New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Caveman Spec Compression

by JuliusBrussee in JuliusBrussee/cavekit

Compresses SPEC.md writes and spec-referencing prose into terse, symbol-heavy fragments that drop articles, filler and hedging while keeping facts intact.

MITAuto-check passedDevelopment

Install Caveman Spec Compression

skills CLI
$ npx skills add JuliusBrussee/cavekit --skill caveman -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install JuliusBrussee/cavekit caveman --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/JuliusBrussee/cavekit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/caveman .claude/skills/caveman && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
caveman
GitHub stars
1.2k
Token cost
~721 tokens
SKILL.md length
268 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Compresses SPEC.md writes and spec-referencing prose into terse, symbol-heavy fragments that drop articles, filler and hedging while keeping facts intact.

  • Writing or editing an entry in SPEC.md
  • SKILL.md covers GRAMMAR, SYMBOLS, PRESERVE VERBATIM and SHAPES, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Logging a bug or task row in a spec-driven development project

What it does

The grammar drops articles, filler words, auxiliary verbs where a fragment still works, and all hedging language, favoring short synonyms like fix over implement; it prefers symbols such as an arrow for leads to, a therefore sign for fix, and a universal quantifier for for all over spelling the words out. Fixed shapes cover an invariant line, a pipe-delimited bug row with a status mark, a pipe-delimited task row with a done, in-progress or to-do mark, and an interface line such as a POST endpoint mapped to its response shape.

Several things are never compressed: code blocks, file paths, URLs, identifiers, numbers and versions, error message strings, SQL, regex, JSON, YAML and quoted strings. The skill steps aside for prose explanations, spec documents meant for external review, commit messages and inline diff comments, which all stay in normal English, and when cutting a word would lose a fact the rule is to keep it, since the goal is compression, not amputation.

When your agent uses it

  • Writing or editing an entry in SPEC.md
  • Logging a bug or task row in a spec-driven development project
  • The user says compress this or be brief about spec text

Example prompts

  • “Add a bug row for the token expiry off-by-one and cite the invariant it violates.”
  • “Write this requirement into SPEC.md in caveman form.”
  • “Compress this spec paragraph without losing any of its facts.”

What it can do on your machine

Read from SKILL.md and the folder at commit 7421e87. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Caveman Spec Compression loads about 721 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 268 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~721

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from JuliusBrussee/cavekit at commit 7421e87, republished under its MIT licence (© JuliusBrussee). 268 words, ~721 tokens.

Download SKILL.mdSave it as .claude/skills/caveman/SKILL.md (or your agent's skills folder).
name
caveman
description
Caveman encoding for SPEC.md and spec-adjacent writes. Loaded by /spec, /build, /check. Cuts tokens ~75% vs prose while staying precise. Triggers on any write to SPEC.md or when user says "caveman", "compress this", "be brief".

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:

  • 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 → reject

Bug row (pipe table under §B):

id|date|cause|fix
B1|2026-04-20|token `<` not `≤`|V2

Task row (pipe table under §T):

id|status|task|cites
T3|x|add auth mw|V1,I.api

Status: 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 ! set

EXAMPLES

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.

© JuliusBrussee, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/caveman of JuliusBrussee/cavekit.

Open the folder on GitHubat commit 7421e87

Compare with similar skills

Caveman Spec Compression next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Caveman Spec Compression compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Caveman Spec Compression this skillJuliusBrussee/cavekit1.2k—~721Automated safety check: PassMIT
BiSheng SDD Document Reviewdataelement/bisheng12k—~717Automated safety check: PassApache-2.0
MVP Technical DesignKhazP/vibe-coding-prompt-template3.1k—~512Automated safety check: PassMIT
Documentation Research Methodologyprime-radiant-inc/greenfield292—~4.6kAutomated safety check: PassApache-2.0
Feature Specificationowainlewis/blueprint412—~938Automated safety check: PassMIT
Speckit Review Runopsmill/infrahub5341 repos~1.6kAutomated safety check: PassApache-2.0

Similar skills

  • BiSheng SDD Document Review

    dataelement/bisheng

    Reviews BiSheng spec, design and tasks documents with checklists for PRD gaps, handover readiness and acceptance traceability, producing a report or an LGTM.

    12k GitHub stars~717 tokensUpdated today
    DevelopmentAuto-check passed

  • MVP Technical Design

    KhazP/vibe-coding-prompt-template

    Writes an MVP technical design from agreed requirements, covering architecture, data ownership, integration contracts, deployment and tradeoffs, then hands off to the next stage.

    3.1k GitHub stars~512 tokensUpdated 5 days ago
    DevelopmentAuto-check passed

  • Documentation Research Methodology

    prime-radiant-inc/greenfield

    Method for extracting behavioral specifications from a product's public documentation: tiered search order, claim extraction rules, output structure, stop criteria and gap analysis.

