Add Caveman Compress documentation to README (usage, how it works, preservation rules, benchmarks) and a new skills/caveman/SKILL.md defining caveman modes, intensity, and rules. Update .gitignore to more accurately ignore macOS .DS_Store files. Trim and adjust tests/caveman-compress fixtures to match compressed output format.
Update .github/workflows/sync-skill.yml to add a pre-change step that configures git user/email and runs git pull --rebase origin main before copying files, reducing risk of merge conflicts. Also rename the commit step to "Commit and push if changed" and remove redundant git config and pull from that step so it only commits and pushes the updated files.
Update GitHub Actions workflow to add concurrency controls, checkout the main ref, simplify ZIP creation (zip directly from skills/), and pull --rebase before committing; commit message now includes [skip ci]. Also update README to add an "Intensity Levels" nav link. Clarify skills/caveman/SKILL.md: document explicit /caveman lite|full|ultra triggers, expand the description of dropped filler/pleasantries/hedging, and apply small formatting tweaks.
Replace verbose two-table layout with compact 3-column side-by-side
table matching the existing Before/After HTML pattern. Remove chatty
intro and forced taglines in favor of natural caveman voice.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Show lite, full, and ultra side-by-side using the same React re-render
and auth middleware examples from the existing Before/After section.
Also fixes emoji encoding from prior edit.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add intensity levels section to README so feature is discoverable
- Document Codex trigger syntax ($caveman lite|full|ultra) in SKILL.md
- Sync plugin copy and rebuild .skill archive
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds three compression levels so users can dial caveman up or down:
- Lite: drops filler/pleasantries, keeps normal grammar
- Full: existing default behavior, unchanged
- Ultra: maximum telegraphic compression with abbreviations
Closes#10
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add a benchmarks directory with prompts.json, requirements.txt, results/.gitkeep, and run.py to measure Claude output token counts (normal vs caveman) using the Anthropic client. run.py supports dry-run, multiple trials, saving JSON results, computing stats, and optionally updating the README benchmark table; it reads the caveman SKILL.md for the system prompt. Also add .gitignore entries and expand README.md with badges, a Benchmarks section, sample table, and usage instructions.
Add GitHub issue templates for bug reports and feature requests tailored to the caveman persona, and add CONTRIBUTING.md describing how to propose changes to skills/caveman/SKILL.md (fork, edit, PR with before/after examples and rationale). These files help standardize contributions and make it easier for maintainers to review small, focused changes; also points contributors to ‘good first issue’ tasks.
Insert a star-history chart badge (linked to star-history.com) into the README to show the repository's star count over time as a visual indicator of project popularity.
Introduce 'caveman' Claude plugin: add .claude-plugin/plugin.json with plugin metadata and author, and add skills/caveman/SKILL.md documenting Caveman Mode rules, examples, and boundaries. Also update README install instructions to use the plugin marketplace and install commands for caveman.
Skill that reduces token usage ~75% by making Claude speak like a caveman
while maintaining full technical accuracy. Includes packaged .skill file,
README with install instructions, and MIT license.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Julius Brussee