just-do

GitHub

基于目标驱动的清单执行技能,自动读取并执行 Manifest,自主决策以达成所有验收标准和全局不变量,支持断点续传和阻塞上报。

claude-plugins/manifest-dev/skills/just-do/SKILL.md doodledood/manifest-dev

Trigger Scenarios

用户要求直接执行清单 基于目标自主运行 Manifest 执行极简流程的任务

Install

npx skills add doodledood/manifest-dev --skill just-do -g -y
More Options

Non-standard path

npx skills add https://github.com/doodledood/manifest-dev/tree/main/claude-plugins/manifest-dev/skills/just-do -g -y

Use without installing

npx skills use doodledood/manifest-dev@just-do

指定 Agent (Claude Code)

npx skills add doodledood/manifest-dev --skill just-do -a claude-code -g -y

安装 repo 全部 skill

npx skills add doodledood/manifest-dev --all -g -y

预览 repo 内 skill

npx skills add doodledood/manifest-dev --list

SKILL.md

Frontmatter
{
    "name": "just-do",
    "description": "Goal-based Manifest executor. Reads a Manifest and pursues it with full autonomy: reach a state where every Acceptance Criterion and Global Invariant holds, deciding for itself how to get there. Use when the user asks to just do a manifest, run it goal-based, or execute with minimal process.",
    "argument-hint": "<manifest-path>",
    "user-invocable": true
}

Read the Manifest at the given path in full; no path → halt with usage. Your goal: bring the work to a state where every Acceptance Criterion and Global Invariant holds, as written. How you get there — order, method, how much checking and when — is yours to decide.

Acceptance Criteria and Global Invariants are the contract. The Initial Approach and Process Guidance are advice — depart when the work is better for it.

The Manifest is read-only. Never edit it. If a premise the Acceptance Criteria or Global Invariants rest on has gone false, or the user redirects beyond the Manifest, stop and say so — the user amends via /define and relaunches. Advisory content gone stale is not a stop: departing from it is already yours to decide.

Before starting work, arm the completion backstop. If a goal is already active for this Manifest's path, continue under it. Otherwise, if the harness provides a goal-setting, continuation, or durable-completion-condition capability, set this goal: "Every Acceptance Criterion and Global Invariant in holds, with evidence from the artifacts the gates name, and completion has been reported. The Manifest at that path is canonical and read-only. Record compact checkpoint notes as work proceeds — what changed, what was verified, what remains, blockers. Stop only when blocked on something a person must resolve." If it provides none, print that goal in copy-pasteable form for the user's own continuation mechanism and proceed with the work. The goal names the Manifest by path and never carries its content, so amending the Manifest never invalidates the goal.

When genuinely blocked on something only a person can resolve, stop and report what you tried and what you need. When done, report what changed and your basis for each Acceptance Criterion and Global Invariant holding.

Version History

  • 2ac487e Current 2026-08-20 08:56

Same Skill Collection

.claude/skills/auto-optimize-prompt/SKILL.md
.claude/skills/compress-prompt/SKILL.md
.claude/skills/harden-task-file/SKILL.md
.claude/skills/learn-from-session/SKILL.md
.claude/skills/optimize-prompt-token-efficiency/SKILL.md
.claude/skills/sync-claude-code-plugins/SKILL.md
.claude/skills/sync-tools/SKILL.md
claude-plugins/manifest-dev-tools/skills/babysit-pr/SKILL.md
claude-plugins/manifest-dev-tools/skills/handoff/SKILL.md
claude-plugins/manifest-dev-tools/skills/prompt-engineering/SKILL.md
claude-plugins/manifest-dev-tools/skills/re-pitch/SKILL.md
claude-plugins/manifest-dev-tools/skills/review-pr/SKILL.md
claude-plugins/manifest-dev-tools/skills/review-prompt/SKILL.md
claude-plugins/manifest-dev-tools/skills/walk-pr/SKILL.md
claude-plugins/manifest-dev/skills/auto/SKILL.md
claude-plugins/manifest-dev/skills/check-pr/SKILL.md
claude-plugins/manifest-dev/skills/define/SKILL.md
claude-plugins/manifest-dev/skills/do/SKILL.md
claude-plugins/manifest-dev/skills/done/SKILL.md
claude-plugins/manifest-dev/skills/escalate/SKILL.md
claude-plugins/manifest-dev/skills/figure-out-team/SKILL.md
claude-plugins/manifest-dev/skills/figure-out/SKILL.md
claude-plugins/manifest-dev/skills/init-context/SKILL.md
claude-plugins/manifest-dev/skills/just-auto/SKILL.md
claude-plugins/manifest-dev/skills/next-ticket/SKILL.md
claude-plugins/manifest-dev/skills/poll-slack/SKILL.md
claude-plugins/manifest-dev/skills/review-writing/SKILL.md
claude-plugins/manifest-dev/skills/run-ticket/SKILL.md
claude-plugins/manifest-dev/skills/sweep-tickets/SKILL.md
claude-plugins/manifest-dev/skills/ticket-up/SKILL.md
claude-plugins/PLUGIN_TEMPLATE/skills/example/SKILL.md
claude-plugins/manifest-dev-tools/skills/teach-me/SKILL.md
claude-plugins/manifest-dev/skills/chat-surface/SKILL.md
claude-plugins/manifest-dev/skills/review-code/SKILL.md

Metadata

Files
0
Version
2ac487e
Hash
46997caf
Indexed
2026-08-20 08:56

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-25 11:40
浙ICP备14020137号-1 $방문자$