prompt-evaluation-runn…
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost…
Use when a Codex or generic local agent needs a focused second opinion from Gemini CLI without MCP routing.
Claude Code
$ npx -y skills add yeaight7/agent-powerups --skill ask-gemini --agent claude-code
Codex
$ npx skills add yeaight7/agent-powerups --skill ask-gemini -a codex -y
Cursor
$ npx skills add yeaight7/agent-powerups --skill ask-gemini -a cursor -y
Gemini CLI
$ npx skills add yeaight7/agent-powerups --skill ask-gemini -a gemini-cli -y
GitHub Copilot
$ npx skills add yeaight7/agent-powerups --skill ask-gemini -a github-copilot -y
OpenCode
$ npx skills add yeaight7/agent-powerups --skill ask-gemini -a opencode -y
Windsurf
$ npx skills add yeaight7/agent-powerups --skill ask-gemini -a windsurf -y
name: ask-gemini description: Use when a Codex or generic local agent needs a focused second opinion from Gemini CLI without MCP routing.
Use local Gemini CLI as an external advisor for brainstorming, design feedback, or focused reviews. The workflow is local-first and always leaves a Markdown artifact.
**For multi-turn advisory sessions** (persistent context across follow-ups), use `relay-gemini` instead — `apx relay start <name> --provider gemini` keeps context across turns.
Run through APX:
apx ask-gemini "Brainstorm edge cases for this CLI"
Equivalent nested APX and direct CLI calls:
apx ask gemini "Brainstorm edge cases for this CLI"
gemini -p "Brainstorm edge cases for this CLI"
If `gemini` is missing, stop and ask the user to install/configure Gemini CLI. Verify with:
gemini --version
APX writes:
.apx/artifacts/gemini-<slug>-<timestamp>.md
Artifact sections:
apx check ask-gemini apx ask-gemini "Return OK only" --json
Confirm JSON includes `provider`, `artifactPath`, `promptLength`, and raw output in `stdout`. Open the artifact before applying advice.
Curated power-ups for coding agents: skills, slash commands, MCP configs, hooks, AGENTS.md templates, and workflows for serious software engineering. Claude Code, Codex, Antigravity CLI, Cursor and more
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost…
Use when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test…
Use when designing, running, debugging, or hardening deterministic eval suites for agent skills, prompts, tool workflows, or…
Use when designing tool definitions for a new agent or subagent, an agent shows high retry rates, ambiguous tool invocations, or…
Use when routing a prompt to a local provider CLI for a second opinion, review, or plan -- you are about to call a provider…
Use when starting work in an unfamiliar area of a codebase, spawning a subagent that needs targeted file context, a first search…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.