Install
$ agentstack add skill-skyf0xx-better-thinking-creative-constraints ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Creative Constraints
Deliberately add artificial constraints to a generative task, since bounded problems provoke more inventive solutions than open ones.
Why
Unlimited freedom paradoxically produces conventional output — without a forcing function, the mind defaults to the familiar. A well-chosen constraint eliminates the easy answers and forces genuine invention.
Use when / Don't use when
- Use when: ideation under full freedom is producing only conventional output; a team needs to break out of "the way we've always done it."
- Don't use when: the task is already meaningfully constrained — real-world constraints are enough; don't stack artificial ones on top.
Inputs → Outputs
- Inputs: an open-ended generative task.
- Outputs: ideas generated under an artificial constraint, plus an assessment of which constraint-forced ideas survive removing the constraint.
Principles
- The constraint should eliminate the default solution specifically, not just add friction randomly.
- Arbitrary constraints work — the mind doesn't need the constraint to be "meaningful" to be provoked by it.
- After generating under constraint, test whether the idea holds up once the artificial constraint is lifted — some ideas only make sense within it.
Procedure
- Identify the default, obvious solution the task keeps producing.
- Choose a constraint that specifically rules that default out — a zero budget, a one-day deadline, banning the primary resource, requiring an absurd element.
- Generate solutions within the constraint.
- For promising ideas, test removing the constraint: does the idea still hold value, or was it only a workaround?
- Keep the ideas that survive constraint removal; discard pure workarounds unless the constraint is permanent.
Common mistakes
- Choosing a constraint too weak to eliminate the default answer.
- Forgetting to test ideas after removing the constraint, keeping brittle workarounds.
- Applying constraints to an already tightly-constrained problem, adding friction without payoff.
Examples
- "Design this with zero budget" to find the truly essential feature.
- "Explain this in one sentence" to force clarity.
- A writing exercise banning the most common word in the genre.
Related
- [[divergent-ideation]] — the generation discipline this constraint is applied within.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: skyf0xx
- Source: skyf0xx/better-thinking
- License: MIT
- Homepage: https://zenbin.org/p/better-thinking
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.