
Caveman
- 259k installs
- 1.1k repo stars
- Updated June 18, 2026
- juliusbrussee/blueprint
Caveman encoding is a compression technique for technical specs that drops articles and filler while using symbolic notation, reducing token usage approximately 75% versus prose.
About
Apply caveman encoding to spec documents and technical writes to save tokens by dropping articles, filler, and auxiliaries while preserving facts using symbolic notation. Cuts prose by approximately 75% while remaining scannable.
- Token-saving spec encoding: drop articles, filler, auxiliary verbs, and pleasantries
- Use symbolic notation for relations (arrow, therefore, forall, exists, not, etc.) to compress written specs
- Cuts tokens approximately 75% versus prose while staying precise and scannable
Caveman by the numbers
- 259,391 all-time installs (skills.sh)
- Ranked #7 of 1,901 Documentation skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
caveman capabilities & compatibility
- Capabilities
- compression · spec formatting · notation system
npx skills add https://github.com/juliusbrussee/blueprint --skill cavemanAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 259k |
|---|---|
| repo stars | ★ 1.1k |
| Security audit | 3 / 3 scanners passed |
| Last updated | June 18, 2026 |
| Repository | juliusbrussee/blueprint ↗ |
How do you compress SPEC.md files for agents?
Write token-efficient technical specifications and design documents that remain precise and scannable using compressed grammar and symbolic notation.
Who is it for?
Teams writing SPEC.md files, design specs, and technical documentation who want to minimize token usage.
Skip if: Production code, commit messages, PR descriptions, error strings, or teams that require full-sentence formal specifications.
When should I use this skill?
User writes SPEC.md or spec-adjacent prose, or asks to compress or be brief.
What you get
Token-efficient SPEC.md files and spec prose encoded in caveman fragment grammar.
- compressed SPEC.md
- caveman-encoded spec prose
By the numbers
- Cuts tokens ~75% vs prose per skill readme
Files
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 referencePRESERVE VERBATIM
Never compress:
- Code blocks, snippets, one-liners with backticks.
- Paths:
src/auth/mw.go. - URLs.
- Identifiers: function names, variable names, env vars.
- Numbers and versions.
- Error message strings.
- SQL, regex, JSON, YAML.
- Quoted strings.
SHAPES
Invariant:
V<n>: <subject> <relation> <condition>
V1: ∀ req → auth check before handler
V2: token expiry ≤ current_time → rejectBug row (pipe table under §B):
id|date|cause|fix
B1|2026-04-20|token `<` not `≤`|V2Task row (pipe table under §T):
id|status|task|cites
T3|x|add auth mw|V1,I.apiStatus: x done, ~ wip, . todo. Escape literal | as \|.
Interface:
<kind>: <name> → <shape>
api: POST /x → 200 {id:string}
cmd: `foo bar <arg>` → stdout JSON
env: FOO_KEY ! setEXAMPLES
Bad:
The system should ensure that every incoming request is properly authenticated before being forwarded to its corresponding handler function.
Good:
V1: ∀ req → auth check before handler
Bad:
We discovered that the token expiration check in the middleware was using a strict less-than comparison operator, which meant tokens were being rejected at the exact moment of their expiry.
Good:
B1: token<not≤→ reject @ expiry boundary.
Bad:
The POST endpoint at /x accepts a JSON body and returns a 200 response with an object containing the created id.
Good:
api: POST /x → 200 {id}
BOUNDARIES
- User asks for prose explanation → switch to normal English.
- Spec documents for external review (RFC, pitch) → normal English.
- Commit message → normal English (git readers expect it).
- Diff comment in code → normal English.
WHEN UNSURE
If cutting a word loses a fact, keep it. Caveman is compression, not amputation.
Related skills
Forks & variants (1)
Caveman has 1 known copy in the catalog totaling 2.5k installs. They canonicalize to this original listing.
- juliusbrussee - 2.5k installs
How it compares
Use caveman for token-efficient SPEC.md encoding rather than general technical writing or code formatting skills.
FAQ
How much does caveman reduce SPEC.md tokens?
caveman targets roughly 75% fewer tokens versus standard prose while staying precise. The grammar uses fragments that drop articles, filler words, auxiliary verbs, pleasantries, and hedging from SPEC.md content.
What files does caveman apply to?
caveman applies to SPEC.md writes, spec-referencing prose, and backprop entries. The skill does not apply to application code, error strings, commit messages, or PR descriptions.
Is Caveman safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.