NeVibeCode · 10 items
Skills and MCP tagged “verification”
verify-and-stop skill Proves existing work meets acceptance criteria without expanding scope. Useful for validation tasks and last-mile checks.
Claude Code CX Codex Cursor +1
104,000installs
do skill The skill runs an implementation plan in phases through subagents. Use it when a plan needs execution with checks after each phase.
Claude Code CX Codex Cursor +1
7,000installs
unlazy skill This skill sets testable completion gates, breaks complex work into stages, and rechecks evidence before the agent reports completion.
Claude Code CX Codex Cursor +1
9,400installs
cmux-testing skill Skill for choosing verification scopes, adding tests, and validating Swift test targets in the cmux project. Decides what local and CI evidence a change needs.
Claude Code CX Codex Cursor +1
4,900installs
grounded-vault skill Maintains a durable Markdown knowledge store with per-claim source provenance and zero-token drift detection against code using git diff.
Claude Code CX Codex Cursor
1,400installs
verify-agent-action
official skill Audits proposed AI agent actions, deployments, and approvals before execution. It checks parameters, nonces, and telemetry, never authorizing or running actions on its own.
GitHub Copilot
29installs
agent-harness skill Turns a goal into tasks with machine-run checks, then keeps the loop open until each task is verified or explicitly waived. Use it for work that needs a verifiable close.
Claude Code
68installs
agent-browser-verify
official skill Checks a dev server page in the browser for loading issues, console errors, and missing UI elements. Use it to verify a running project before moving on.
CX Codex GP ChatGPT
14installs
Doublecheck
official subagent Verifies AI-generated text by finding web sources and highlighting hallucination risks. Useful before publishing content containing legal citations, statistics, or API syntax.
GitHub Copilot
★ 40,369repo stars
doublecheck
official plugin Extracts factual claims from AI text, searches the web for sources, and flags hallucination patterns before you act on inaccurate data.
GitHub Copilot
★ 40,369repo stars