done

GitHub

用于 /do 工作流结束时的完成标记技能。接收验收标准与全局不变量的通过证据,生成包含构建内容、关键变更、自主决策及遗留债务的纯文本总结报告。

claude-plugins/manifest-dev/skills/done/SKILL.md doodledood/manifest-dev

触发场景

/do 工作流需要输出完成摘要时 所有验收标准和全局不变量均获得 PASS 证据后

安装

npx skills add doodledood/manifest-dev --skill done -g -y
更多选项

非标准路径

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

不安装直接使用

npx skills use doodledood/manifest-dev@done

指定 Agent (Claude Code)

npx skills add doodledood/manifest-dev --skill done -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": "done",
    "description": "Completion marker for the \/do workflow. Outputs a plain-prose summary of what was built. Called by \/do after every Acceptance Criterion and Global Invariant has fresh PASS evidence, when the manifest is complete, all criteria pass, or the workflow needs to wrap up with a completion summary.",
    "user-invocable": false
}

Receive the manifest path from /do, along with the basis on which each Acceptance Criterion and Global Invariant was judged to hold.

Include material autonomous decisions and their rationale, including any Appetite revision and why its benefit justified the added complexity and maintenance. Carry any drafted Taste entry /do supplies verbatim, with its question for the user's yes.

The user's call. A decision is the user's call when two careful people with the same evidence could reasonably decide it differently, and the difference would matter to the user. Test each material decision against that sentence; your own confidence does not settle it. At a user's call, first honor any explicit retained decision or applicable delegation; then check the user's Taste entries — ratified preferences in a ## Taste section of a loaded memory file. Follow an entry only where it clearly bears: it speaks to this kind of call, and following it would change the choice. A general lean that would tilt almost any call, such as less effort or lower cost, does not bear on its own. Otherwise decide on the evidence. Wherever decisions are reported, list first each decision record the run reopened, with the reason set aside and what reversing would cost, then the user's calls, each with the alternative not taken and what decided it — the entry followed, or that no entry applied.

Emit a completion summary in plain prose: what was built, the key changes (files, behavioral effect — not just paths), any Process Guidance departed from and any deviation from the Initial Approach or the Deliverable order with why, anything notable about how the work landed. State the basis for each gate exactly as /do supplied it. Name the debt /do hands over, item by item as supplied, offering ticket-up for any the user wants worked, and link the exercise evidence the surface kept. Name each offer flagged for a person rather than accepted, such as a setup-project update or a ticket-up handoff, whether the run flagged it or the Manifest's ASM-* entries carry it. Name each decision record written with an agent as its decider. For each offer and record, say what accepting or reviewing it would change. Name the issues fixed on the way, and any test removed as useless or tautological with why. The debt /do hands over is only what the run could not fix: an issue whose fix is a project of its own — a design decision someone should weigh, a migration or rollout beyond the repository's code, or a review that would bury the change — named with why; what needs access, authority or a decision a person retains, such as an ask-first run owed; an unrelated issue the project's own rules keep out of the pull request; and a new suppression. Never list a finding below a gate's bar or a pre-existing issue the run fixed on the way as handed over. Name any gate whose bar the run read as suspect without a user to ask, with what the rounds beneath it turned up. Name all of these even when an execution log already records them; a reader of the summary should not have to open the log to learn which advisory guidance was set aside or how the plan moved. Adapt detail to the task's complexity — a small fix gets a couple of sentences; a multi-deliverable refactor gets a paragraph or two. Multi-repo manifests: a single summary covers the whole manifest, naming which repos' deliverables were verified.

Reachable only after every Acceptance Criterion and Global Invariant holds on fresh evidence, with none left unverified, failing, stale, actionably blocked, or pending escalation. End with the mandatory trailing line — directive, not observational, because the manifest stays the source of truth post-completion:

If the next message describes a change or new requirement (not a pure question), invoke /define <this-manifest-path> to amend. Pure questions are answered inline.

版本历史

  • 927bf32 当前 2026-11-03 11:10

    新增记录被搁置的决定记录及其撤销成本;明确仅移交无法修复的债务(如独立项目、权限问题),不再列出已修复或低于门槛的问题;细化了用户决策和代理决策的记录要求。

  • 5d3a066 2026-10-19 18:05

    新增对用户调用(User's call)的判定逻辑与Taste偏好检查;增加对代理决策记录、Suspect门限及多仓库验证范围的详细说明要求。

  • d76241f 2026-09-28 09:22

    新增记录低于阈值的发现项和未修复的既有问题,而非直接修复,并在摘要中向用户移交这些事项。

  • 3fc997a 2026-09-22 22:25

    重构为单技能结构;移除对验证模式等参数的显式依赖,简化输入处理。

  • 2ac487e 2026-08-20 08:56

同 Skill 集合

.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/eli5/SKILL.md
claude-plugins/manifest-dev-tools/skills/handoff/SKILL.md
claude-plugins/manifest-dev-tools/skills/manifest-to-goal/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-holistic/SKILL.md
claude-plugins/manifest-dev-tools/skills/review-pr-judgment/SKILL.md
claude-plugins/manifest-dev-tools/skills/review-pr-thread-verify/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-tools/skills/write-goal/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/design/SKILL.md
claude-plugins/manifest-dev/skills/do/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/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-design/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/manifest-dev-help/SKILL.md
claude-plugins/manifest-dev/skills/orchestrate/SKILL.md
claude-plugins/manifest-dev/skills/review-code/SKILL.md
claude-plugins/manifest-dev/skills/setup-project/SKILL.md

元信息

文件数
0
版本
927bf32
Hash
35b1a42e
收录时间
2026-08-20 08:56

首页 - Wiki
Copyright © 2011-2026 iteam. Current version is 2.156.0. UTC+08:00, 2026-11-06 09:44
浙ICP备14020137号-1