MCPInstall

ga

by jnsahajAI & Agents

Kick off a new feature or fix in a parallel clone with Pi working autonomously. Takes a problem description, generates a concise branch name, runs ga to set up the worktree, and sends a crafted prompt to the new Pi session.

Installs
91
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/jnsahaj/skills --skill ga
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads ga automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

ga - Start a New Task

Kick off a new parallel development task. Creates a clone, branch, tmux session, and starts Pi with a crafted prompt.

Steps

  1. Get the task description from the user's message. If unclear, ask what they want to build or fix.

  2. Generate a concise branch name from the description:

    • Use lowercase kebab-case
    • Max 3-4 words, abbreviate aggressively
    • Prefix with fix- for bug fixes
    • Examples:
      • "the login button doesn't work on mobile" → fix-mobile-login-btn
      • "add a dark mode toggle to settings" → dark-mode-toggle
      • "search results are slow when filtering by date" → fix-search-date-perf
      • "implement rate limiting on the API" → api-rate-limit
      • "the sidebar collapses when resizing" → fix-sidebar-resize
      • "add webhook support for deployments" → deploy-webhooks

  3. Build the prompt that Pi will receive in the new session. The prompt MUST follow this structure:

    <Clear description of the problem or feature>

<Any relevant context: file paths, error messages, specific behavior>

When you're done, run /create-draft-pr to commit, push, and open a draft PR.

    Keep the prompt direct and actionable. Don't over-explain. Include specific file paths or error details if the user mentioned them.

  4. Pick the harness. Default is pi, so omit the flag for normal use. If the user's message explicitly asks for Claude Code (e.g. "use claude", "with claude", "claude harness"), pass --harness c.

  5. Run ga with the branch name, prompt, and base branch. The ga function accepts a second argument for the prompt and a third for the base branch, which skips the fzf picker:

    ga <branch-name> "<prompt>" main
# or explicitly with Claude Code:
ga --harness c <branch-name> "<prompt>" main

    If ga is not found, source ~/.zshrc first and then run it again, since in some environments ga is defined as a shell function rather than an executable.

  6. Report back to the user with the branch name and tmux session name so they can attach:

    Started: <session-name>
Branch: <branch-prefix>/<branch-name>
Attach: tmux a -t <session-name>

Rules

  • Branch names must be short. 3-4 words max. Abbreviate (btn, auth, cfg, nav, perf, err, msg, req, res, fmt, val, tmpl, env, deps).
  • Always include the /create-draft-pr instruction in the prompt.
  • The prompt should be a single clear message, not a multi-step plan. Let Pi figure out the implementation.
  • If the user provides file paths or error messages, include them verbatim in the prompt.
  • Don't over-specify. Trust Pi to explore the codebase and find the right approach.

FAQ

What does the ga skill do?

Kick off a new feature or fix in a parallel clone with Pi working autonomously. Takes a problem description, generates a concise branch name, runs ga to set up the worktree, and sends a crafted prompt to the new Pi session.

How do I install ga?

Run npx skills add https://github.com/jnsahaj/skills --skill ga in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/ga/ (personal) or .claude/skills/ga/ (project).

Which AI agents can use ga?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is ga safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains ga?

It is published by jnsahaj in jnsahaj/skills. It has 91 recorded installs.

More from jnsahaj/skills

View all →

zero-tech-debt

jnsahaj/skills

Rework a change as if the intended UX and architecture existed from day one, deleting compatibility cruft and accidental complexity.

Frontend & Design544 installs

code-refactor-review

jnsahaj/skills

Open the skill to read its SKILL.md instructions.

Code Quality & Workflow175 installs

ux-flow-plan

jnsahaj/skills

Open the skill to read its SKILL.md instructions.

Frontend & Design141 installs

pit-of-success

jnsahaj/skills

Open the skill to read its SKILL.md instructions.

130 installs

prepare-branch-context

jnsahaj/skills

Analyze the current branch's diff from main and related PR to build context for followup requests. Triggers on "prepare context", "branch context", "catch me up", "what's on this branch".

Code Quality & Workflow105 installs

create-draft-pr

jnsahaj/skills

Open the skill to read its SKILL.md instructions.

Code Quality & Workflow104 installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs