Stats
Actions
Tags
From Cairn
Open a Cairn decision so subsequent file edits attach to it. Use right before making a deliberate implementation choice worth recording — when there is a real intent, a constraint being worked around, or alternatives being weighed.
How this skill is triggered — by the user, by Claude, or both
Slash command
/cairn:decision <intent><intent>The summary Claude sees in its skill listing — used to decide when to auto-load this skill
```!
node "${CLAUDE_SKILL_DIR}/../../dist/cli.js" open-decision-stdin <<'CAIRN_EOF_6fbb5abbb981ffcf5e266ad6'
$ARGUMENTS
CAIRN_EOF_6fbb5abbb981ffcf5e266ad6
A Cairn decision is now open. Until the next decision opens (or the session ends), the files you edit are journaled under this decision in .git/cairn/. On your next commit, Cairn folds that journal into a Lore-compatible decision record on the commit message and into the refs/notes/cairn graph, so a future session can ask why(<file>) and get this reasoning back.
To make the captured record richer, state in your next message — if they apply — the constraint you are working around and any alternative you considered and rejected, with the reason. That text is snapshotted from the transcript at edit time and refined into the record at consolidation.
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
npx claudepluginhub andrewjsauer/cairn