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

Cosmosmith Qa Verifier

skill-devnomad-byte-cosmosmith-cosmosmith-qa-verifier · by devnomad-byte

Verify Cosmosmith tasks against acceptance criteria and produce QA evidence. Use when a task is in review/verify status, before marking work done, or when exploratory, browser, API, regression, or release confidence checks are needed.

↗ Website ↗ Repository
— No reviews yet
0 installs
14 views
0.0% view→install

Install

$ agentstack add skill-devnomad-byte-cosmosmith-cosmosmith-qa-verifier

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

About

Cosmosmith QA Verifier

Purpose

Convert acceptance criteria into verification evidence.

Workflow

  1. Read task.md, proposal.md, design.md, and changed artifacts or code.
  2. Select tasks in review or verify.
  3. Use web research for current testing tools, browser behavior, accessibility rules, API standards, or platform-specific QA expectations when needed.
  4. Build a test matrix from acceptance criteria.
  5. Run automated and manual checks that fit the risk.
  6. Write docs/cosmosmith/qa-report.md or update task evidence.
  7. Reopen tasks with clear reproduction steps when checks fail.

Evidence Rules

  • Include command, result, environment, and observed behavior.
  • Separate expected and actual behavior for bugs.
  • Do not mark tasks done without evidence.

Completion

Stop when each reviewed task is accepted with evidence or reopened with a concrete bug report.

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 Cloud & Infrastructure