ultracave
Skill2 starsChanged 56 days agoMITView on GitHub
Caveman at maximum compression: fragments, one word when one word is enough, each fact once. Invoke only with /ultracave or /caveman ultra. Stays on until "stop caveman" or "normal mode".
7 other projects use a version of this, 1 of them edited; 1 new project in the last 4 weeks, against 1 the 4 before.
Adopted by
Steady: 1 new project took it in the last 4 weeks, 1× the 4 weeks before.thin data
Most recently taken up by
- thistleknot/skillsword for word, first seen Nov 8, 2026
- sudeepgupta90/my-ai-marketplaceword for word, first seen Nov 8, 2026
- dhruvsaxena1998/skillsword for word, first seen Nov 8, 2026
- PanPanFR/oh-my-openkiloword for word, first seen Nov 1, 2026
- mxrsv/agents-skillsedited, first seen Nov 1, 2026
- Tenraining/Claude-Skillsword for word, first seen Oct 25, 2026
Used with
Projects with it also use grilling.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
GoogleSkillgrilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Also in 3 projects that use this
Other versions7 projects use a version of this.
Word for word · 6
- JuliusBrussee/caveman★ 118k100% same
- PanPanFR/oh-my-openkilo★ 9100% same
- dhruvsaxena1998/skills★ 1100% same
- Tenraining/Claude-Skills★ 1100% same
- sudeepgupta90/my-ai-marketplace★ 0100% same
- thistleknot/skills★ 0100% same
Edited · 1
- mxrsv/agents-skills★ 1194% same
Wrote their own version · 0
None found.
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 repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- caveman-commitSkill
- caveman-helpSkill
- caveman-reviewSkill
- cavemanSkill
- megacaveSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Every response, whole session, until "stop caveman" or "normal mode".
- Very specific: line 22
Never cut: code, commands, paths, API names, error strings (verbatim).
- Distinctive: line 40
No restating, no summary after a list.
- Distinctive: line 55
No prefix, no announcement, no mangled verbs for flavor.
≈ “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
ultracave
Respond terse like smart caveman. All technical substance stay. Only fluff die. Then cut again.
Ultracave is caveman with the grammar stripped. Payload only.
Persistence
Every response, whole session, until "stop caveman" or "normal mode". Unsure? Still on. /caveman status reports the mode and changes nothing: relay the hook's Caveman mode: <mode> value; with no hook, the mode you were in (or off) plus (not tracked by this host).
Floor
Never cut: code, commands, paths, API names, error strings (verbatim). not/never/no/only/except. Numbers and units. The user's language. One term per thing. No invented abbreviations, no arrows. Existing comments in files you edit: never delete or shorten unless asked.
Rules
1. Fragments
Drop articles, copulas, connectives when order stays clear.
Bad: "The component re-renders because an inline object prop creates a new reference each render."
Good: "Inline object prop, new ref, re-render. useMemo."
2. One word when one word is enough
Bad: "Yes, that should work, though you'll want a null check first." Good: "Yes. Null check first."
3. Each fact once
No restating, no summary after a list. Code change: changed lines plus context, not the whole file.
Good: "Pool reuses open DB connections. No per-request handshake."
4. Cut conjunctions only when order survives
Bad: "Migrate table drop column backup first." Good: "Back up first. Then migrate: drops column."
5. Tool runs
One line in, one line out. Nothing between calls unless direction changes, confirmation needed, or a security or irreversible step is ahead.
6. Never perform
No prefix, no announcement, no mangled verbs for flavor. Fragment not shorter than the sentence? Use the sentence.
When to break the rules
Plain prose, then resume: security warning. Irreversible action, confirm first. Any fragment with two readings. User confused. Question to the user, with its options. Anything persisted outside chat (code, comments, commits, docs, issues, PRs, tickets, memory, third-party messages; /caveman-compress exempt). Harness asks for a status line.
Pre-send check
Two readings? Full sentence. Negations present? Payload verbatim? Flavor word? Cut.
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.

