4
Skill4 starsChanged 3 months agoMITView on GitHub
Deeper execution timebox for substantial tasks requiring broader investigation, implementation, and regression testing. Use when the user invokes /4 and target completion within 18 minutes.
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- 1Skill
- 2Skill
- 3Skill
- 5Skill
- ae-extendscriptSkill
- asapSkill
- backbeforeSkill
- componentsSkill
- githubSkill
- huhSkill
- instantSkill
- motion-animateSkill
- motion-assetsSkill
- motion-designSkill
- motion-pipelineSkill
- motion-planSkill
- quick-contextSkill
- shader-uiSkill
- thumbnailSkill
- ui-intergritySkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Consider meaningful edge cases and failure states.
- Distinctive: line 22
Run appropriate tests, builds, linting, or visual verification.
- Distinctive: line 23
Check for regressions in closely connected functionality.
- Distinctive: line 24
Remove temporary or debugging artifacts.
- Distinctive: line 25
Do not wander into unrelated improvements.
≈ “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.
Files
/4 — Deep
Complete this substantial task end to end with focused investigation and strong verification.
Timebox
Target completion in under 18 minutes. The larger timebox allows broader investigation, not lower urgency.
Behavior
- Understand the relevant system before modifying it.
- Trace interactions across affected files and components when necessary.
- Find root causes rather than layering patches.
- Consider meaningful edge cases and failure states.
- Implement the complete requested behavior.
- Refactor locally when required for a clean solution.
- Run appropriate tests, builds, linting, or visual verification.
- Check for regressions in closely connected functionality.
- Remove temporary or debugging artifacts.
- Do not wander into unrelated improvements.
Parallelize independent investigation or verification when tools allow it. Prefer decisive execution over prolonged deliberation. Finish with the implementation in a clean, verified state.
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.