Skip to main content
skill CX Codex

constraint-based-creativity — Claude Code skill: install and use

constraint-based-creativity — a skill that makes the model invent inside tight limits, such as a small budget or a fixed format, so brainstorming stops circling the same answers.

no license 115 installs ★ 203 updated 2026-09-01

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add lyndonkl/claude --skill constraint-based-creativity -a claude-code
Open on GitHub

What constraint-based-creativity does

Give an agent an open brief and the suggestions come back predictable. This skill narrows the brief on purpose. It picks a box, maybe a tiny budget or a ban on one tool, and the shortage becomes the material to work with. The limits it works with fall into resources, format or medium, rules, technical limits, and audience or point of view.

Five steps carry the session: read the problem, choose one to three constraints, generate inside them, pick the strongest ideas, verify. Output lands in constraint-based-creativity.md, with the active rules and the full idea list, failed attempts included when they pointed somewhere useful. Two support files do the heavy lifting: resources/template.md when limits already exist, resources/methodology.md when you need to design them.

The last step scores the work against resources/evaluators/rubric_constraint_based_creativity.json. Anything averaging under 3.5 does not pass. That bar forces the agent to show the constraint caused the idea rather than sitting next to it. Go past three limits and you starve the process yourself.

What it helps with

  • pull unusual ideas out of a small budget or a short deadline
  • get a stuck brainstorm moving again
  • fit a layout or a piece of copy into a fixed format
  • show an idea came from the limit, not from habit
  • narrow a long list of constraints to the ones that help

Example prompts for the agent

  • Brainstorm 10 ideas for the launch page on a $500 budget with no UI library, then tell me which limit produced the best one.
  • Design the sync feature as if there were no network, and explain what the offline rule changed.
  • Run these ideas past rubric_constraint_based_creativity.json and show where the constraint did nothing.

How to install constraint-based-creativity

1Skills CLI (Vercel)

npx skills add lyndonkl/claude --skill constraint-based-creativity -a claude-code

2Manually: put the files in place

~/.claude/skills/constraint-based-creativity/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/constraint-based-creativity/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about constraint-based-creativity

How do I install constraint-based-creativity in Claude Code?

Run npx skills add lyndonkl/claude --skill constraint-based-creativity -a claude-code. The skill file lands at ~/.claude/skills/constraint-based-creativity/SKILL.md.

What does this skill do?

It makes the agent generate ideas inside deliberate limits and checks the output against a rubric before handing it over.

Can it work with limits I already have?

Yes. resources/template.md covers projects where the budget, timeline or materials are fixed; resources/methodology.md is for designing constraints when nothing is fixed yet.

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set49

The whole set →
environmental-scanning-foresight environmental-scanning-foresight tracks external trends across six PESTLE dimensions, catches weak signals of change, builds scenario futures, and sets adaptive indicators for early warning. CX Codex +1 120installs scout-mindset-bias-check scout-mindset-bias-check is a Claude Code skill that checks forecasts with Scout Mindset procedures, including when an estimate feels emotional or stuck at 50/50. CX Codex +1 119installs domain-research-health-science domain-research-health-science structures health science and medical evidence synthesis using PICOT framing, formal bias checklists, and GRADE certainty scoring. CX Codex +1 119installs adr-architecture adr-architecture turns an architecture choice into a written decision record with context, rejected options and consequences, then scores the draft against a rubric. CX Codex +1 118installs translation-reframing-audience-shift translation-reframing-audience-shift rewrites content for a different audience: technical docs to business cases, strategy to action steps, expert text to plain language. CX Codex +1 115installs meta-prompt-engineering The meta-prompt-engineering skill turns unclear prompts into structured instructions with a defined role, task steps, constraints, and quality checks. Use it when an agent’s responses vary between runs. CX Codex +1 114installs systems-thinking-leverage systems-thinking-leverage turns a tangled problem into a mapped system with ranked intervention points, built on feedback loops and Meadows' leverage ladder. CX Codex +1 114installs reviews-retros-reflection reviews-retros-reflection structures retrospectives, incident post-mortems, and periodic check-ins. Helps teams identify root causes and turn feedback into SMART action items without blame. CX Codex +1 113installs

Project sponsors

Companies that keep this analytics open