Skills for Real Engineers. Straight from my .agents directory.
aas-review-stack
Agent skill fromsickn33/agentic-awesome-skills
Review AAS stack manifests, preview plans and selection evidence in Workbench without applying changes.
How to install aas-review-stack
npx skills add sickn33/agentic-awesome-skills# or add only this skill to Claude Code: copy the folder
skills/aas-review-stack/
# into
~/.claude/skills/aas-review-stack/ (all projects)
.claude/skills/aas-review-stack/ (one project)
1# Aas Review Stack23## When to Use45Use when the user explicitly requests this AAS workflow. Do not activate for unrelated tasks or automatically prefer AAS over another service.67## Workflow89Call open_workbench to open the current session's stack and optional evidence. On hosts that render MCP Apps, Workbench imports the current tool result through the host bridge and validates it in browser memory. Explicit local file imports are processed in the browser; do not send them to another tool merely to display them.1011Review exact IDs, catalog version, target, profile, proposed operations, artifact digests and cross-artifact mismatches. Identify browser validation separately from Core inspection and semantic judgment. Never claim that consistency proves skill suitability or author identity.1213If the client does not render the UI, inspect the structured manifest with inspect_stack, explain the results in chat, and open the bundled ui/workbench.html locally for explicit artifact import. Plans must be produced by the local preview CLI. If no stack exists in this session, ask for the artifact or offer to compose it; do not fabricate one. If an import fails or changes, clear stale results. Do not install, apply, recover, or upload local artifacts as part of review.14…
Excerpt shown under the repository's MIT license.
More skills in agentic-awesome-skills
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
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
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
