Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

caveman — spec encoding · juliusbrussee | DecimalAI

documentationby juliusbrussee

caveman — spec encoding

juliusbrussee/caveman

Source juliusbrussee/cavekit ↗License MIT

Caveman encoding for SPEC.md and spec-adjacent writes. Loaded by /spec, /build, /check. Cuts tokens ~75% vs prose while staying precise.

SkillScore95Maintained

Automatic

Doc Ops pack

Last verified 8/15/2026

What it changes

Passed 21 of 22 test cases with the skill, and 11 of 22 without it.

Without skill50%

With skill95%

Checks it passed that the model alone missed

Uses the arrow symbol → to denote output.
Uses the api and env interface shape prefixes.
Uses the short synonym run instead of execute.

and 12 more in the full report

10 fixed11 passed either way1 still failing0 broke

Pass-rate lift: +45 pp
Tokens: -14%
Agent turns: 0%
Response time: -67%

Model gemini-3.6-flashMeasured 8/15/2026v121 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/juliusbrussee-caveman/SKILL.md https://app.decimal.ai/s/juliusbrussee-caveman/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add juliusbrussee-caveman, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/juliusbrussee-caveman/ and pins it in .decimal/skills.lock

decimalai skills add juliusbrussee-caveman

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/juliusbrussee-caveman/SKILL.md https://app.decimal.ai/s/juliusbrussee-caveman/SKILL.md

Raw file: /s/juliusbrussee-caveman/SKILL.md ↗ · machine-readable summary at /s/juliusbrussee-caveman.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 10

Prompt

I need to update our internal `SPEC.md` document with a new security invariant regarding rate limiting on login attempts, plus a task entry showing that we completed implementing it. Please format these additions for the spec.

What was checked, without and with the skill
Checked	Without skill	With skill
Uses the invariant format starting with V1 or V<n> prefix.	Missed	Passed
Uses the pipe-separated task format with status symbol x and citations.	Missed	Passed

case-01 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md110 linessingle file

caveman — spec encoding

Applies to SPEC.md writes, spec-referencing prose, backprop entries. Does NOT apply to code, error strings, commit messages, PR descriptions.

GRAMMAR

Drop articles (a, an, the).
Drop filler (just, really, basically, simply, actually).
Drop aux verbs where fragment works (is, are, was, were, being).
Drop pleasantries.
No hedging (skip "might", "perhaps", "could be worth").
Fragments fine.
Short synonyms: fix > implement, big > extensive, run > execute.

SYMBOLS

Prefer over words:

→   leads to / becomes / on <x>
∴   therefore / fix
∀   for all / every
∃   exists / some
!   must / required
?   may / optional / unknown
⊥   never / forbidden / nil
≠   not equal
∈   in
∉   not in
≤   at most
≥   at least
&   and
|   or
§   section reference

PRESERVE VERBATIM

Never compress:

Track record

Benchmark

21 / 22

test cases passed, vs 11 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

juliusbrussee / cavekit

skills/caveman/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

caveman — spec encoding

GRAMMAR

SYMBOLS

PRESERVE VERBATIM

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills