Agent skill

Ideate

by athola in athola/claude-night-market

Generate diverse solution candidates with category-spanning ideation methods and rotation.

MITAuto-check passedAgent Workflows

Install Ideate

skills CLI
$ npx skills add athola/claude-night-market --skill ideate -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install athola/claude-night-market ideate --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/tome/skills/ideate .claude/skills/ideate && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ideate
GitHub stars
342
Used in
1 other repo
Token cost
~1.4k tokens
SKILL.md length
713 words
Files
1
Skills in repo
159
Repo updated
First seen
Licence
MIT

At a glance

Generate diverse solution candidates with category-spanning ideation methods and rotation.

  • Works in 6 steps: Pick how many approaches you want (3 to… → Select methods spanning distinct… → Apply each method's reasoning prompt to… → …
  • Stuck on a design
  • SKILL.md covers When NOT To Use, The one design rule, Catalog and Workflow, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ideate is an agent skill from athola/claude-night-market. Generate diverse solution candidates with category-spanning ideation methods and rotation. Use when stuck on a design or fighting repetitive LLM output.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Brainstorming. The repository describes itself as: 23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context… The licence is MIT.

When your agent uses it

  • Stuck on a design
  • Fighting repetitive LLM output

Example prompts

  • “/ideate”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Pick how many approaches you want (3 to 5 is the useful range).
  2. Select methods spanning distinct categories
  3. Apply each method's reasoning prompt to the problem. Generate ideas
  4. On a second pass, rotate: select_methods(n, exclude=used_ids) or
  5. Score the candidates with score_idea (weighted criteria per
  6. Report the final set with rationale and scores.

What it can do on your machine

Read from SKILL.md and the folder at commit 9f3eb00. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ideate loads about 1.4k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 713 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~40
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from athola/claude-night-market at commit 9f3eb00, republished under its MIT licence (© athola). 713 words, ~1,441 tokens.

Download SKILL.mdSave it as .claude/skills/ideate/SKILL.md (or your agent's skills folder).
name
ideate
description
Generate diverse solution candidates with category-spanning ideation methods and rotation. Use when stuck on a design or fighting repetitive LLM output.
category
research
tags
ideation, creativity, diversity, mode-collapse, problem-solving
estimated_tokens
500
model_hint
standard

Ideation: Diverse Methods With Rotation

Diversity is a selection problem, not a volume problem.

Generating ten ideas from one mental frame yields ten variations of the same idea. The fix is to ideate from different categories of method, then rotate methods across passes so the next round does not repeat the last. This is the documented lever against LLM mode collapse, not a brainstorming ritual.

When NOT To Use

  • Surveying what already exists (use tome:research)
  • Cross-domain analogies specifically (use tome:triz)

The one design rule

Structure the reasoning, not the output.

"The Price of Format" (arXiv 2505.18949) found that rigid output templates collapse output diversity, while reasoning scaffolds raise it. So each method hands you a reasoning prompt. Do not force the ideas into a fixed schema while generating; impose structure only when reporting the final set.

Catalog

Nine methods that port to technical problem-solving, each tagged with an honest evidence grade (see Sources below):

MethodCategoryEvidence
SCAMPERtransformationweak
SIT task unificationtransformationmixed
Morphological analysis (Zwicky)decompositionmixed
SIT subtractiondecompositionmixed
Cross-domain analogy (TRIZ, Synectics)analogicalmixed
Inversion (reverse brainstorming, pre-mortem)inversionanecdotal
Constraint provocationperturbationanecdotal
Devil's advocacyadversarialmixed
Multiple working hypotheseshypothesismixed

The grades are deliberately conservative. Individual-method evidence is thin; the value is the diverse-selection-plus-rotation pattern, not any single method. For the structured analogical form, use Skill(tome:triz). For finding an implied-but-empty cell in a concept space, map the field and its hidden optimization axis first, then apply generation methods to fill the gap.

