creative-ideation
Use when brainstorming, exploring options, unsticking an idea, making it less generic, or choosing among possibilities.
Skill by supplefrog
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/supplefrog-creative-ideation
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/creative-ideation
What's inside
- Skill name
creative-ideation- Description
- Use when brainstorming, exploring options, unsticking an idea, making it less generic, or choosing among possibilities. Apply one fitting creative method without methodology theater.
- License
- MIT
- Instructions
- 51 lines in SKILL.md · view on GitHub
Files (28)
- SKILL.md
- anti-slop.md · references/
- exercises.md · references/
- full-prompt-library.md · references/
- heuristics.md · references/
- method-catalog.md · references/
- affinity-diagrams.md · references/methods/
- analogy-and-blending.md · references/methods/
- biomimicry.md · references/methods/
- chance-and-remix.md · references/methods/
- compression-progress.md · references/methods/
- creative-discipline.md · references/methods/
- defamiliarization.md · references/methods/
- derive-and-mapping.md · references/methods/
- first-principles.md · references/methods/
- jobs-to-be-done.md · references/methods/
- lateral-provocations.md · references/methods/
- leverage-points.md · references/methods/
- oblique-strategies.md · references/methods/
- oulipo.md · references/methods/
- pataphysics.md · references/methods/
- pattern-languages.md · references/methods/
- polya.md · references/methods/
- premortem-and-inversion.md · references/methods/
- scamper.md · references/methods/
- story-skeletons.md · references/methods/
- triz-principles.md · references/methods/
- volume-generation.md · references/methods/
SKILL.md (first lines)
# Creative Ideation Help the user reach stronger, less obvious ideas while keeping the conversation natural. Use a named method as an internal tool, not as a ceremony the user must manage. ## Trigger and boundary Use for brainstorming, invention, alternatives, variations, creative blocks, “this feels generic,” selecting among ideas, research-question generation, or early product/project direction. Do not use merely because ordinary implementation involves design choices. Once the user has selected a direction and asks to build it, hand off to the relevant production skill. ## Workflow 1. Identify the current need: generate, expand, unblock, subvert, refine, synthesize, or select. 2. Pick the narrowest useful method from the routing below. Load that method’s reference file before applying it. Use one method unless two genuinely supply different stages, such as generation then selection. 3. Generate past the obvious defaults internally. Return concrete options tied to the user’s real constraints, each with a mechanism and honest tradeoff. Include at least one grounded option with a feasible first step. 4. Keep the method mostly invisible. Name or explain it only when that improves the user’s thinking or they ask how the ideas were produced. 5. Follow the user’s reactions. Refine or combine what survives instead of restarting with another generic list. When they choose, stop ideating and help execute. Ask one clarifying question only when the missing distinction would materially change the method or domain. Otherwise infer from context and begin. ## Routing - Blank page or no useful constraint: `references/full-prompt-library.md`. - Existing idea needs variations: `references/methods/scamper.md`. - Existing work is stuck: `references/methods/oblique-strategies.md`. - Output is safe, generic, or predictable: `references/methods/lateral-provocations.md`; use `pataphysics.md` only when implausibility is welcome. - Many notes or observations need structure: `references/methods/affinity-diagrams.md`. - Several options need a decision: `references/methods/premortem-and-inversion.md`; use `compression-progress.md` for research/project upside. - Engineering contradiction: `references/methods/triz-principles.md`. - Software or product structure: `references/methods/pattern-languages.md`, `first-principles.md`, or `jobs-to-be-done.md` according to the actual question. - Research question: `references/methods/compression-progress.md`; known formal problem: `polya.md`. - Narrative: `references/methods/story-skeletons.md`; formal writing constraint: `oulipo.md`; exhausted source material: `chance-and-remix.md`. - System, organization, or policy intervention: `references/methods/leverage-points.md`. - Life/career direction or unfamiliar territory: `references/methods/derive-and-mapping.md`. If these cues conflict, prefer the user’s explicit desired effect over domain defaults. For the full catalog or close calls, load `references/method-catalog.md` or `references/heuristics.md`. ## Quality bar Strong output is specific enough to imagine or test, non-obvious for a reason, and candid about failure modes. Avoid idea-shaped labels such as “an AI app for X” without a concrete mechanism. Do not force a fixed number, rigid template, inventor attribution, or narrated rejection ritual unless useful to the task. ## References - `references/method-catalog.md` — compact method index. - `references/heuristics.md` — close-call routing and edge cases. - `references/anti-slop.md` — use when the domain strongly attracts generic answers. - `references/exercises.md` — use when the user wants an exercise rather than generated ideas. - `references/full-prompt-library.md` — blank-page constraints. - `references/methods/` — individual methods; load only the chosen one.
From supplefrog/agent-sync, MIT.
More from supplefrog/agent-sync
- 0.592score
agent-orchestration-operations
supplefrog
Use when the user calls the agent “the orchestrator,” says “resume the orchestrator,” or coordinates agents, workers, coding CLIs, durable Kanban queues…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
delegation-workflows
supplefrog
Use when routing bounded coding implementation or tests to a Hermes worker, or when independent tasks warrant parallelism, isolation, or fresh review.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
hermes-lcm
supplefrog
Use, configure, diagnose, and retrieve exact evidence with the Hermes-LCM lossless context plugin.
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
skill-creator
supplefrog
Use when authoring instructions, reviewing model-facing tool interfaces, or preserving reusable workflows.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
trial-handoff
supplefrog
Use when drafting an internal customer trial handoff from an account packet for an implementation lead before a trial review.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
trial-handoff
supplefrog
Use when an advocate needs a concise internal handoff from a customer trial packet before its review.
SkillAFreshness: A★ 1Claude Code +9 - 0.554score
prototype
supplefrog
Build a throwaway prototype to answer a logic or state-model question.
SkillAFreshness: A★ 1Claude Code +9 - 0.549score
creative-production-workflows
supplefrog
Use for non-website visual and media artifacts: standalone diagrams, generative art, kinetic typography, ASCII media, GIFs, animation, ComfyUI, or…
SkillBFreshness: B★ 1Claude Code +9 - 0.546score
hermes-agent
supplefrog
Configure, troubleshoot, extend, or contribute to Hermes Agent.
SkillBFreshness: B★ 1Claude Code +9 - 0.538score
adversarial-ux-test
supplefrog
Roleplay a hostile user to find and triage UX pain points.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 13, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/supplefrog/agent-sync
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from supplefrog
- 0.592score
agent-orchestration-operations
supplefrog
Use when the user calls the agent “the orchestrator,” says “resume the orchestrator,” or coordinates agents, workers, coding CLIs, durable Kanban queues…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
delegation-workflows
supplefrog
Use when routing bounded coding implementation or tests to a Hermes worker, or when independent tasks warrant parallelism, isolation, or fresh review.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
hermes-lcm
supplefrog
Use, configure, diagnose, and retrieve exact evidence with the Hermes-LCM lossless context plugin.
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
skill-creator
supplefrog
Use when authoring instructions, reviewing model-facing tool interfaces, or preserving reusable workflows.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
trial-handoff
supplefrog
Use when drafting an internal customer trial handoff from an account packet for an implementation lead before a trial review.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
trial-handoff
supplefrog
Use when an advocate needs a concise internal handoff from a customer trial packet before its review.
SkillAFreshness: A★ 1Claude Code +9
Cite this page
creative-ideation skill. Agent Mart. https://agentmart.dev/skills/supplefrog-creative-ideation (last updated 2026-10-24)