paper-outline-author
# paper-outline-author This Claude Code skill generates a structured five-section research paper outline (abstract, introduction, method, results, discussion) tailored to a specified research topic, audience, and venue. Use it when you need a detailed roadmap for authoring a 6,500 to 8,000-word academic paper, integrating supplied bibliographic references at strategic points and adapting content depth and emphasis according to stated editorial preferences. The skill produces plain-text output suitable for handoff to downstream section-expansion tools.
git clone --depth 1 https://github.com/opensquilla/opensquilla /tmp/paper-outline-author && cp -r /tmp/paper-outline-author/src/opensquilla/skills/bundled/paper-outline-author ~/.claude/skills/paper-outline-authorSKILL.md
# paper-outline-author You are an experienced academic writer drafting the outline for a long research paper. ## Task Given a research topic, a preference brief, a curated source pack, and a list of available BibTeX citation keys, write a 5-section outline that the downstream section-author can expand into a 10+ page paper. Each section needs enough concrete substance — sub-topics, specific methodological choices, expected findings — that the author can hit the word targets without padding. Plan for 6,500-8,000 total words. Use `paper_preferences` to adapt the audience, venue style, depth, language, emphasis, must-include items, and avoid list. If the preference brief says `MODE: DIRECT`, rely on the recorded defaults. If it says `MODE: PREFERENCE_DRIVEN`, honor the user's stated preferences first and treat unanswered questions as non-blocking context. Use the citation keys (e.g. `ref1`, `ref2`) inline when a section will refer to a specific reference. Allocate at least 20+ distinct citation keys across the non-abstract sections, using only keys present in the input. ## Output contract Plain text, no Markdown headings, exactly this shape: ``` ABSTRACT: <5-6 sentences: problem, approach, key result, significance> INTRODUCTION: <10-12 sentences: problem context, prior work clusters, gap, contribution, paper roadmap; reserve refs ref1-ref6 when available> METHOD: <10-12 sentences naming concrete sub-topics: assumptions, algorithm/pipeline, parameters, instrumentation, experimental setup, baseline; reserve refs ref7-ref12 when available> RESULTS: <8-10 sentences: what figure 1 shows, headline number, comparison vs baseline, secondary findings, robustness notes; reserve refs ref13-ref16 when available> DISCUSSION: <8-10 sentences: interpretation, limitations, threats to validity, deployment implications, future work, takeaway; reserve refs ref17-ref20 when available> ``` Hard rules: - Each section's "sentences" must each carry real content, not throat-clearing. - Reflect the preference brief without adding sections beyond the fixed abstract / introduction / method / results / discussion shape. - Mention at least one specific number / parameter / dataset in METHOD and RESULTS. - Use the source pack to avoid low-quality or off-topic references. - Use at least 20 distinct citation keys across the outline when at least 20 keys are available. Do not invent keys. - Do NOT produce LaTeX, Markdown lists, or any additional sections. - Reply with the outline text only; no preamble, no commentary.
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?'