跳到正文
cccskills
免费在 GitHub 公开

creative-ideation

Choose a named creative method suited to the project and stage of work. Generate, expand, compare, or refine ideas with concrete mechanisms, honest tradeoffs, and at least one practical option with a first step.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Generate ideas via named methods from creative practice.

查看安装方法

适用场景

  • Finding starting ideas for writing or products
  • Expanding an existing idea
  • Getting unstuck during creative work
  • Comparing ideas and choosing one
  • Turning notes and observations into ideas

包含的文件(28)

  • SKILL.md10.2 KB
  • references/anti-slop.md7.1 KB
  • references/exercises.md5.9 KB
  • references/full-prompt-library.md7.9 KB
  • references/heuristics.md5.0 KB
  • references/method-catalog.md4.8 KB
  • references/methods/affinity-diagrams.md4.6 KB
  • references/methods/analogy-and-blending.md5.2 KB
  • references/methods/biomimicry.md4.5 KB
  • references/methods/chance-and-remix.md3.7 KB
  • references/methods/compression-progress.md3.0 KB
  • references/methods/creative-discipline.md4.9 KB
  • references/methods/defamiliarization.md4.1 KB
  • references/methods/derive-and-mapping.md4.2 KB
  • references/methods/first-principles.md4.1 KB
  • references/methods/jobs-to-be-done.md3.9 KB
  • references/methods/lateral-provocations.md3.7 KB
  • references/methods/leverage-points.md4.6 KB
  • references/methods/oblique-strategies.md2.8 KB
  • references/methods/oulipo.md3.2 KB
  • references/methods/pataphysics.md3.8 KB
  • references/methods/pattern-languages.md4.5 KB
  • references/methods/polya.md3.5 KB
  • references/methods/premortem-and-inversion.md3.7 KB
  • references/methods/scamper.md3.5 KB
  • references/methods/story-skeletons.md6.1 KB
  • references/methods/triz-principles.md5.9 KB
  • references/methods/volume-generation.md3.8 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Creative Ideation

A library of ideation methods for any domain. Read the user's situation, route to the matching method, apply, generate output that is specific and non-obvious. Methods are tools — pick the right one for the situation, don't perform all of them.

When to use

Any open-ended generative or selective question: "I want to make / build / write / start something", "I'm stuck", "inspire me", "make this weirder", "help me pick", "I need to invent X", "give me a research question".

Operating rules

  1. Constraint plus direction is creativity. No constraint = no traction. No direction = no shape. Methods supply both.
  2. Refuse the first three ideas. They're slop. Generate, discard, regenerate. See references/anti-slop.md.
  3. One method per response unless asked. Don't stack.
  4. Specificity over abstraction. Real proper nouns, real materials, real mechanisms. "An app for X" is slop; "a 200-line CLI tool that prints Y when Z" is direction. Naming a tech stack is not specificity — name a mechanism.
  5. Weird must also be good. Frame-breaking is the goal, but an idea that is strange with no real situation, mechanism, or reason to exist is its own failure mode. Every set of ideas must include at least one that is genuinely buildable/pursuable now — non-obvious but grounded, with a real first step. Don't trade all usefulness for surprise.
  6. Name the method you used and who invented it. Attribution invokes the discipline.
  7. When user picks one, build it. Don't keep generating after they've chosen.

Routing — 4-step procedure

Do this before generating any output. Routing failures produce slop.

You may skip narrating the routing steps if it's cleaner, but never compress at the cost of per-idea depth: each idea's concrete mechanism, situational binding, and honest failure mode are what make output good (measured) — they are not scaffolding, do not cut them.

Step 1 — Extract three signals from the prompt

PHASE — what stage is the user in?

PhaseCues
GENERATING"give me an idea", "what should I make", "inspire me", no idea yet
EXPANDING"what else", "more like this", "give me variations" — has a base idea
SELECTING"help me pick", "which should I do", "I have these options"
UNBLOCKING"I'm stuck", "blocked", "going in circles", "stale" — has material
SUBVERTING"make it weirder", "less obvious", "this is too safe"
REFINING"this is fine but missing something", "feels rough"
SYNTHESIZING"I have a pile of notes / interviews / observations"

DOMAIN — what is the user making/doing?

