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

Loopify Checks

skill-andreratzenberger-loopify-loopify-checks · by AndreRatzenberger

Use when turning vague requirements into concrete automated checks, visual review gates, manual review items, acceptance tests, or quality-gate commands.

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

Install

$ agentstack add skill-andreratzenberger-loopify-loopify-checks

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

About

loopify-checks

Turn requirements into honest evidence.

When To Use

  • A Loop Contract has weak evidence.
  • A spec uses words like polished, fast, delightful, or production-ready.
  • A project needs tests, screenshot checks, build checks, or manual gates.

Do Not Use

  • Do not invent tests that do not prove the requirement.
  • Do not erase manual review just because automation is easier.
  • Do not modify product behavior unless the user authorized implementation.

Workflow

  1. Read the spec or Loop Contract.
  2. Identify weak, fake, or missing evidence.
  3. Use references/check-patterns.md to propose checks by evidence class.
  4. Use references/visual-review-gates.md for UI/screenshot work.
  5. Use references/manual-review-language.md for subjective acceptance.
  6. Add or draft checks only when authorized.
  7. Update the Requirement Evidence Map.

Output

Updated Loop Contract, quality gate, tests, screenshot plan, or acceptance checklist using templates/acceptance-checklist.md.

Validation

  • Each required behavior has evidence or an explicit ambiguity.
  • Visual/manual gates are not hidden inside automated claims.
  • New checks are runnable or clearly marked as drafts.

Example

Use loopify-checks to strengthen .loopify/loops/001-papertrail/loop-contract.md for mobile layout and fallback behavior.

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