{
  "markdown": "# openskills\n\nA curated collection of **agent skills** — reusable capability packs that plug into skill-aware coding agents like Codex, Claude, and Cursor. Each skill is self-contained: one folder, one `SKILL.md` entry point, plus the scripts and references needed to do the job well.\n\nThis repository is a **multi-skill collection**. The discovery convention is:\n\n```text\nskills/<skill-name>/SKILL.md\n```\n\nThat is the same collection layout used by repositories such as `obra/superpowers`, where one repo publishes multiple independently installable skills.\n\n## How This Collection Works\n\nYou can treat this repository in two ways:\n\n1. As a **collection**: install `GargantuaX/openskills` and let your agent discover any bundled skill.\n2. As a **package of individual skills**: install only the one sub-skill you want, such as `nanobanana` or `gpt-image-2`.\n\nIn other words, the repository itself is the distribution unit, while each `skills/<name>/` directory is an installable skill unit.\n\n## What is a skill?\n\nA skill is a small, versioned folder that teaches an agent how to perform a specific task reliably:\n\n- **`SKILL.md`** — the agent-facing manual: triggers, workflow, rules, examples.\n- **`scripts/`** — deterministic code the agent can execute instead of re-deriving logic.\n- **`references/`** — deep docs loaded on demand.\n- **`agents/`** — optional runtime-specific registration files (e.g. Codex YAML).\n\nSkills follow the [skill-creator](https://github.com/anthropics/skills) conventions: concise frontmatter (`name` + `description`), imperative workflow, one source of truth per topic.\n\n## Skills in this repo\n\n| Skill | Description |\n| --- | --- |\n| [gpt-image-2](./skills/gpt-image-2/) | Full OpenAI-compatible GPT Image 2 coverage: text-to-image, mask edits, multi-image batches, streaming, partial_images, and the Responses `image_generation` tool. |\n| [nanobanana](./skills/nanobanana/) | Gemini-native Nano Banana coverage for Nano Banana, Nano Banana 2, and Nano Banana Pro with custom endpoint support, dry runs, batch generation, and multi-reference edits. |\n\n## Repository layout\n\n```\nopenskills/\n└─ skills/\n   └─ <skill-name>/\n      ├─ SKILL.md\n      ├─ README.md        # optional, human-facing\n      ├─ agents/          # optional, runtime registration\n      ├─ references/      # optional, deep docs\n      ├─ scripts/         # optional, executable helpers\n      └─ assets/          # optional, templates and sample files\n```\n\n## Using a skill\n\nMost skills are designed to be consumed two ways:\n\n1. **By an agent** — install either the full collection or a single skill through [Skills](https://skills.sh/).\n2. **By hand** — read the skill's own `README.md` for human-facing setup, then run `scripts/` directly from a terminal.\n\nInstall the full collection:\n\n```powershell\npnpm dlx skills add GargantuaX/openskills\n```\n\nFor Codex specifically, a simpler option is to junction the repository's [`skills/`](./skills/) directory into your local agent skills root instead of copying skills into many agent-specific folders. See [.codex/INSTALL.md](./.codex/INSTALL.md).\n\nInstall one skill from the collection:\n\n```powershell\npnpm dlx skills add https://github.com/GargantuaX/openskills --skill nanobanana\npnpm dlx skills add https://github.com/GargantuaX/openskills --skill gpt-image-2\n```\n\n`skills.sh` ecosystem docs also show a shorthand form for single-skill installs:\n\n```powershell\npnpm dlx skills add GargantuaX/openskills@nanobanana\npnpm dlx skills add GargantuaX/openskills@gpt-image-2\n```\n\nPrefer the `--skill` form in human-facing docs when you want the most explicit command. Use the `owner/repo@skill` shorthand when brevity matters or when another tool expects a single package-like token.\n\nEach skill folder documents its own requirements, configuration, and commands. Start there.\n\n## Quick Setup\n\nFor the fastest path:\n\n1. Install the full repo with `pnpm dlx skills add GargantuaX/openskills`, or install one skill with either `pnpm dlx skills add https://github.com/GargantuaX/openskills --skill <name>` or `pnpm dlx skills add GargantuaX/openskills@<name>`.\n2. Open the target skill's `README.md`.\n3. Copy the repository-level `.env.example` or the skill's documented `.env` example, then set your own API key and endpoint.\n4. Run that skill's documented `--dry-run` command first to verify configuration before making live API calls.\n\nFor the current image skills, detailed setup and env vars are documented in [skills/gpt-image-2/README.md](./skills/gpt-image-2/README.md), [skills/gpt-image-2/references/config.md](./skills/gpt-image-2/references/config.md), [skills/nanobanana/README.md](./skills/nanobanana/README.md), and [skills/nanobanana/references/config.md](./skills/nanobanana/references/config.md).\n\n## Shared `.env` Strategy\n\nFor this collection, the recommended setup is to keep one shared `.env` at your project root and let each skill inherit from it.\n\nThe current lookup order is:\n\n1. `--env-file <path>`\n2. Process environment variables\n3. The nearest `.env` found by searching from the current working directory upward through parent directories\n4. Built-in defaults\n\nThis means you can place a single `.env` in a project root and run `gpt-image-2` or `nanobanana` from nested subdirectories without duplicating config files.\n\n## Adding a new skill\n\n1. Scaffold a new folder under `skills/` (e.g. via `skill-creator`).\n2. Write `SKILL.md` with a frontmatter `name` and a trigger-rich `description`.\n3. Put deterministic logic in `scripts/`, deep docs in `references/`, templates in `assets/`.\n4. Validate the layout (`quick_validate.py` from skill-creator, or equivalent).\n5. Add an entry to the **Skills in this repo** table above.\n\n## Conventions\n\n- Skills must be self-contained; do not share code across skills at the repo level.\n- Keep `SKILL.md` body ASCII-friendly when tooling reads it with the platform default encoding.\n- Prefer the standard library and zero third-party dependencies in `scripts/` unless there is a clear reason not to.\n- Never commit API keys or other secrets; rely on environment variables and `.env` files that are gitignored.\n\n## License\n\nMIT. See [LICENSE](./LICENSE).\n",
  "bytes": 6166,
  "sha": "d20dad70235de8596bcbfa96a4d0ab72b923baf1b32419b2412c2b2331e9ca7d",
  "repo_slug": "gargantuax/openskills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_gargantuax_openskills_gpt_image_2_3eea429c/readme"
}