opensquilla

PREFERRED way to change code in a REAL repository: fix a GitHub issue, fix a bug, add/implement a function or feature, or make any edit to a project the user names by a filesystem path (e.g. /tmp/foo, ~/code/bar) or a git URL. Clones the repo, runs an OpenSquilla agent on the host to make the change on a task branch, then independently VERIFIES it with a red→green→regression test loop and reports a structured result. STRONGLY prefer this over hand-editing the user's files yourself in this session: editing files directly skips the isolation and the runner-verified red→green proof, so it is not equivalent. Use it whenever the request names a real on-disk repo/path or a repo URL and asks to fix/add/implement/change code. Examples: 'fix issue 412 in github.com/acme/widgets', '给 /tmp/calc 加个 average 函数', '帮我改一下 ~/proj 里的 X', 'implement CSV export in my project'. Docker-free host execution; treat the target repo as TRUSTED. GitHub issue mode needs the `gh` CLI. For self-contained, TESTABLE code from scratch when NO

Convert multi-search-engine JSON to a minimal BibTeX file (@misc{} entries). Demo-only.

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.

Build an SRT subtitle file from a 3-shot short-drama script (ai-video-script OUTPUT FORMAT). Reads each SHOT_N block's DURATION_S + VOICEOVER, emits cumulative-timestamped SRT cues. Pure text-processing, no LLM, no network. Used by meta-short-drama between merge and the final subtitle-burn step.

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.

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.

OpenSquilla-compatible audio generation adapter for webpage audio requests. Prefer OpenRouter config/API key in OpenSquilla; preserve the upstream CellCog workflow only as optional ClawHub provenance.

Deterministic image downloader for AwesomeWebpageMetaSkill search results. Use as skill_exec to fetch candidate image URLs into the configured local project tree without sandboxed shell curl.

Single-pass mini research for AwesomeWebpageMetaSkill: produce a short cited topic brief from one bounded web-search round. Not a general deep-research replacement.

Build a local multimedia webpage project from a user topic, audience, language, style, and media preferences by framing requirements, researching, planning, acquiring media, generating files, packaging, validating, repairing, and delivering usage guidance.

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.

Advanced filesystem operations - listing, searching, batch processing, and directory analysis for Clawdbot

Expert HTML development skill for building web pages, forms, and interactive content. Use when creating HTML documents, structuring web content, implementing semantic markup, adding forms and media, working with HTML5 APIs, or needing HTML templates, best practices, and accessibility guidance. Supports modern HTML5 standards and responsive design patterns.

Use this meta-skill instead of answering directly when a child or their guardian wants to plan a school project, science fair entry, hobby kit, or kid-sized creative venture (volcano model, bug-watching YouTube channel, magnet maze, model rocket). The skill assesses feasibility against the child's age band, builds an age-appropriate step plan, lists materials with budget substitutes, surfaces safety considerations, and produces a parent-facing learning-objective summary so the guardian can supervise meaningfully. Refuses inappropriate or unsafe projects.

Use this meta-skill instead of answering directly when the current user asks to draft, repair, compile, or produce an 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 for web research reports, slide decks, document decisions, or generic plotting.

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, pauses for one free-form review (the user can approve, adjust render style / character / shot count / shot details, or cancel in plain language), optionally re-drafts the script with the user's adjustments, 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,

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.

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 or declare a configured OpenRouter video asset for AwesomeWebpageMetaSkill. Use only when the meta skill needs a local webpage video and the provider, model, API key, and output directory come from config.

Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".

