← All skill packs

AI Agent Workflow Collection

Skill pack
20 skills0 selected
hugotownSkills in this pack

Print the currently-installed airc version (short git SHA, branch, commit subject, install dir). Use this to verify everyone in a mesh is on the same build.

English

Use when working with ANY Gemini API skill (image generation/nano banana, image understanding, document/PDF processing, Google Search grounding, Deep Research). Provides shared setup: API key location, SDK install (Python/JS), model picker, output folder conventions (gemini-output/), and the ask-vs-direct rule for parameter defaults.

English

Use when analyzing, describing, or extracting information FROM images with Gemini vision. Triggers — "describe this image", "caption", "OCR this", "extract text from screenshot", "what's in this picture", "classify this", "detect objects", "find bounding boxes", "segment", "count items", "read this receipt/invoice", "annotate", "compare two images", "find allergens on this label". NOT for generating new images (see gemini-image-generation).

English

Use when installing, upgrading, or migrating the official Gemini API SDK (Google GenAI SDK) in any language — Python google-genai, JavaScript/TypeScript @google/genai, Go google.golang.org/genai, Java com.google.genai, C Google.GenAI. Also use when migrating off the deprecated google-generativeai / @google/generativeai packages (sunset 2025-11-30).

English

Generate an AI-SPEC.md design contract for phases that involve building AI systems.

English

Capture ideas, tasks, notes, and seeds to their…

English

Configure GSD settings — workflow toggles, advanced knobs, integrations, and model…

English

Socratic ideation and idea routing — think through ideas before committing to…

English

Ingest external plans with conflict detection against project decisions before writing anything.

English

Triage and review open GitHub issues and PRs against project templates and contribution guidelines.

English

Plan a phase as a vertical MVP slice — user story, SPIDR splitting, then…

English

codebase intelligence | map graphify docs…

English

project lifecycle | milestones audits…

English

workflow | discuss plan execute verify phase…

English

CRUD for phases in ROADMAP.md — add, insert, remove, or edit…

English

Sketch UI/design ideas with throwaway HTML mockups, or propose what to sketch next (frontier…

English

[BETA] Offload plan phase to Claude Code's ultraplan cloud; review in browser and import back.

English

Safe git revert. Roll back phase or plan commits using the phase manifest with dependency checks.

English

Update GSD to latest version with changelog…

English

Contributor-only skill: create a new host config for gstack's multi-host system. NOT installed for end users. Only usable from the gstack source repo.

English

Includes Airc:version, Gemini Common, Gemini Image Understanding, and other workflows.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Pack stats

Skills20CategorygeneralStars0

What’s included

Airc:version

Print the currently-installed airc version (short git SHA, branch, commit subject, install dir). Use this to verify everyone in a mesh is on the same build.

Gemini Common

Use when working with ANY Gemini API skill (image generation/nano banana, image understanding, document/PDF processing, Google Search grounding, Deep Research). Provides shared setup: API key location, SDK install (Python/JS), model picker, output folder conventions (gemini-output/), and the ask-vs-direct rule for parameter defaults.

Gemini Image Understanding

Use when analyzing, describing, or extracting information FROM images with Gemini vision. Triggers — "describe this image", "caption", "OCR this", "extract text from screenshot", "what's in this picture", "classify this", "detect objects", "find bounding boxes", "segment", "count items", "read this receipt/invoice", "annotate", "compare two images", "find allergens on this label". NOT for generating new images (see gemini-image-generation).

Gemini Libraries

Use when installing, upgrading, or migrating the official Gemini API SDK (Google GenAI SDK) in any language — Python google-genai, JavaScript/TypeScript @google/genai, Go google.golang.org/genai, Java com.google.genai, C Google.GenAI. Also use when migrating off the deprecated google-generativeai / @google/generativeai packages (sunset 2025-11-30).

Gsd AI Integration Phase

Generate an AI-SPEC.md design contract for phases that involve building AI systems.

Gsd Capture

Capture ideas, tasks, notes, and seeds to their destination

Gsd Config

Configure GSD settings — workflow toggles, advanced knobs, integrations, and model profile

Gsd Explore

Socratic ideation and idea routing — think through ideas before committing to plans

Gsd Import

Ingest external plans with conflict detection against project decisions before writing anything.

Gsd Inbox

Triage and review open GitHub issues and PRs against project templates and contribution guidelines.

Gsd Mvp Phase

Plan a phase as a vertical MVP slice — user story, SPIDR splitting, then plan-phase

Gsd Ns Context

codebase intelligence | map graphify docs learnings

Gsd Ns Project

project lifecycle | milestones audits summary

Gsd Ns Workflow

workflow | discuss plan execute verify phase progress

Gsd Phase

CRUD for phases in ROADMAP.md — add, insert, remove, or edit phases

Gsd Sketch

Sketch UI/design ideas with throwaway HTML mockups, or propose what to sketch next (frontier mode)

Gsd Ultraplan Phase

[BETA] Offload plan phase to Claude Code's ultraplan cloud; review in browser and import back.

Gsd Undo

Safe git revert. Roll back phase or plan commits using the phase manifest with dependency checks.

Gsd Update

Update GSD to latest version with changelog display

Gstack Contrib Add Host

Contributor-only skill: create a new host config for gstack's multi-host system. NOT installed for end users. Only usable from the gstack source repo.

Quick start

  1. Choose your skills. Select individual skills above, or choose the entire pack.
  2. Copy the install prompt. Use Copy install prompt above the list.
  3. Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.

Try it with your agent

After installation, start with a request like:

Example request
Use the Airc:version skill to help with my task.
Ask me for the context you need before getting started.

Requirements & license

  • A coding agent that can access your project files and install skills.
  • Your agent checks each skill’s instructions, dependencies, and permissions during setup.
  • License details are not provided in these listings. Check the author’s terms before using the skills.
AI Agent Workflow Collection | Agent Skills Atlas