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。
搜索与研究

ideate

Generates, stress-tests, and evolves ideas for a stated problem with research-grounded divergent/convergent loops — persona generators, independent judges, recombination — at quick or deep depth. Triggers on "brainstorm", "give me ideas", "ideate on", "what could we build", "/ideate".

mthines · 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 mthines/agent-skills --skill ideate

技能说明


name: ideate description: > Generates, stress-tests, and evolves ideas for a stated problem with research-grounded divergent/convergent loops — persona generators, independent judges, recombination — at quick or deep depth. Triggers on "brainstorm", "give me ideas", "ideate on", "what could we build", "/ideate". disable-model-invocation: false argument-hint: '[quick|deep] [--n ] [--no-framing] []' license: MIT metadata: author: mthines version: '1.1.0' workflow_type: orchestrator tags: - ideation - brainstorming - divergent-thinking - idea-evaluation - creativity - agent-loops - confidence-gate - innovation

Ideate

Turns a problem statement into a small set of validated, evolved ideas by simulating a nominal group of independent generators, scoring with independent judges, and breeding the winners — instead of asking one context for a list and polishing it.

This SKILL.md is a thin index. Phase procedures live in rules/*.md and load on demand. The evidence behind every numerical default lives in references/ideation-research.md — section references below (§) point there, and its defaults tables flag which numbers are study values vs the skill's own operationalizations.

Contents


Mode Detection

Parse $ARGUMENTS:

ModeDefaultTrigger
quickquick token, or auto-triage says small.
deepdeep token, or auto-triage says open-ended.
autoyesNo mode token — run the depth triage table below.
FlagDefaultMeaning
--n <count>unsetOptional cap on the Lead-finalists list. Unset by default — the finalist count is emergent from the quality bar (see idea-scoring.md § Selection rules). --n only narrows; it never manufactures finalists the bar did not admit.
--no-framingoffSkip Phase 1 (problem is already well-framed).

Everything else in $ARGUMENTS is the problem statement. If it is missing, ask for it — never ideate on a guessed problem.

Depth triage (auto mode)

First match wins:

#SignalDepth
1User asks for thorough / extensive / "really new" ideas, or the problem combines ≥ 2 domains ("X meets Y").deep
2Outcome is a product, business, strategy, or roadmap decision.deep
3Problem is a local decision: naming, small feature shape, workaround, single component.quick
4User is mid-conversation and wants options fast ("any ideas?", "what do you think?").quick
5Unsure.quick, and name the escalation path: "run /ideate deep <problem> for the full pipeline".

Cost expectation: a deep run with a typical 2–4-idea finalist band dispatches ~17 subagents (2 bursts × 5 generators, 1 pool judge, 1 breeder, 1 variant judge, 3 panel judges, 1 pre-mortem) — prefer quick for casual or budget-sensitive asks. A richer pool that admits more finalists adds only panel-judge cost, not generation cost.


Workflow

PhaseNameRule fileGate
0Intake & triage(inline below)Problem restated in one sentence; success criterion named; depth chosen; lessons read.
1Frame(inline below)3–5 "How Might We" framings at different widths; one selected and logged.
2Divergerules/divergence.mdPool ≥ 12 (quick) / ≥ 25 (deep) unique ideas; zero evaluation happened during generation.
3Scorerules/idea-scoring.mdEvery pooled idea scored on 4 independent axes by a non-generator judge.
4Evolverules/evolution-loop.md≤ 3 rounds; stopped on flat external scores, never on self-assessed improvement.
5Validaterules/idea-scoring.md § Finalist validationEvery finalist has an executability probe; confidence(analysis) ≥ 70 on the recommendation.
6Reporttemplates/ideation-report.mdReport emitted; finalist count reflects the quality bar; high-novelty wildcard included; "Ideas worth revisiting" filled; verdict question asked.
7Learnrules/self-improvement-loop.md
阅读完整来源 ↗