跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
设计与 UI

define-done

Pin a measurable, outcome-based Definition of Done for a diamond — a behaviour-change that creates value, not a build-list. Problem-first Socratic sequence; writes definition_of_done to the diamond at birth or retrofits it when missing.

haabe · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add haabe/mycelium --skill define-done

技能说明


name: define-done description: "Pin a measurable, outcome-based Definition of Done for a diamond — a behaviour-change that creates value, not a build-list. Problem-first Socratic sequence; writes definition_of_done to the diamond at birth or retrofits it when missing." metadata: instruction_budget: "48" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin install mycelium@haabe-mycelium."

Define Done

Pin an explicit, outcome-based Definition of Done for a diamond. "Done" is a change in human behaviour that creates value (Seiden), not "the feature shipped" — you're done when it ships and has the intended impact (Amplitude). The diamond's implicit done defaults to the harshest, least-controllable bar ("a user shipped a product"), which is both wrong for validating purpose and a demotivation engine. This skill makes the bar explicit, measurable, and pre-committed.

This is distinct from /mycelium:definition-of-done (the per-feature agile quality checklist run at Deliver→Complete). This skill sets the outcome bar a whole diamond is judged against; that one verifies a feature meets quality criteria. Both can apply.

When to use

  • At diamond birth — /mycelium:interview (L0) and child-diamond spawn (/mycelium:diamond-progress) call this before a diamond is "live."
  • Retrofit — when /mycelium:canvas-health, /mycelium:diamond-assess, or the SessionStart nudge flags a diamond with no definition_of_done.
  • Never silent-fill. The question is what produces a real bar ("fits, not ships"); a back-filled field is theatre.

Preflight: Read target file before any Write/Edit

Hard rule. The definition_of_done field lives on the diamond in .claude/diamonds/active.yml. Before Write/Edit on it, use the Read tool on that file this session (cat/head/grep via Bash do NOT satisfy Claude Code's check). Edit with limit:1 suffices for a partial update; full Read before a Write. See CLAUDE.md Canvas writes — Read before Write.

The sequence (Socratic, problem-first)

Ask these in order. The teaching is in the sequencing (problem → signal → maybe-number → kill) and the good/bad contrast — not a help doc. Reject build-lists at step 1; that is the whole point.

1. "When this is done, what's different — and for WHOM?" → outcome + whose behaviour. Lead with the problem and the person, never the deliverable (Cagan: "most measurement problems are clarity problems").

  • ✗ "the onboarding flow ships." (a build-list — reject it)
  • ✓ "non-fluent users get through the brief without hitting the vocabulary wall."

2. "What's the ONE thing you'd SEE them DO that proves it?" → signal (One Metric That Matters — one, not many).

  • ✗ "it feels better."
  • ✓ "they came back for a second session."

3. (optional) "Is there a point where it's ENOUGH?" → threshold, only if one genuinely fits. A number is optional, not mandatory — directional outcomes are legitimate. When you do set one, pair it with a qualitative guard ("3 warm bodies who bounce ≠ done") so it can't be gamed (Goodhart).

4. Pre-mortem for the kill-criterion. Ask in the past tense: "It's [review date]. This diamond failed. What happened?" (premortem finds ~30% more real failure reasons than "might it fail?" — Klein). From the answer derive a concrete state + date that means kill, not finish:

  • state — an objective benchmark that means this goal is wrong.
  • date — the review date by which the state must hold. Pre-commit BOTH, before the data (anti-HARKing). Invalidation-with-evidence at that date is a legitimate "done" — routed through /mycelium:diamond-progress kill + dogfood-mode, not silently declared.

Per-scale "done" + lead/lag defaults

Default kind by altitude: lower/activity scales take leading measures (predictive, team-influenceable); higher value-validation scales take lagging (already realized). Direct most attention to lead measures (4DX).

Scale"Done" meanskind default
L0 Purposepeople keep choosing it ("fits, not ships")lagging
L1 Strategya where-to-play bet validatedlagging
L2 Opportunitya real user need confirmed worth solvingmixed
L3 Solutionthe solution actually solves it for users (not just built)leading
L4 Deliveryshipped AND has the intended impactleading
L5 Marketadoption / business outcome at scalelagging

Build-mode gate — refuse build-to-earn during build-to-learn

The per-scale table isn't only a kind default — it encodes the build mode (Patton/Cagan). This skill enforces it at diamond birth (agent-adjudicated), with a /canvas-health lint backstop that fires unconditionally (step 8c there). This is the mechanism behind philosophy.md's "the framework refuses to let the agent build-to-earn during a build-to-learn phase — that refusal is the gate."

  • Build-to-LEARN (a diamond whose terminal purpose is to learn — scales L0 Purpose → L3 Solution): its DoD outcome must be a learning / validation result ("the bet is validated", "the need is confirmed worth solving", "the solution actually solves it for users").
  • Build-to-EARN (terminal purpose is to ship value — L4 Delivery, L5 Market): its DoD outcome is a shipped-value / adoption result ("shipped AND the intended impact landed").

The discriminator is NOT the word "ship" — it is what the done-bar IS. Discovery legitimately ships to learn: a fake-door test, wizard-of-oz, a disposable prototype shipped to a few opted-in users. Those are build-to-LEARN — the ship is the method, the learning it yields is the done-bar ("40% of the 5 opted-i

阅读完整来源 ↗