Skills for Real Engineers. Straight from my .agents directory.
verification
Agent skill fromChatCut-Inc/agent-plugin
Use with the ChatCut connector (the `chatcut` MCP server). Verify that ChatCut plugin edits are reflected in project structure and visible timeline output before reporting success.
How to install verification
npx skills add ChatCut-Inc/agent-plugin# or add only this skill to Claude Code: copy the folder
claude-directory/skills/verification/
# into
~/.claude/skills/verification/ (all projects)
.claude/skills/verification/ (one project)
1# Verification23Use both structural and visual evidence when the requested result is visible:451. Re-read the affected scope with `read_project`, `preview_timeline`, `inspect_item`, `browse_assets`, or `inspect_asset` as appropriate. Use the latest response for ids, tracks, timing, and readiness.62. Inspect composed timeline frames through the visual tool exposed by the current manifest. Successful rendering or mutation metadata is not visual proof until the returned pixels are inspected.78Check your own work the cheapest way that answers the question: `preview_timeline` frames for the picture, a `format:"audio"` export to hear audio, and a local `480p` range export to watch motion. Never make a full-resolution or cloud export for a self-check.910Use local source bytes for raw source understanding when the original path is available. Use `inspect_asset` when the original is not locally available. Source frames help select moments but do not prove timeline composition; use composed timeline frames for trims, layers, captions, effects, crops, transitions, and Motion Graphics.1112If signed frame URLs are returned and the host cannot inspect them directly, download the complete shell-quoted URLs into a temporary directory and inspect those files. Do not report visual success from URLs alone.13…
Excerpt shown under the repository's Apache-2.0 license.
More skills in agent-plugin
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
