From cli-wrapper
Wrapped access to Gemini CLI. Captures gemini --help, caches subcommands, validates flags, post-processes output. Use for ANY Gemini CLI invocation from Claude Code or other harnesses. Saves ~85% tokens vs raw gemini output.
How this skill is triggered — by the user, by Claude, or both
Slash command
/cli-wrapper:gemini-cliThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Wrapped Gemini CLI access. Digest-driven, token-optimized.
Wrapped Gemini CLI access. Digest-driven, token-optimized.
/gemini-cli invoke <args> — run gemini command with validated flags
/gemini-cli explain <cmd> — show what a gemini subcommand does
/gemini-cli audit — token savings report
/gemini-cli wrap — rebuild digest from live gemini --help
Gemini CLI help output ~4KB+. Digest = ~350 bytes. 91% savings.
| Phase | Raw | Wrapped |
|---|---|---|
| Discovery | 4.1KB | 0.35KB |
| Invocation | variable | filtered + deduped |
| Flag validation | trial/error | first-try via digest |
/gemini-cli invoke --version
/gemini-cli invoke config list
/gemini-cli invoke extensions list
/gemini-cli invoke agent run <name>
.claude/cli-wrappers/gemini.json — auto-refreshed on /gemini-cli wrap
When Claude Code delegates to Gemini CLI, always use this wrapper.
The wrapper agent gemini-cli handles the full delegation lifecycle.
npx claudepluginhub andersonlimahw/lemon-ai-hub --plugin cli-wrapperGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.