/distill
When there's a failure, bug, unexpected behavior, or important finding, distills it into a verified general rule saved under .loop/memory/. Invoke right after resolving a gate (test/typecheck) failure, right after fixing a verifier-graded fail, or right after pinning down a
$ npx -y skills add hiphapis/loopcraft --skill distill --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/distill
Context preview
The summary Claude sees to decide when to auto-load this skill.
When there's a failure, bug, unexpected behavior, or important finding, distills it into a verified general rule saved under .loop/memory/. Invoke right after resolving a gate (test/typecheck) failure, right after fixing a verifier-graded fail, or right after pinning down a
Loop engineering plugin for Claude Code — instead of steering the model with ever-longer prompts, design loops where it self-corrects from environment feedback and accumulates memory across sessions.
Other skills on loopcraft.
- /loop-init
Onboards loopcraft into a project — scans the repo to detect gate commands, confirms the backlog and rubrics through an interview, then scaffolds the .loop/ structure. Run once per project, or when refreshing the config.
Open skill - /loop-run
Traverses the backlog unattended, applying the loop-task cycle (rubric · verifier · gate · Loop-Verified commit) to each item. Invoke only when the user explicitly starts an autonomous batch run — for individual work, use loop-task directly.
Open skill - /loop-task
Runs non-trivial implementation/fix work that needs a verifiable output through a rubric + independent verifier grading cycle. Invoke before starting code/docs work. Not for simple questions, exploration, or one-line fixes.
Open skill