nano-banana-pro-openrouter
Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skill_exec when a meta-skill needs local image files and structured IMAGE_READY records without spawning an LLM agent.
git clone --depth 1 https://github.com/opensquilla/opensquilla /tmp/nano-banana-pro-openrouter && cp -r /tmp/nano-banana-pro-openrouter/src/opensquilla/skills/bundled/nano-banana-pro-openrouter ~/.claude/skills/nano-banana-pro-openrouterSKILL.md
# Nano Banana Pro OpenRouter Adapter
This skill is a deterministic adapter around OpenRouter image generation. It is
intended for meta-skill `skill_exec` use, not as an open-ended agent surface.
## Contract
- During MetaSkill execution, accepts only the parent-resolved, process-local
provider lease. The credential, endpoint, and proxy never enter `with`, argv,
the plan, or persisted run data. Direct standalone CLI use may still provide
`OPENROUTER_API_KEY`.
- Does not read `.env` files, prompt for credentials, print credentials, or
write credentials to disk.
- Uses only the model, base URL, output directory, and local path prefix passed
by the caller.
- Saves generated image bytes under the supplied output directory.
- Emits one `IMAGE_READY:` JSON line per saved image.
- A missing/invalid required MetaSkill lease exits 78 before any provider
submission. Provider failures after submission emit `IMAGE_GENERATION_FAILED`
with exit 0 so the webpage can bind a replacement slot without auto-replay.
## Meta-Skill Payload Mode
When stdin is JSON containing `media_slots`, `image_slots`, `slots`, or
`page_outline`, the adapter generates image slots and preserves already
downloaded images. Structured slots are preferred over free-form outline text:
```json
{
"requirement_framing": "...",
"media_slots": {"slots": [{"slot_id": "hero-visual", "modality": "image"}]},
"page_outline": "...",
"image_download": "...",
"include_images": "YES",
"visual_style": "..."
}
```
Existing `IMAGE_READY:` records in `image_download` are preserved. If
`IMAGE_DOWNLOAD_INCOMPLETE:` lists `unfilled_slot_ids`, only those slots are
generated. If the caller requested images but both structured slots and outline
slot parsing are empty, the adapter synthesizes minimal webpage-safe image
slots from the brief instead of emitting `no_image_slots_to_generate`.
## Plain Prompt Mode
When stdin is plain text, the adapter generates one image using that text as the
prompt and the `--filename` stem as the `slot_id`.Submit audio or video for multilingual dubbing, poll status, and download dubbed audio. Use when the user asks for dubbing, 多语言配音, 视频翻译配音, 译制片, or wants a source clip dubbed into another language.
Generate a structured short-video shooting script from a topic. Emits a strict, machine-parseable shot list (3 shots by default) with image prompt + video prompt + voiceover + on-screen text per shot. Trigger when the user asks for a video script, 分镜, 短视频文案, AI视频, 短剧脚本, or wants visual prompts ready for image/video generation.
Use when the user asks to schedule recurring tasks, one-off reminders, timers, or cron-style jobs through the OpenSquilla cron tool.
Multi-round research with explicit methodology, evidence tracking, and citation-tagged synthesis. Trigger on 'deep dive', 'research report', 'literature review', 'investigate X across sources', 'multi-round investigation'. Distinct from the `summarize` skill, which is a single-pass condensation; this skill maintains a state file across iterations, tracks coverage, and produces a long-form report with per-claim citations. Three execution stages: plan (scope into sub-questions), iterate (record evidence per round), compile (synthesize report). The skill itself does not fetch the web — it tells the host agent which fetches to perform via OpenSquilla's existing web tools, and records what comes back.
Read, edit, or create Microsoft Word `.docx` files. Trigger this skill whenever the user mentions a Word document, .docx file, contract, report, brief, memo, or asks to extract text, modify an existing doc, generate one from a brief, or audit tracked changes. Three execution paths: text-and-structure extraction, in-place edit-by-run (preserves styles), and create-from-scratch with python-docx. Falls back to OOXML unzip-and-patch for layout work python-docx cannot reach.
Capture the current git diff (staged, working-tree, or staged file list) as text. Direct shell call for workflows that need repository diffs without an LLM agent loop.
GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.
Query the per-turn DecisionEntry log for skill co-occurrence patterns, meta-skill usage stats, and the router fixture corpus. Returns a JSON summary suitable for downstream LLM consumption. Used by meta-skill-creator's harvest step but also useful standalone for 'which skills did I use most this week?'