Workflow

  1. Pick how many approaches you want (3 to 5 is the useful range).
  2. Select methods spanning distinct categories: select_methods(n) from tome.channels.ideation returns methods from different categories by construction.
  3. Apply each method's reasoning prompt to the problem. Generate ideas freely; do not normalize them into a schema yet.
  4. On a second pass, rotate: select_methods(n, exclude=used_ids) or rotation_plan(passes, n_per_pass) so no method repeats until the catalog is exhausted.
  5. Score the candidates with score_idea (weighted criteria per Skill(leyline:evaluation-framework)). Novelty claimed without evidence is capped, so "novel" must be earned, not asserted.
  6. Report the final set with rationale and scores.

Scoring

score_idea(scores, novelty_evidence=False) applies weighted criteria (novelty 0.25, fit 0.20, feasibility 0.20, simplicity 0.15, reversibility 0.10, impact 0.10) and an anti-inflation rule: a novelty score of 8 or higher without supporting evidence is capped to 7. Pass novelty_evidence=True only when you have checked for prior art and found the idea genuinely new.

Show full SKILL.md (307 more words)Show less

Anti-goals

  • Do not generate many ideas from one method and call it diverse.
  • Do not impose a rigid output schema during generation; it collapses diversity.
  • Do not present anecdotal-evidence methods as proven; cite the grade.
  • Do not import the full 20-method bundle; the catalog is curated on purpose.

Sources

The diversity rationale and method evidence grades draw on:

  • Verbalized Sampling (arXiv 2510.01171): distributional prompting for 1.6 to 2.1x diversity gains, training-free.
  • The Price of Format (arXiv 2505.18949): rigid output schemas collapse generation diversity. This is the basis for the reasoning-prompt-not-schema rule above.
  • Barriers to Diversity in LLM-Generated Ideas (arXiv 2602.20408): chain-of-thought reduces fixation; diverse personas restore collective diversity.
  • The originality and SCAMPER / morphological-analysis education literature underpins the per-method evidence grades.
  • Innovation Paradox (Shi et al., Design Science 2024): patent analysis of 4M+ concepts found originality declined 31% from 1981-2016 as concept space expanded. Cognitive burden drives clustering near familiar terrain rather than the edge.
  • Devil's advocacy: Schwenk, OBHDP 47(1), 1990, a meta-analysis in which devil's advocacy beat the expert-plan approach. Graded mixed because one model arguing both sides is weaker than two people.
  • Multiple working hypotheses: Lord, Lepper and Preston, JPSP 47(6), 1984, where considering the opposite corrected biased judgment. The prompt stays light on purpose: in Dhami, Belton and Mandel, Applied Cognitive Psychology 33(6), 2019, the full hypothesis matrix (ACH) did not improve analyst accuracy.

Methods surveyed and not catalogued, with grades, are in ADR-0024.

Exit Criteria

  • At least 3 candidate approaches were generated, each from a method in a distinct category (verifiable: the methods used span >= 3 categories from list_categories()).
  • A second pass, if run, used exclude or rotation_plan so no method repeated before the catalog was exhausted.
  • Each candidate carries a weighted score from score_idea, with any uncapped novelty backed by an explicit prior-art check.
  • The final report structures the output; generation did not.

© athola, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/tome/skills/ideate of athola/claude-night-market.

Open the folder on GitHubat commit 9f3eb00

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in athola/claude-night-market, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Ideate next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ideate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ideate this skillathola/claude-night-market3421 repos~1.4kAutomated safety check: PassMIT
Brainstormingxpinjection/test-driven-spring-boot11254 repos~2.6kAutomated safety check: PassMIT
LLM Councilgcpdev/llm-council-skill4611 repos~1kAutomated safety check: NotesMIT
Typesafe AIOpenAgentsInc/openagents4559 repos~2.5kAutomated safety check: PassMIT
Yao Meta Skillyaojingang/yao-meta-skill2.7k—~768Automated safety check: PassMIT
Trellis StartROYIANS/foliq-print-template-designer1356 repos~646Automated safety check: PassMIT

Similar skills

  • Brainstorming

    xpinjection/test-driven-spring-boot

    You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.

    112 GitHub starsUsed in 54 repos~2.6k tokens
    Agent WorkflowsAuto-check passed
  • LLM Council

    gcpdev/llm-council-skill

    Multi-LLM collaborative brainstorming and planning. An agent skill from gcpdev/llm-council-skill.

