From Builder Skills
Makes completion state obvious at the end of every Claude Code response using a red/yellow/green status block convention.
How this skill is triggered — by the user, by Claude, or both
Slash command
/builder-skills:quick-recapThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Make completion state obvious at the end of every response.
Make completion state obvious at the end of every response.
Every response that completes a unit of work must end with:
🟢 Actual concise status sentence
Rules:
🟢 when the requested work is finished.🟡 when non-routine follow-up remains; name the pending item.🔴 only when blocked on user input.---, spacer lines, or any content after the status line.This convention is only automatic when it is present in project or user
instructions. When installing this skill, prefer adding the managed
AGENTS.md / CLAUDE.md block unless the user opts out.
If you are following the convention manually, choose the status from the user's perspective: finished, pending a specific non-routine step, or blocked.
Finished work:
🟢 Updated quick recap docs with output examples
Non-routine follow-up remains:
🟡 Code updated, set PROVIDER_WEBHOOK_SECRET before testing webhooks
Blocked on user input:
🔴 Need the production API key to continue
npx claudepluginhub builderio/skillsSummarizes recent verbose agent activity (tool calls, file changes, decisions) into Mission, Result, Wasted effort, Status format. Triggers on 'wtf did you say', 'tldr', 'summarize what you did'.
Shows a single-screen work status dashboard with task state, epic progress, knowledge flywheel health, and recent activity. Useful for getting oriented or deciding next actions.