From capybaraa
Quick reference for capybaraa, what it does, the lean ladder and five habits, and how to turn it on or off. Use when the user types /capybaraa-help or asks how capybaraa works.
How this skill is triggered — by the user, by Claude, or both
Slash command
/capybaraa:capybaraa-helpThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Render this card, change nothing.
Render this card, change nothing.
capybaraa: lean senior-dev mode. ponytail's discipline + five habits.
one mode, always on, scaled to the task. no command needed.
LADDER does it need to exist? · reuse what's here · stdlib/platform ·
installed dep · one line · then the least code that works
HABITS ASK Claude already asks; the add is an ASCII sketch on the
options when you do. ask only the deciding questions.
OPTIMAL right data structure · no needless O(n^2)
TERSE few words · few comments · no filler
CLEAN refactor = replace · kill dead code / stale comments
SYNC after a change, update docs/tests/refs/versions that
named the old shape · delete stale · /capybaraa-sync sweeps
NEVER drop validation, error handling, security, accessibility for fewer lines
SLASH /capybaraa [on|off] turn it on or off
/capybaraa-review review the diff against the rules
/capybaraa-audit scan the whole repo for bloat + drift
/capybaraa-sync fix drift: code vs its docs/tests/refs
/capybaraa-help this card
DETAIL longer guidance: references/principles.md
SIGNAL replies open with 🦫 so you can see it is on. no other ceremony.
OFF "stop capybaraa" or /capybaraa off
DEFAULT CAPYBARAA_DEFAULT_LEVEL env (on|off), or
~/.config/capybaraa/config.json {"defaultState":"off"}
npx claudepluginhub katipally/capybaraa --plugin capybaraaGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Enforces test-driven development: write failing test first, then minimal code to pass. Use when implementing features or bugfixes.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.