    292 GitHub stars~4.6k tokensUpdated 2 mo ago
    DevelopmentAuto-check passed

  • Feature Specification

    owainlewis/blueprint

    Writes one implementation-ready spec for a feature or major change, settling behavior, technical design, failure handling and acceptance checks before delivery.

    412 GitHub stars~938 tokensUpdated today
    DevelopmentAuto-check passed

  • Speckit Review Run

    opsmill/infrahub

    Comprehensive code review using specialized agents — orchestrates code, comments, tests, errors, types, and simplify agents sequentially.

    534 GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed

  • Speckit Review Comments

    opsmill/infrahub

    Code comment accuracy verification, documentation completeness assessment, comment rot detection.

    534 GitHub starsUsed in 1 repo~1.3k tokens
    DevelopmentAuto-check passed

More from JuliusBrussee/cavekit

All 8 skills in this repo

  • Backprop: Bug-to-Spec Protocol

    JuliusBrussee/cavekit

    After a bug is found, traces its root cause and feeds a new testable invariant back into the project spec so the bug class can't recur.

    1.2k GitHub stars~653 tokensUpdated 1 mo ago
    Auto-check passed

  • Spec Drift Check

    JuliusBrussee/cavekit

    Read-only detector that compares SPEC.md with the code and reports invariant, interface and task drift grouped by severity, without changing anything.

    1.2k GitHub stars~666 tokensUpdated 1 mo ago
    Auto-check passed

  • Adversarial Spec Review

    JuliusBrussee/cavekit

    Builds a skeptical reviewer grounded in the codebase and research notes to try to refute a spec before any code is written, citing file:line evidence and ending in a go or no-go gate.

    1.2k GitHub stars~959 tokensUpdated 1 mo ago
    Auto-check passed

  • Deepen Module Design

    JuliusBrussee/cavekit

    Scans the code a spec touches for its shallowest module, then proposes a refactor that hides more behind a smaller interface without changing behavior.

    1.2k GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed

  • Grill Before Spec

    JuliusBrussee/cavekit

    Interrogates a vague idea one question at a time, recommending an answer each round and recording results as goals and constraints before a spec is written.

    1.2k GitHub stars~812 tokensUpdated 1 mo ago
    Auto-check passed

  • Research

    JuliusBrussee/cavekit

    Gather external knowledge the spec needs and distill it into §R — the durable research log — so build grounds in facts instead of hallucinating library behavior.

    1.2k GitHub stars~782 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Caveman Spec Compression

What does Caveman Spec Compression do?

Compresses SPEC.md writes and spec-referencing prose into terse, symbol-heavy fragments that drop articles, filler and hedging while keeping facts intact. The grammar drops articles, filler words, auxiliary verbs where a fragment still works, and all hedging language, favoring short synonyms like fix over implement; it prefers symbols such as an arrow for leads to, a therefore sign for fix, and a universal quantifier for for all over spelling the words out. Fixed shapes cover an invariant line, a pipe-delimited bug row with a status mark, a pipe-delimited task row with a done, in-progress or to-do mark, and an interface line such as a POST endpoint mapped to its response shape.

When should I use Caveman Spec Compression?

Caveman Spec Compression fits situations like: writing or editing an entry in SPEC.md; logging a bug or task row in a spec-driven development project; the user says compress this or be brief about spec text.

How do I install Caveman Spec Compression in Claude Code?

Run `npx skills add JuliusBrussee/cavekit --skill caveman -a claude-code`. Or copy the skill folder (skills/caveman in JuliusBrussee/cavekit) into .claude/skills/caveman in your project. Claude Code loads it when a task matches its description.

How do I install Caveman Spec Compression in Codex?

Run `npx skills add JuliusBrussee/cavekit --skill caveman -a codex`. Or copy the skill folder (skills/caveman in JuliusBrussee/cavekit) into .agents/skills/caveman in your project. Codex loads it when a task matches its description.

Can I use Caveman Spec Compression in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JuliusBrussee/cavekit --skill caveman -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/caveman, .gemini/skills/caveman, .github/skills/caveman and .opencode/skills/caveman in your project.

What does Caveman Spec Compression need to run?

SKILL.md names no scripts, command-line tools or credentials: Caveman Spec Compression is instructions for the agent only.

Does Caveman Spec Compression access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Caveman Spec Compression safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Caveman Spec Compression use?

Caveman Spec Compression is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Caveman Spec Compression use?

About 721 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Caveman Spec Compression?

Skills that share tags, products or a category with Caveman Spec Compression: BiSheng SDD Document Review (dataelement/bisheng, 12k stars), MVP Technical Design (KhazP/vibe-coding-prompt-template, 3.1k stars), Documentation Research Methodology (prime-radiant-inc/greenfield, 292 stars) and Feature Specification (owainlewis/blueprint, 412 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Caveman Spec Compression?

JuliusBrussee (a GitHub user) maintains it in JuliusBrussee/cavekit, which has 1,151 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on August 14, 2026.

Source: JuliusBrussee/cavekit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.