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

Loopify Debug

skill-andreratzenberger-loopify-loopify-debug · by AndreRatzenberger

Use when a loop is stuck, repeating failures, flaking, patching the wrong target, hitting an authority conflict, or burning turns without convergence.

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

Install

$ agentstack add skill-andreratzenberger-loopify-loopify-debug

✓ 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 Debug? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

loopify-debug

Rescue stuck loops.

When To Use

  • The same failure repeats.
  • Checks are flaky or invalid.
  • The evaluator is weak.
  • The loop is burning turns without convergence.
  • The next useful step might be blocked or escalated, not another patch.

Do Not Use

  • Do not keep applying cosmetic patches to repeated failures.
  • Do not weaken checks just to escape a stuck loop.
  • Do not ignore authority-boundary conflicts.

Workflow

  1. Read Loop Contract and trace.
  2. Classify the stuck pattern with references/stuck-loop-taxonomy.md.
  3. Identify whether the issue is implementation, check, spec, context,

authority, or budget.

  1. Recommend recovery using templates/recovery-plan.md.
  2. Write a blocked report if no authorized recovery exists.
  3. Patch only when recovery is clear and authorized.

Output

Diagnosis, recovery plan, or blocked/escalated report.

Validation

  • The repeated pattern is named.
  • The next diagnostic differs from the failed attempts.
  • Blocked/escalated recommendations cite the contract rule.

Example

Use loopify-debug on docs/examples/stuck-loop-debug/trace.md and classify why the loop is not converging.

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