context-capsule
Skill0 starsChanged 5 months agoMITView on GitHub
Compress project facts into the smallest useful context block so agents stop guessing and start building.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- wrg32786/aigent-ostheir own version, first seen Oct 13, 2026
- Parad0x-Labs/openclaw-skillstheir own version, first seen Oct 6, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- wrg32786/aigent-os★ 25same name
- Parad0x-Labs/openclaw-skills★ 22same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/vibe-ship-skills.mdcCursor rule
- agent-briefSkill
- bug-replaySkill
- creator-launch-packSkill
- docs-as-testsSkill
- guardrail-refactorSkill
- mvp-scope-slicerSkill
- prompt-to-planSkill
- ship-it-checkSkill
- ui-polish-passSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 15
Use it when you want AI speed without the usual vibe-coding tax: vague scope, broken demos, missing tests, or code that looks done but …
≈ “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
Context Capsule
What this skill does
Compress project facts into the smallest useful context block so agents stop guessing and start building.
Use it when you want AI speed without the usual vibe-coding tax: vague scope, broken demos, missing tests, or code that looks done but cannot ship.
Operating mode
- Name the outcome — one sentence, user-visible, demoable.
- List constraints — stack, files to avoid, style, deadline, and non-goals.
- Create a tiny proof loop — test, script, screenshot, curl command, or manual checklist.
- Build one vertical slice — no speculative framework work.
- Verify out loud — report the exact command or evidence that proves the slice works.
Prompt template
Use the Context Capsule skill.
Goal: <what I want built or improved>
Context: <repo/app/user/problem>
Constraints: <stack, files, time, style>
Done means: <observable proof>
Do not: <scope traps or risky changes>Anti-patterns this skill blocks
- Starting with a folder explosion instead of a working slice.
- Accepting generated code without a verification loop.
- Rewriting the app to fix one small issue.
- Shipping a README claim that no command has proven.
- Letting the agent hide uncertainty behind confident prose.
Done checklist
- The request has a one-line success condition.
- The agent knows what not to change.
- There is at least one concrete verification step.
- The final answer includes evidence, not vibes.
Part of Vibe Coder Skills by Mustafa — Instagram: @mustafaiscoding, X/Twitter: @mustafa30.
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.