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.

Use this meta-skill instead of answering directly when the user wants to turn an idea, research, notes, talk, or document into publishable blog, social, Xiaohongshu, Zhihu, slide, newsletter, or short-video content through multi-skill orchestration.

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

Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCK_WITH_OVERRIDE / PASS_WITH_NOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.

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.

Read, inspect, edit, or create Microsoft Excel `.xlsx` workbooks, including structured data extraction, formula-aware cell edits, and workbook generation from rows.

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.

Turn a single still image (PNG/JPG) into a short MP4 with a slow Ken-Burns zoom and a silent audio track. Pure ffmpeg wrapper. Designed as the on_failure substitute for AI video-gen steps that get blocked by content moderation: when seedance refuses, this skill emits a valid replacement clip from the already-generated still so a downstream merge can still produce a complete deliverable.

Concatenate a directory of numbered MP4 segments (1_*.mp4, 2_*.mp4, ...) into one MP4 with optional fade transitions, unified resolution/fps/codec. Pure ffmpeg wrapper, no LLM. Trigger when a workflow has produced several short clips that need stitching into a final reel.

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 deterministic programmatic PDF work — examples: pull tables from a report, combine three PDFs, extract pages 5-12, fill a tax form, or build a new PDF from data. This is the single public PDF entry and uses pypdf, pdfplumber, and reportlab.

Render a static title / ending card PNG with Pillow. Centered headline + optional subtitle on a solid-colour background. Uses managed or platform CJK fonts with glyph verification and fails actionably instead of rendering tofu. Pure deterministic, no LLM, no network. Used by meta-short-drama for opening and closing cards.

Read, inspect, edit, or create PowerPoint `.pptx` presentations, including text extraction, template-preserving changes, slide review, and generation from a brief.

Read a UTF-8 text file and emit its raw content on stdout. Tiny helper for meta-skills that need to round-trip an artefact through disk so the user can hand-edit it between steps (e.g. tweak script.txt during a review pause). Unlike the builtin read_file tool — which returns line-numbered output for model display — this returns bytes verbatim, suitable for downstream parsers.

Burn an SRT subtitle file into an MP4 via ffmpeg's subtitles filter (libass). Single-pass re-encode of video; audio copied as-is. Uses a verified managed Noto Sans CJK font when available. Used by meta-short-drama as the final subtitling step after merge.

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 here). Prefer non-interactive CLI modes such as codex exec, claude --print, opencode run, or pi -p.

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.

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.

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.

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 repo is named (e.g. 'write a function that maps A-Z to pitches'), use `--verification-mode scratch` with no --repo: it scaffolds a throwaway project, writes the code plus a test, and verifies it green. Only truly trivial one-liners or conceptual/non-testable questions are answered inline.

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.