    461 GitHub starsUsed in 1 repo~1k tokens
    Agent WorkflowsAuto-check: notes
  • Typesafe AI

    OpenAgentsInc/openagents

    Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives.

    455 GitHub starsUsed in 9 repos~2.5k tokens
    Agent WorkflowsAuto-check passed
  • Yao Meta Skill

    yaojingang/yao-meta-skill

    Create, improve, or evaluate an existing skill from workflows, prompts, SOPs, scripts.

    2.7k GitHub stars~768 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Trellis Start

    ROYIANS/foliq-print-template-designer

    Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/.

    135 GitHub starsUsed in 6 repos~646 tokens
    Agent WorkflowsAuto-check passed
  • Brainstorming Before Building

    jnMetaCode/superpowers-zh

    Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate.

    8.3k GitHub stars~1.8k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed

More from athola/claude-night-market

All 159 skills in this repo
  • Night Market Diagnostics Toolkit

    athola/claude-night-market

    Run and interpret repo diagnostic scripts (ratchets, validators, token stats).

    342 GitHub stars~3.4k tokensUpdated 2 days ago
    Auto-check passed
  • Skills Eval

    athola/claude-night-market

    Evaluate Claude skill quality through auditing. An agent skill from athola/claude-night-market.

    342 GitHub stars~1.6k tokensUpdated 2 days ago
    Auto-check passed
  • Agent Teams

    athola/claude-night-market

    Coordinates Claude agent teams via filesystem protocol. An agent skill from athola/claude-night-market.

    342 GitHub stars~2.5k tokensUpdated 2 days ago
    Auto-check passed
  • Delegation Core

    athola/claude-night-market

    Delegates execution to eight CLIs (Gemini, Qwen, MiniMax, GLM, Muse, Codex, OpenCode, Glimmer).

    342 GitHub stars~2.5k tokensUpdated 2 days ago
    Auto-check passed
  • Elegant Code

    athola/claude-night-market

    Guide minimal code via a decision ladder with full safety, edge, and negative-case coverage.

    342 GitHub stars~2.1k tokensUpdated 2 days ago
    Auto-check passed
  • Skill Library Mission

    athola/claude-night-market

    Build a project skill library in .claude/skills/ via discovery, parallel authoring, and review.

    342 GitHub stars~1.6k tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Ideate

What does Ideate do?

Generate diverse solution candidates with category-spanning ideation methods and rotation. Ideate is an agent skill from athola/claude-night-market. Generate diverse solution candidates with category-spanning ideation methods and rotation.

When should I use Ideate?

Ideate fits situations like: stuck on a design; fighting repetitive LLM output.

How do I install Ideate in Claude Code?

Run `npx skills add athola/claude-night-market --skill ideate -a claude-code`. Or copy the skill folder (plugins/tome/skills/ideate in athola/claude-night-market) into .claude/skills/ideate in your project. Claude Code loads it when a task matches its description.

How do I install Ideate in Codex?

Run `npx skills add athola/claude-night-market --skill ideate -a codex`. Or copy the skill folder (plugins/tome/skills/ideate in athola/claude-night-market) into .agents/skills/ideate in your project. Codex loads it when a task matches its description.

Can I use Ideate in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add athola/claude-night-market --skill ideate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ideate, .gemini/skills/ideate, .github/skills/ideate and .opencode/skills/ideate in your project.

What does Ideate need to run?

SKILL.md names no scripts, command-line tools or credentials: Ideate is instructions for the agent only.

Does Ideate access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ideate safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ideate use?

Ideate is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ideate use?

About 1.4k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ideate?

Skills that share tags, products or a category with Ideate: Brainstorming (xpinjection/test-driven-spring-boot, 112 stars), LLM Council (gcpdev/llm-council-skill, 461 stars), Typesafe AI (OpenAgentsInc/openagents, 455 stars) and Yao Meta Skill (yaojingang/yao-meta-skill, 2.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ideate?

athola (a GitHub user) maintains it in athola/claude-night-market, which has 342 GitHub stars. The repository holds 159 skills in this directory. The repository was last updated on October 6, 2026.

Source: athola/claude-night-market on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.