Skip to main content
skill CX Codex

quick-recap — Claude Code skill: what it does, how to install

quick-recap adds a short final status block to completed agent responses. Use it when project instructions require a consistent completion signal.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add BuilderIO/skills --skill quick-recap -a claude-code
Open on GitHub

What quick-recap does

quick-recap sets a final status format for every response that completes a unit of work. A green marker means the requested work is finished, yellow names a specific non-routine step that remains, and red is reserved for cases blocked on user input. The status line stays under 100 characters and must be the last content in the response.

When the skill is installed, it prefers adding a managed block to AGENTS.md or CLAUDE.md unless the user opts out. The convention becomes automatic only when it exists in project or user instructions. That is the point to check: installing the skill alone does not make the format apply everywhere.

What it helps with

  • mark completed work with a green status
  • name a pending step in a yellow status
  • show when user input blocks progress
  • add status rules to AGENTS.md or CLAUDE.md

Example prompts for the agent

  • Finish the response using the quick-recap rules and add the final status block.
  • If the task is complete, put a green status on the last line of your response.
  • Use a yellow status to name the step still pending after the code update.

How to install quick-recap

1Skills CLI (Vercel)

npx skills add BuilderIO/skills --skill quick-recap -a claude-code

2Manually: put the files in place

~/.claude/skills/quick-recap/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/quick-recap/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about quick-recap

How do I install quick-recap in Claude Code?

Run npx skills add BuilderIO/skills --skill quick-recap -a claude-code, run npx skills add BuilderIO/skills --skill quick-recap -a claude-code again, then check ~/.claude/skills/quick-recap/SKILL.md.

What does quick-recap do?

It defines a final response block for agent work: green marks completion, yellow names a remaining step, and red signals a block caused by missing user input.

When does quick-recap apply automatically?

Only when its rule is present in project or user instructions. During installation, it prefers adding a managed block to AGENTS.md or CLAUDE.md unless the user opts out.

Source text

SKILL.md · MIT
---
name: quick-recap
description: Use when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.
---

# 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.

## Installer Behavior

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.

## 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
```

© BuilderIO · MIT · BuilderIO/skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set6

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor