AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Loopify Retro

skill-andreratzenberger-loopify-loopify-retro · by AndreRatzenberger

Use after a loop completes to extract reusable lessons from the contract, trace, final diff, failures, useful checks, ambiguities, and rejected attempts.

↗ Repository
— No reviews yet
0 installs
0 views
— view→install

Install

$ agentstack add skill-andreratzenberger-loopify-loopify-retro

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Loopify Retro? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

loopify-retro

Extract lessons from completed loops.

When To Use

  • A loop finished.
  • Trace data should improve future specs or checks.
  • Failures reveal recurring weak spots.
  • Rejected attempts contain useful process knowledge.

Do Not Use

  • Do not write a generic victory lap.
  • Do not promote a project-specific lesson as universal without evidence.
  • Do not discard "why not that" knowledge.

Workflow

  1. Read contract, trace, final diff, and final report.
  2. Use references/retro-patterns.md to classify lessons.
  3. Identify ambiguous spec phrases, useful checks, missing checks, failure

clusters, authority surprises, and rejected attempts.

  1. Write a retro from templates/loop-retro.md.
  2. Recommend updates to future Loop Contract templates.
  3. Update memory only when requested or when project rules permit it.

Output

Loop retro document and optional template/process improvements.

Validation

  • The retro names checks that mattered.
  • The retro names missing evidence.
  • Future-template recommendations are concrete.

Example

Use loopify-retro on .loopify/loops/001-papertrail/trace.md and write .loopify/loops/001-papertrail/retro.md.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills