How this skill is triggered — by the user, by Claude, or both
Slash command
/spwnr:spwnr-doThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill for `/spwnr-do`: small work that can finish in the current run without a durable plan/task/team workflow. Use `spwnr-principle` only for shared normalization habits and defaults.
Use this skill for /spwnr-do: small work that can finish in the current run without a durable plan/task/team workflow. Use spwnr-principle only for shared normalization habits and defaults.
Skill, Read, Write, Edit, and optional Agent.spwnr resolve-workers --search "<brief>" --host claude_code --format json.Stay in /spwnr-do when the work is a single bounded goal, one-off operation, inspection, narrow edit, or follow-up cleanup.
Redirect to /spwnr-plan when the task is broad, multi-stage, risky, planning-sensitive, or better handled by pipeline/team.
Redirect to /spwnr-worker-audit only when worker coverage is weak, missing, or unsupported for claude_code.
Write or update .claude/do/spwnr-do-<project-folder-name>-<YYYY-MM-DD-HHMMSS>-<slug>.md with:
MetadataUser RequestDo ReadinessWorker SelectionExecution NotesOutcomeNext Recommended CommandDo Readiness must say one of: stayed in /spwnr-do, redirected to /spwnr-plan, or blocked on /spwnr-worker-audit.
Use: Do Note, Fit Check, Worker Selection, Outcome, Next Recommended Command.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub cheong43/spwnr --plugin spwnr