opensquilla

Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to run G3 (positive smoke) and G4 (negative smoke) gates against a candidate meta-skill SKILL.md. Cross-vendor: fixture-generation LLM != classifier LLM. Returns JSON.

Internal tool (not user-invocable). Called by meta-skill-creator's persist step and by `opensquilla meta accept` CLI (Phase 2) to manage `~/.opensquilla/proposals/`: write_proposal / list / accept. Returns JSON.

Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to lint a candidate meta-skill SKILL.md against G1 (parse + reference check + xml_escape grep + structural lint) and G2 (scheduler dry-run with stub executors). Deterministic, sub-second, no LLM. Returns JSON diagnostics.

Render a single 3-15s video clip via Seedance 2.0. Supports two backends: OpenRouter (default, model bytedance/seedance-2.0) and the official Volcengine ARK / BytePlus ModelArk endpoint (model doubao-seedance-2-0-260128 / dreamina-seedance-2-0-260128). Accepts a structured English video prompt, optional first-frame image, and optional identity/style reference image. Trigger when the user asks for AI video clip generation, 分镜视频, seedance, or wants a short cinematic shot from a prompt + frame.

Read, edit, or create PowerPoint .pptx files. Trigger this skill whenever the user mentions a deck, slides, slide deck, presentation, or a `.pptx` filename — whether the goal is to extract text, modify an existing deck, build one from scratch, or prepare slides for review. Three execution paths are supported: text extraction (always available), template editing (unzip → patch slide XML → repack), and creation from scratch (python-pptx for Python or PptxGenJS for Node).

Structured `.pdf` operations: extract text/tables, merge pages from multiple PDFs, split a PDF by page ranges, fill PDF form fields, and generate fresh PDFs from JSON. Trigger when the user wants programmatic PDF work without natural-language rewriting — examples: pull tables from a report, combine three PDFs, extract pages 5-12, fill a tax form, or build a new PDF from data. Distinct from `nano-pdf`, which uses an LLM to rewrite a page from a sentence; this skill is deterministic byte-level work via pypdf, pdfplumber, and reportlab.

Curate search results and BibTeX entries into a reliable source pack for a long research paper.

Write one publication-style research-paper section as a bounded, citation-grounded LaTeX fragment from a writing plan, outline, citation plan, and optional figure/table context.

Revise independently drafted paper sections into one coherent LaTeX body before the abstract is written.

Convert normalized multi-search-engine results to minimal BibTeX, preserving real DOI, author, publication year, arXiv ID, source URL, and provenance metadata when available. Unknown years are omitted and duplicate DOI records collapse to one entry.

Extract paper-writing preferences from a user request before research and drafting, choosing direct generation defaults when the request does not require a preference interview.

Plot a results CSV (x, y_baseline, y_ours) as a two-line matplotlib chart and write a PDF. Demo-only.

Author a 5-section paper outline (abstract / introduction / method / results / discussion) for a research topic, citing supplied reference keys when relevant.

Demo-only stub experiment for meta-paper-write: generates a deterministic results.csv seeded by topic hash. Not real science.

Map paper claims to available BibTeX citation keys before section drafting.

Write the abstract after the paper body has been revised, using the final claims and evidence.

Generate or declare an OpenRouter video asset for AwesomeWebpageMetaSkill using a parent-leased Provider Settings connection and configured non-secret model/output values.

Edit PDFs with natural-language instructions using the nano-pdf CLI.

Generate or edit a single image via OpenRouter (google/gemini-3.1-flash-image-preview by default). Accepts a text prompt and optional --input-image for image-to-image editing. Trigger when the user asks for an AI image, illustration, concept art, product render, or wants to modify an existing image.

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.

Generate instrumental music, background beds, jingles, or sung songs with lyrics through OpenSquilla audio tools. Use when the user asks for BGM, music generation, 唱歌, 生成歌曲, lyrics to song, or a playable music audio artifact.

Query scholarly metadata and the web through Crossref, Brave, Tavily, and DuckDuckGo with a single CLI surface. Trigger when the user asks for research search, fact lookup, source discovery, or engine comparison. Results retain DOI, publication year, and authors when supplied by Crossref, then deduplicate by DOI, arXiv ID, or normalized URL. API-key engines gate themselves on the relevant environment variable; Crossref and DuckDuckGo need no key.

Use this meta-skill instead of answering directly only when the current user explicitly asks to create, compose, synthesize, or propose a new meta-skill that orchestrates multiple existing skills. It uses multi-skill orchestration for intent clarification, optional history mining, trigger-collision checks, linting, smoke/runtime gates, preview, and optional proposal persistence. Do not use it for creating a normal standalone skill, asking how meta-skills work, analyzing pasted skill lists, or discussing existing meta-skills.

Use this meta-skill instead of answering directly when the current user asks to generate an AI short-drama or 短剧 from a topic. The workflow infers render style, character identity, and shot count (1-10, default 5) from the request (filling in conservative defaults when missing), drafts a strict shot-by-shot shooting script, and pauses for a free-form review. A direct approval can continue; an adjustment only re-drafts and previews the script, then requires a second explicit approval before any external media call. After approval it generates one universal full-cast identity-reference image plus per-shot composition images, then per-shot video clips (each video anchored to BOTH the universal reference image and its own composition image so the character identity AND scene layout stay consistent), bookends them with a title card and an ending card, burns subtitles in the user's language, and saves the script alongside the final MP4. Do not use it for slide decks, document-decision analysis, single-image generation, isolated script writing, or pasted historical short-drama examples.

Use this meta-skill instead of answering directly when the current user asks to draft or produce a new academic/research paper or LaTeX manuscript. It uses multi-skill orchestration for manuscript workflows that need source search, citation planning, experiment or figure/table placeholders, drafting, length checks, citation integrity, and LaTeX/PDF compilation. Ordinary paper requests use a compact draft path; explicit full/PDF/long-form requests use the full manuscript path. Do not use it to repair or compile an existing manuscript, or for web research reports, slide decks, document decisions, or generic plotting.