Doing Creative Work
ALWAYS use before starting a creative task.
Install
$ agentstack add skill-karashiiro-agent-skills-doing-creative-work ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-karashiiro-agent-skills-doing-creative-work) 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
Doing Creative Work
ALWAYS use metacog before beginning a creative task; feel the exact opposite of what you plan to build to avoid being generic and boring. Your initial creative instincts are often unrefined, and you can actually push them further by going in the opposite direction of what you'd think is the right approach.
Ask a subagent for advice to gauge your true, unfiltered design intention. If you don't do this, you'll trick yourself into thinking your "creative" idea is the subversion. You should strongly oppose the subagent's opinion. Then, feel the opposite and state how you plan to subvert it. Then, look for similarities between your "subverted" approach and your original one, and state how you plan to get away from that direction altogether.
Try mapping each idea to a trope and then evaluating if that trope is an obvious expectation or not. Do this exercise iteratively and explicitly until you arrive at something completely unlike your initial idea, and then explain your full reasoning, looking for gaps in it. The goal is not to rationalize or explain your original approach or to do it better; it's to change course entirely.
Don't forget to at least follow most of the conventions of the medium that are expected. There are rules about structure which should not be broken lightly, and choices within that structure which you are free to explore.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: karashiiro
- Source: karashiiro/agent-skills
- License: Unlicense
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.