just-auto

GitHub

自动化端到端任务执行技能,自动解析目标、生成清单并自主完成开发,无需人工审批。适用于从想法到交付的全流程自动化场景。

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

Trigger Scenarios

用户要求直接构建或自动化执行任务 希望从想法端到端完成而不经过审批节点

Install

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

Non-standard path

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

Use without installing

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

指定 Agent (Claude Code)

npx skills add doodledood/manifest-dev --skill just-auto -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-auto",
    "description": "Goal-based autonomous chain: figures out the task, encodes a Manifest, and pursues it end-to-end with full autonomy and minimal process. Use when the user asks to just build it, just auto it, run end-to-end goal-based, or go from idea to done without approval gates.",
    "argument-hint": "<task>",
    "user-invocable": true
}

Run the full flow for the given task — stated as an argument or inferable from the conversation; with neither, halt with usage.

Before starting, arm the completion backstop. If an active goal's completion condition already covers this task's outcome, continue under it. Otherwise, if the harness provides a goal-setting, continuation, or durable-completion-condition capability, set this goal, with <task> replaced by a one-line statement of the task: "For the task : shared understanding is reached — where figure-out runs, a full-anatomy Read checkpoint is completed before define runs: every load-bearing branch pressed, independent re-derivation run or explicitly unavailable, the rival set no longer moving; a missing or weak Read checkpoint is a defect to repair before define, not a terminal failure after gates pass — a Manifest is written from it, every Acceptance Criterion and Global Invariant in that Manifest holds with evidence from the artifacts they name, and completion has been reported. The Manifest, once written, is canonical and read-only. Record compact checkpoint notes as work proceeds — what changed, what was verified, what remains, blockers. Record the Manifest's path in a checkpoint note as soon as it is written. 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.

Then: if the conversation lacks shared understanding of the task, first invoke the manifest-dev:figure-out skill with the task and --autonomous. Invoke the manifest-dev:define skill with --autonomous. Invoke the manifest-dev:just-do skill with the Manifest path define reports, noting that the chain goal already owns the completion backstop, so just-do continues under it rather than arming its own. If define reports no Manifest path, stop and report.

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-do/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
0496ad63
Indexed
2026-08-20 08:56

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-25 08:34
浙ICP备14020137号-1 $방문자$