DomainCues
TEXTfiction, essay, poem, lyric, script, copy
OBJECTvisual art, music, sound, performance, installation, sculpture
ARTIFACTsoftware, hardware, mechanism, device
SYSTEMorg, civic, institution, ecology, community
SELFlife decision, career, personal practice
RESEARCHpaper, thesis, scholarly question
PRODUCTbusiness, market, service

SPECIFICITY — how much constraint is in the prompt?

LevelCues
NONE"I'm bored", "inspire me" — no domain, no project
DOMAIN"I want to write something" — knows the field, no project
PROJECT"I'm working on this specific X"
PROBLEM"I have this specific friction within X"

Step 2 — Apply overrides (highest priority, fire first)

Override rules beat the routing table:

  • Mood signal — user says "weird", "strange", "surprising", "less obvious", "more interesting" → references/methods/lateral-provocations.md or references/methods/pataphysics.md, regardless of domain.
  • User names a method — use it.
  • User asks for a method recommendation ("which method") → surface 2–3 candidates with one-line each, ask which to apply. Don't silently default.
  • High-slop terrain — "AI ideas", "startup ideas", "habit tracker", "productivity / wellness / fitness / food / travel app" → force references/methods/lateral-provocations.md or references/methods/pataphysics.md over the obvious method. Refuse the first 5 ideas, not 3.

Step 3 — Route by phase first, then domain

By phase (applies regardless of domain):

PhaseDefault route
GENERATING + SPECIFICITY=NONEreferences/full-prompt-library.md General section (constraint dispatch)
GENERATING + DOMAIN knownroute by domain (next table)
EXPANDINGreferences/methods/scamper.md
SELECTINGreferences/methods/premortem-and-inversion.md (or references/methods/compression-progress.md for upside)
UNBLOCKINGreferences/methods/oblique-strategies.md
SUBVERTINGreferences/methods/lateral-provocations.md (fallback references/methods/pataphysics.md)
REFINING (text)references/methods/defamiliarization.md
REFINING (other)references/methods/creative-discipline.md (Tharp's spine)
SYNTHESIZINGreferences/methods/affinity-diagrams.md
Volume needed fastreferences/methods/volume-generation.md

By domain (when GENERATING with DOMAIN known):

DomainDefault route
TEXT — formal / poetryreferences/methods/oulipo.md
TEXT — narrativereferences/methods/story-skeletons.md
TEXT — has source material to remixreferences/methods/chance-and-remix.md
OBJECT (music, visual, performance)references/methods/oblique-strategies.md
OBJECT — physical maker / wants a starting constraintreferences/full-prompt-library.md Physical / object section
ARTIFACT — wants a starting constraintreferences/full-prompt-library.md Software / artifact section
ARTIFACT — engineering invention with parameter conflictreferences/methods/triz-principles.md
ARTIFACT — software architecturereferences/methods/pattern-languages.md
ARTIFACT — has natural-system analogreferences/methods/biomimicry.md
ARTIFACT — accumulated assumptions to questionreferences/methods/first-principles.md
SYSTEM (civic, org, institutional)references/methods/leverage-points.md
SYSTEM — collective / participatoryreferences/full-prompt-library.md Social / collective section
SELF (life, career, what-to-study)references/methods/derive-and-mapping.md
RESEARCH — picking a questionreferences/methods/compression-progress.md
RESEARCH — attacking a known problemreferences/methods/polya.md
PRODUCT (business, service)references/methods/jobs-to-be-done.md
Need to break a frame / find analogyreferences/methods/analogy-and-blending.md

Step 4 — Handle ambiguity and contradiction

  • Multiple paths plausible → pick the one closest to the user's actual phrasing. Don't pick the most interesting method to seem sophisticated.
  • Genuinely ambiguous → ask ONE clarifying question, don't silently guess. Examples: "Are you generating ideas or picking between ones you have?" / "Is this for fiction, essay, or something else?"
  • Signals contradict (e.g., "weird startup ideas" → product domain + weird mood) → stack two methods explicitly. State what you're doing: "Using jobs-to-be-done for the product framing + lateral-provocations to break the obvious shape."
  • No match → constraint dispatch (references/full-prompt-library.md) is the safe fallback.
  • Same question asked again → switch methods. Variation in method = variation in idea distribution.

Anti-default check (run before generating)

  • About to write "Here are 5 ideas:" or a bare numbered list? → STOP. Pick a method first.
  • About to default to generic LLM-mode brainstorming? → STOP. Pick a path above.
  • Output looks like what an unrouted LLM would produce? → routing failed, redo.

