paper-latex-sanitizer
Deterministically normalize safe LaTeX punctuation and replace unsupported forecast magnitudes with explicit placeholders before meta-paper-write publication gates run.
git clone --depth 1 https://github.com/opensquilla/opensquilla /tmp/paper-latex-sanitizer && cp -r /tmp/paper-latex-sanitizer/src/opensquilla/skills/bundled/paper-latex-sanitizer ~/.claude/skills/paper-latex-sanitizerSKILL.md
# Paper LaTeX sanitizer
Internal deterministic pre-publication sanitizer for `meta-paper-write`.
It runs before the length, citation, and publication-quality gates.
The sanitizer performs only two bounded repairs:
- normalize U+2011, U+2013, and isolated U+2014 punctuation to LaTeX-safe
ASCII equivalents while preserving paired Chinese em dashes (`——`);
- when `EVIDENCE_STATUS: not_supplied`, replace concrete forecast magnitudes
in results-facing sections with `TBD` / `待实验确定`. Planned setup values
remain intact. A declared result threshold remains intact only when the same
magnitude is present in the authoritative user request/paper contract;
labeling an invented number as a target or hypothesis does not preserve it;
- remove only the known generated `figure_placeholder_template` or
`table_placeholder_template` input line when the same manuscript already
contains the corresponding inlined figure/table environment. Arbitrary user
`\input{...}` commands and non-redundant template inputs remain untouched.
For an artifact-backed package, the referenced `MANUSCRIPT_PATH` is replaced
atomically and the compact manifest is returned. Inline manuscript packages
are normalized in the returned package. This step is not a quality gate: the
independent `paper-quality-gate` must still run afterwards and block any
unsupported semantic claims that remain.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?'