一键在 Manus 中运行任何 Skill

gemini

星标0

分支0

更新时间2026年4月9日 14:47

Run tasks through the Gemini CLI and then review, verify, and evaluate the resulting changes. Use when the user asks to delegate work to Gemini (or says "use gemini") and expects a follow-up review of the edits, diffs, or outputs.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

Unintendedsideeffects

Unintendedsideeffects/Skills-And-Agents

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

Gemini

Delegate a task to Gemini CLI in yolo (auto-approve) mode, then validate and evaluate the resulting changes before reporting back.

Workflow

1) Prepare the prompt

Restate the task as a single, focused instruction.
Include relevant file paths, constraints, and expected outputs.
Keep the prompt concrete — Gemini will act on it directly without further confirmation.

2) Choose execution path

Path A — running inside Claude Code (you ARE Claude Code): Do NOT spawn a nested claude process. Use the Bash tool to run the script directly:

skills/gemini/scripts/run.sh "Your task prompt here"

Optional model override:

skills/gemini/scripts/run.sh "Your task prompt here" --model gemini-2.5-pro

Or set GEMINI_MODEL in the environment to avoid repeating the flag.

Path B — running as an external agent (bash, CI, orchestrator):

scripts/run.sh "Your task prompt here"

The script validates that gemini is on PATH and runs gemini --yolo --prompt "<prompt>".

3) Review the result

After Gemini finishes, inspect what changed:

git status -sb
git diff --stat
git diff

Verify changes match the requested scope.
Look for unintended file deletions, renames, or edits outside the target area.
Check that project conventions (formatting, naming, test coverage) are preserved.

4) Evaluate and report

Summarize what Gemini changed and whether it satisfies the request.
Flag any concerns: regressions, missing tests, out-of-scope edits.
If changes are unexpected or destructive, ask the user before reverting.

Model Selection

Model	Best for
`gemini-2.5-pro` (default)	Complex multi-file refactors, reasoning-heavy tasks
`gemini-2.0-flash`	Fast, focused edits; simple one-file tasks

Override via --model flag or GEMINI_MODEL env var.

Safety Notes

--yolo skips all confirmation prompts. Gemini will write files immediately.
Always run in a clean git state so changes are easy to inspect and revert.
If the working tree is dirty before the run, stash first: git stash.

Files

scripts/run.sh: validate gemini is installed and invoke gemini --yolo --prompt "<prompt>".

同仓库更多 Skills

同仓库

claude-diff-review

Unintendedsideeffects/Skills-And-Agents

Run Claude CLI in non-interactive mode to review git diffs between branches or commits and return severity-ordered findings with file references. Use when a user asks for a "Claude review", wants a second-opinion code review from Claude, or needs fast triage of a large branch diff like master...feature.

2026-04-090

claude-planner

Unintendedsideeffects/Skills-And-Agents

Create strict JSON execution plans with Claude Code and return machine-readable handoff objects for planner-executor workflows. Use when a user asks for a 2-step planner to executor pipeline, wants Claude to produce a structured plan schema, or needs validated plan JSON before step-by-step execution.

2026-04-090

copilot-delegate

Unintendedsideeffects/Skills-And-Agents

Delegate a bounded local coding task to the Copilot CLI, either as a single non-interactive run or as multiple tmux workers with per-task logs. Use when the user explicitly wants local `copilot --yolo` execution with strict file ownership, prompt files, and post-run review.

2026-04-090

dead-code

Unintendedsideeffects/Skills-And-Agents

Detect and remove dead/unused code using language-appropriate static analysis tools (ruff+vulture, knip, cargo clippy, golangci-lint, etc.). Use when cleaning up after vibe-coding, AI-generated code, or any session that may have left unused imports, dead functions, or unreachable exports.

2026-04-090

gh-request-copilot-review

Unintendedsideeffects/Skills-And-Agents

Request or re-request GitHub Copilot review on the open PR for the current branch, or on a specified PR number, using gh CLI; verify gh auth first, trigger the reviewer request, and confirm GitHub recorded a fresh review request event.

2026-04-090

home-assistant-docker-update

Unintendedsideeffects/Skills-And-Agents

Update a Docker-based Home Assistant deployment to the latest stable image and verify the service is healthy afterward. Use when a user asks to upgrade Home Assistant, check whether a Docker-based HA update is safe, or recover Home Assistant after an image refresh.

2026-04-090

name	gemini
description	Run tasks through the Gemini CLI and then review, verify, and evaluate the resulting changes. Use when the user asks to delegate work to Gemini (or says "use gemini") and expects a follow-up review of the edits, diffs, or outputs.

Gemini

Delegate a task to Gemini CLI in yolo (auto-approve) mode, then validate and evaluate the resulting changes before reporting back.

Workflow

1) Prepare the prompt

Restate the task as a single, focused instruction.
Include relevant file paths, constraints, and expected outputs.
Keep the prompt concrete — Gemini will act on it directly without further confirmation.

2) Choose execution path

Path A — running inside Claude Code (you ARE Claude Code): Do NOT spawn a nested claude process. Use the Bash tool to run the script directly:

skills/gemini/scripts/run.sh "Your task prompt here"

Optional model override:

skills/gemini/scripts/run.sh "Your task prompt here" --model gemini-2.5-pro

Or set GEMINI_MODEL in the environment to avoid repeating the flag.

Path B — running as an external agent (bash, CI, orchestrator):

scripts/run.sh "Your task prompt here"

The script validates that gemini is on PATH and runs gemini --yolo --prompt "<prompt>".

3) Review the result

After Gemini finishes, inspect what changed:

git status -sb
git diff --stat
git diff

Verify changes match the requested scope.
Look for unintended file deletions, renames, or edits outside the target area.
Check that project conventions (formatting, naming, test coverage) are preserved.

4) Evaluate and report

Summarize what Gemini changed and whether it satisfies the request.
Flag any concerns: regressions, missing tests, out-of-scope edits.
If changes are unexpected or destructive, ask the user before reverting.

Model Selection

Model	Best for
`gemini-2.5-pro` (default)	Complex multi-file refactors, reasoning-heavy tasks
`gemini-2.0-flash`	Fast, focused edits; simple one-file tasks

Override via --model flag or GEMINI_MODEL env var.

Safety Notes

--yolo skips all confirmation prompts. Gemini will write files immediately.
Always run in a clean git state so changes are easy to inspect and revert.
If the working tree is dirty before the run, stash first: git stash.

Files

scripts/run.sh: validate gemini is installed and invoke gemini --yolo --prompt "<prompt>".