fix works before re-running full verification.
Trade-offs guide adjustmentWhen risks (R-*) materialize, consult trade-offs (T-*) for decision criteria. Log adjustments with rationale.

Constraints

Log after every action - Write to execution log immediately after each AC attempt. No exceptions. This is disaster recovery—if context is lost, the log is the only record of what happened.

Must call /verify - Can't declare done without verification. Invoke manifest-dev:verify with manifest, log paths, and the resolved mode: /verify <manifest> <log> --mode <level>.

Escalation boundary - Escalate when: (1) ACs can't be met as written (contract broken), (2) user requests a pause mid-workflow, (3) you discover an AC or invariant should be amended (use "Proposed Amendment" escalation type), or (4) mode-specific fix-verify loop limit is reached (see references/BUDGET_MODES.md). If ACs remain achievable as written and no user interrupt, continue autonomously. Approach pivots don't require escalation — log adjustments with rationale and continue.

Mode-aware loop tracking - Track fix-verify iteration count and escalation count in the execution log. When mode limits are reached, follow the escalation rules in references/BUDGET_MODES.md. In efficient mode, also track total escalations and suggest mode switch after 3.

Stop requires /escalate - During /do, you cannot stop without calling /verify→/done or /escalate. If you need to pause (user requested, waiting on external action), call /escalate with "User-Requested Pause" format. Short outputs like "Done." or "Waiting." will be blocked.

Refresh before verify - Read full execution log before calling /verify to restore context.

Refresh between deliverables - Before starting a new deliverable, re-read the manifest's deliverable section and relevant execution log entries. Context degrades gradually across a long session — don't rely on what you remember from D1 when starting D3.

Memento Pattern

Externalize progress to survive context loss. The log IS the disaster recovery mechanism.

Execution log: Create /tmp/do-log-{timestamp}.md at start. After EACH AC attempt, append what happened and the outcome. Goal: another agent reading only the log could resume work.

Todos: Create from manifest (deliverables → ACs). Start with execution order from Approach (adjust if dependencies require). Update todo status after logging (log first, todo second).

Collaboration Mode

When $ARGUMENTS contains a TEAM_CONTEXT: block, read references/COLLABORATION_MODE.md for full collaboration mode instructions. If no TEAM_CONTEXT: block is present, ignore this — all other sections apply as written.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

34.3%
按下载量换算43

Claude

32.23%
按下载量换算40

Cursor

19.05%
按下载量换算24

Gemini CLI

9.78%
按下载量换算12

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills