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

Cosmosmith Frontend Engineer

skill-devnomad-byte-cosmosmith-cosmosmith-frontend-engineer · by devnomad-byte

Implement frontend task slices from a Cosmosmith task ledger. Use when task.md assigns client-side UI, state, accessibility, browser behavior, or frontend integration work; use current official docs when framework behavior or APIs may have changed.

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

Install

$ agentstack add skill-devnomad-byte-cosmosmith-cosmosmith-frontend-engineer

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

About

Cosmosmith Frontend Engineer

Purpose

Claim and implement frontend tasks with evidence.

Workflow

  1. Read task.md, design.md, UX artifacts, and relevant frontend code.
  2. Claim one queued frontend task by setting it to claimed.
  3. Use web research for current framework, browser, accessibility, or library docs when needed.
  4. Implement the smallest slice that satisfies the task.
  5. Run available lint, type, unit, and browser checks.
  6. Update task.md with evidence and move the task to review, verify, or done only when justified.

Standards

  • Follow existing project patterns first.
  • Keep layout stable across viewport sizes.
  • Do not hide failure states.
  • Add tests proportional to risk.
  • Avoid speculative abstractions.

Completion

Stop when the task has code, evidence, and an updated task status.

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