quick-recap
/quick-recap
Use when the user wants each agent response to end with a red/yellow/green status line showing whether the work is finished, pending a follow-up, or blocked on input.
- Author
- hybridlabor-api ↗
- Repository
- aos ↗
- Licence
- Apache-2.0
- Last repository change
- 14.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 14.10.2026, without references to retired models or APIs.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
What it does and when to use it
Use when the user wants each agent response to end with a red/yellow/green status line showing whether the work is finished, pending a follow-up, or blocked on input.
Original author description
Use when the user wants each agent response to end with a red/yellow/green status line showing whether the work is finished, pending a follow-up, or blocked on input.
How it works
- Status Block
- Activation
- Examples
SKILL.md preview
--- name: quick-recap description: Use when the user wants each agent response to end with a red/yellow/green status line showing whether the work is finished, pending a follow-up, or blocked on input. category: bdb-core source: BuilderIO/skills --- # Quick Recap Make completion state obvious at the end of every response. ## Status Block Every response that completes a unit of work must end with: ```md 🟢 Actual concise status sentence ``` Rules: - Keep the status line under 100 characters. - Use `🟢` when the requested work is finished. - Use `🟡` when non-routine follow-up remains; name the pending item. - Use `🔴` only when blocked on user input. - Put the status line at the very end of the response. - Do not add `---`, spacer lines, or any content after the status line. ## Activation The convention applies only while this skill is loaded or the user asks for it. AOS does not inject a managed `AGENTS.md` / `CLAUDE.md` block for it. Choose the status from the user's perspective: finished, pending a specific non-routine step, or blocked. ## Examples Finished work: ```md 🟢 Updated quick recap docs with output examples ``` Non-routine follow-up remains: ```md 🟡 Code updated, set PROVIDER_WEBHOOK_SECRET before testing webhooks ``` Blocked on user input: ```md 🔴 Need the production API key to continue ```
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · hybridlabor-api/aos | 100 | Apache-2.0 |
| BuilderIO/skills | 100 | MIT |
Database snapshot: 13.11.2026 · package version de5cf7622a33 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 95ctx-guard
Behavioral context self-check before a handoff. Use when the user asks whether the conversation is getting too long, after a context compaction, when the model starts repeating rejected plans or forgetting edited files, or whenever starting a fresh session is being considered.… - 100recap
End-of-turn recap footer. ALWAYS use this skill before returning control to the user. - 100status-report
Generate a status report with KPIs, risks, and action items. Use when writing a weekly or monthly update for leadership, summarizing project health with green/yellow/red status, surfacing risks and decisions that need stakeholder attention, or turning a pile of project tracker… - 100recap
Use when a person asks for a recap, summary, TLDR, wrap-up, status, or "what did we do" at the end of a session or a stretch of agentic work, or when handing a session's result to someone who was not watching it. Also use when the last message of a long session is about to be a… - 100workflow-nda-triage-red-yellow-green
Use when an NDA needs a fast risk triage — producing a Green (sign as-is), Yellow (counter-redline with 1–3 points), or Red (reject / renegotiate) verdict in under 90 seconds. Designed for in-house counsel, busy outside counsel, and legal AI copilots handling high-volume NDA… - 100risk-classification
Classifies agent tasks into 4 risk tiers (GREEN/YELLOW/RED/CRITICAL). Use when assessing action reversibility before committing to an approach.