herdr-explore
Skill36 starsChanged 2 days agoGPL-3.0View on GitHub
Find the best answer to a hard, open non-UI question by making several agents think in deliberately different directions, attacking each one for edge cases, then picking and merging. Use it for an architecture, protocol, process or prevention decision that will be costly to reverse or that more than one reasonable answer exists for: how to stop a recurring mistake, how to handle release numbers, how to model a new agent kind, how to keep a link alive in the background, whether to build or delete. Use it whenever the owner says "think hard", "cover edge cases", "explore options", "different directions", "what is the best way", "tear this apart", "which approach", or when two earlier answers disagreed. Skip it for a one-line fix, a decision the owner has already made, and a UI question (herdr-prototype). Pair it with herdr-plan (this is its section 3 when the design is open) and herdr-design (the journey).
In this repository27 other files it gives its agents.
- AGENTS.mdAGENTS.md
- site/llms.txtllms.txt
- general-videoSkill
- herdr-changelogSkill
- herdr-criticSkill
- herdr-designSkill
- herdr-motionSkill
- herdr-prototypeSkill
- herdr-reviewSkill
- herdr-screen-checkSkill
- hyperframes-animationSkill
- hyperframes-audioSkill
- hyperframes-cliSkill
- hyperframes-coreSkill
- hyperframes-creativeSkill
- hyperframes-keyframesSkill
- hyperframes-registrySkill
- hyperframesSkill
- hyperframes-studioSkill
- media-useSkill
- motion-graphicsSkill
- product-launch-videoSkill
- pr-to-videoSkill
- rust-best-practicesSkill
- rust-portSkill
- rust-reviewSkill
- skill-creatorSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

