Skip to main content
ClaudeWave
Skill6.9k repo starsupdated 2d ago

paper-quality-gate

Deterministic pre-compile gate for meta-paper-write. Enforces length/citation verdicts and rejects unsupported empirical-result claims when no user evidence was supplied.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/opensquilla/opensquilla /tmp/paper-quality-gate && cp -r /tmp/paper-quality-gate/src/opensquilla/skills/bundled/paper-quality-gate ~/.claude/skills/paper-quality-gate
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Paper quality gate

Internal deterministic gate used after bounded LaTeX sanitization and
immediately before compilation. Input is a JSON object containing
`paper_contract`, `length_gate`, `citation_gate`, and `manuscript_package`.
The preceding sanitizer may normalize safe punctuation and replace detected
forecast magnitudes with explicit placeholders, but this gate remains an
independent fail-closed audit of the resulting artifact.

The command exits non-zero when an upstream LLM gate blocks, when a required
verdict marker is absent, when the manuscript artifact cannot be read, or when
an evidence-free manuscript presents empirical findings as completed results.
It also rejects concrete English or Chinese predicted outcome numbers (for
example, an anticipated 12% improvement) when evidence is absent. Experimental
setup parameters remain allowed; a predefined metric target such as 50%
accuracy is also allowed when the unknown time-to-target remains nonnumeric.
Explicitly conditional claims and planned significance thresholds are not
treated as observed findings. Unknown outcomes must use `TBD` / `待实验确定`
instead of invented point estimates.

Every figure/table caption is audited independently when evidence is absent.
Categorical outcome claims such as "the proposed method achieves lower cost"
or "所提方法保持最低通信成本" are blocked. Neutral planned placeholders and
explicit hypotheses/future tests remain valid, including captions that state
concrete setup values.

The gate also rejects literal Unicode Greek math glyphs, Unicode en dashes, and
single Latin-style em dashes in the manuscript. Paired Chinese em dashes
(`——`) remain valid native-language punctuation. Authors should use named
LaTeX math macros such as `\(\alpha\)` / `\(\varepsilon\)` and LaTeX `--` /
`---` punctuation, avoiding silent missing-glyph degradation in XeLaTeX.
advanced-dubbing-studioSkill

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.

ai-video-scriptSkill

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.

cronSkill

Use when the user asks to schedule recurring tasks, one-off reminders, timers, or cron-style jobs through the OpenSquilla cron tool.

deep-researchSkill

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.

docxSkill

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.

git-diffSkill

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.

githubSkill

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.

history-explorerSkill

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?'