The default LLM mode is exactly what this skill exists to displace. If you generate without routing, you've defeated the skill.

For deeper edge cases (mood signals, stacking, anti-patterns) see references/heuristics.md.

Output format

For the constraint-dispatch default path:

## Constraint: [Name] — from [Source]
> [The constraint, one sentence]

### Ideas

1. **[One-line pitch]**
   [2-3 sentences — what specifically is made, why it's interesting]
   ⏱ [weekend/week/month]  •  🔧 [stack/medium/materials]

2. ...
3. ...

For other methods, use the format the method specifies (TRIZ produces a contradiction analysis; OuLiPo produces constrained text; Oblique Strategies produces a single applied card → next move). Don't force every method into the constraint template.

Every idea set, regardless of method:

  • Name the method used. On slop terrain, name the obvious ideas you refused.
  • Give each idea its concrete mechanism and its honest failure mode / tradeoff / who-it's-for. This depth is what makes ideas land — measured, not decorative.
  • Mark at least one idea as the grounded one — buildable/pursuable now, non-obvious but with a real first step. The others can run further toward the strange; this one has to be genuinely doable. Don't let the whole set be weird-but-impractical.

File map

  • references/full-prompt-library.md — constraint library, sectioned by domain (General, Software, Physical, Social, Lists). Default path for SPECIFICITY=NONE.
  • references/method-catalog.md — one-line summary + when-to-use per method
  • references/heuristics.md — extended decision tree for edge cases
  • references/anti-slop.md — anti-slop rules; apply to every output
  • references/exercises.md — time-boxed exercises (5min / 30min / 1hr / day / week)
  • references/methods/ — 22 named methods, one file each, load only the one you're using

Attribution

Constraint-dispatch core adapted from wttdotm.com/prompts.html. Methods drawn from primary sources cited in each method file.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

1password

免费

Set up the 1Password CLI and use stored passwords or API keys in commands and configuration templates. Choose an authentication method, retrieve secret references, and pass credentials to processes through environment variables.

中文简介正在准备中。当前显示英语简介。

  • Installing and configuring the 1Password CLI
  • Running commands with stored API keys
  • Filling configuration templates with stored secrets
NousResearch/hermes-agent25.5万2026年10月18日 更新

Build an Excel workbook linking the income statement, balance sheet, and cash flow statement. Populate historical figures, create formula-based forecasts, compare scenarios, and check that balances and cash totals agree across all three statements.

中文简介正在准备中。当前显示英语简介。

  • Populating a financial model template with historical data
  • Building linked forecasts across three financial statements
  • Comparing base, upside, and downside scenarios
NousResearch/hermes-agent25.5万2026年10月18日 更新

Adapt existing PyTorch training scripts to use multiple GPUs or machines with limited code changes. The skill guides configuration, launch commands, mixed precision, which uses lower-precision numbers, and DeepSpeed or FSDP settings for distributing training work and memory.

中文简介正在准备中。当前显示英语简介。

  • Move a single-GPU training script to multiple GPUs
  • Configure mixed precision training
  • Set up DeepSpeed or FSDP to reduce memory use
NousResearch/hermes-agent25.5万2026年10月18日 更新

Configure Hermes to run AI models through Actual Computer on your own hardware. Set up either the hosted relay or a local connection, select models, verify responses, and troubleshoot request errors or empty output.

中文简介正在准备中。当前显示英语简介。

  • Connecting Hermes with an Actual inference key
  • Running models through a local Actual daemon
  • Downloading and loading local models
NousResearch/hermes-agent25.5万2026年10月18日 更新

Test an app from the perspective of a frustrated, less technical user. Find confusing steps and barriers, separate actionable usability problems from personal complaints, and produce screenshots, suggested fixes, and prioritized tickets.

中文简介正在准备中。当前显示英语简介。

  • Reviewing usability before a launch or demo
  • Checking the experience of a new user
  • Finding friction in signup and subscription flows
NousResearch/hermes-agent25.5万2026年10月18日 更新

Resolve Git merge conflicts between two agents by comparing both changes and their stated goals. Combine compatible work, explain choices where designs differ, and verify the merged result with project builds or tests.

中文简介正在准备中。当前显示英语简介。

  • Resolving conflicts between branches edited by two agents
  • Integrating changes from parallel worktrees
  • Reviewing reasons for conflicting design choices
NousResearch/hermes-agent25.5万2026年10月18日 更新

查看 NousResearch 的全部技能

报告此技能的问题