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:

🟢 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:

🟢 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

Files2

2 files · 2.5 KB

Select a file to preview

Overall Score

82/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

95

Quality

78

Clarity

88

Completeness

72

Summary

The `quick-recap` skill instructs agents to add a color-coded status footer (🟢/🡡/🔴) to every response, signaling whether work is finished, pending follow-up, or blocked. It defines clear rules for status line format and semantics, and optionally installs managed blocks into `AGENTS.md` or `CLAUDE.md` to make the convention automatic. This is a behavioral instruction skill with no file operations, external calls, or code execution.

Detected Capabilities

instruction templatedocumentationmanaged file installation (AGENTS.md/CLAUDE.md)

Trigger Keywords

Phrases that agents use to match this skill to user intent.

add status footermark task completeresponse conventionwork state signalagent instructionsproject status blockcompletion indicator

Use Cases

Signal task completion status in multi-agent workflows
Improve response scannability for long-running or delegated work
Install standard agent response conventions across a repository
Make blocking issues immediately visible without reading full responses
Establish consistent work state communication between humans and agents

Quality Notes

Clear, concise instruction set with practical examples for all three status states
Well-defined scope: purely behavioral, no file writes or code generation
Status line constraints (100 characters, no trailing content) are explicit and unambiguous
Installer pattern is reasonable but relies on user choosing `--update-instructions` flag
README and SKILL.md content are well-aligned and comprehensive
No edge case guidance for unusual situations (e.g., multiple parallel tasks, resuming partial work)
Would benefit from guidance on when NOT to use status block (e.g., within code blocks, documentation only)

Model: claude-haiku-4-5-20251001Analyzed: Sep 9, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

quick-recap