Delegate a self-contained task to a sub-Agent (Codex, Claude Code, or Pi via background process). The original use case was coding tasks — building features, reviewing PRs, refactoring — but the skill is the generic "spawn a sub-Agent with full tool surface" slot used by meta-skill DAG steps for any LLM-driven sub-task (policy review, trace parsing, report synthesis, document generation). Renamed from ``coding-agent`` to reflect actual usage; the wrapped CLIs (codex / claude / pi) still bias toward coding workloads. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative tasks that need file exploration, (5) meta-skill steps requiring full tool/LLM agency. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents

Run SWE-bench instances with an OpenSquilla agent inside the official Docker images. Trigger when the user wants to run/solve/evaluate a SWE-bench instance (e.g. 'run django__django-16429', 'test OpenSquilla on SWE-bench', '跑一道 SWE-bench 题'), benchmark the agent on SWE-bench_Verified or SWE-bench_Multilingual, or check whether a generated patch resolves an instance. Optional dependency — install via `pip install opensquilla[swebench]`; also needs the docker CLI and an OPENROUTER_API_KEY.

This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources.

Fetch the day's top arXiv submissions in a chosen category, write a structured per-paper digest, render the digest as a PPTX deck (one slide per paper), and persist the digest to long-term memory. Use for a daily 'arxiv morning briefing' — manual fire or cron-scheduled.

Auditable compliance bundle: deep-research with citations → signable .docx report → read-only PDF archive → memory note of audit findings.

Scan a target codebase path, classify the most informative diagram kind, then render it as BOTH a PlantUML source file AND a draw.io XML in parallel, and compose them into a single architecture doc. Use when writing an RFC or onboarding doc and you want a text-friendly (PlantUML) and an editable (drawio) view of the same architecture.

Inspect the user's open GitHub PRs / failing CI / new issues via `gh`, summarize into 3 buckets (to-review / awaiting-me / CI-red), and persist follow-ups to memory.

[DEPRECATED] Build watchdog — launches arbitrary commands from the user message in tmux and lets sub-agent auto-apply a fix. Disabled pending the E5 bounded sub-agent contract + Jinja sandbox + side-effect ledger (plan §3.1 A1/A8 / §5.3 E4): the launch task interpolates raw user_message into a shell-bound tmux session and the heal step lets sub-agent mutate state with no rollback. Do not re-enable without `metadata.opensquilla.risk: high` + capabilities {shell, tmux, filesystem-write, subprocess} and a saga-style compensation step.

Use this meta-skill instead of answering directly when the user needs PDF analysis, pasted PDF excerpt analysis, digesting, comparison, or question answering that benefits from multi-skill orchestration across PDF extraction, summarization, cross-document synthesis, traceable evidence indexing, and memory capture.

Run three quality gates (ruff + mypy + pytest) in parallel over the staged diff, then arbitrate a single BLOCK/APPROVE verdict. Use before committing changes locally when you want a comprehensive pre-commit gate beyond per-file linting — exactly the same gate set CI enforces.

Compose a morning digest combining local weather, news for the user's interest topic, a structured summary, and a memory note.

Compose three independent security gates over a candidate operation — policy/governance review, secret/credential scan, and audit-log emit — then arbitrate the verdicts with a strict priority rule (governance DENY > scanner WARN > ALLOW). Use when reviewing a proposed code change, script, or environment manipulation for safety.

Turn an Excel workbook into business insight: structured read → trend/anomaly summary → write back to a new 'Insights' sheet → persist KPIs to memory.

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 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.

Create and register cloned voices for later TTS only when the speaker has explicit consent. Use when the user asks for voice clone, clone voice, 克隆音色, 复刻声音, or wants a reusable voice_id.

Convert a local source recording into an authorized target voice. Use when the user asks for voice conversion, voice changer, 换声, 变声, 音色转换, or converting existing narration to another approved voice.

Generate narration, product voiceover, IVR prompts, podcast reads, or short-video VOICEOVER audio through OpenSquilla audio tools. Use when the user asks for TTS, 配音, 旁白, 口播, audio narration, or wants script text turned into a playable audio artifact.

[DEPRECATED] Issue-to-PR autopilot — opens a PR via `gh`, runs a sub-agent fix loop, and writes to git. Disabled pending the E5 bounded sub-agent contract + side-effect ledger (plan §3.1 A8 / §5.3 E4): no risk metadata enforcement, no per-step budget, no rollback path. Do not re-enable without `metadata.opensquilla.risk: high` + capabilities {vcs, filesystem-write, network-write, subprocess} and a saga-style compensation step.

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.