Agent Skills › opensquilla/opensquilla › paper-quality-gate

paper-quality-gate

GitHub

作为论文生成的确定性前置检查门控，验证长度、引用及实证结果声明。拒绝无证据支持的预测数据和特定格式错误，确保稿件符合编译前质量规范。

src/opensquilla/skills/bundled/paper-quality-gate/SKILL.md opensquilla/opensquilla

Trigger Scenarios

论文生成后质量校验 LaTeX编译前内容审计

Install

npx skills add opensquilla/opensquilla --skill paper-quality-gate -g -y

More Options

Non-standard path

npx skills add https://github.com/opensquilla/opensquilla/tree/main/src/opensquilla/skills/bundled/paper-quality-gate -g -y

Use without installing

npx skills use opensquilla/opensquilla@paper-quality-gate

指定 Agent (Claude Code)

npx skills add opensquilla/opensquilla --skill paper-quality-gate -a claude-code -g -y

安装 repo 全部 skill

npx skills add opensquilla/opensquilla --all -g -y

预览 repo 内 skill

npx skills add opensquilla/opensquilla --list

SKILL.md

Frontmatter

{
    "name": "paper-quality-gate",
    "metadata": {
        "requires": {
            "anyBins": [
                "python",
                "python3"
            ]
        }
    },
    "entrypoint": {
        "parse": "text",
        "stdin": "{{ with.payload }}",
        "command": "python {baseDir}\/scripts\/audit.py",
        "timeout": 30
    },
    "provenance": {
        "origin": "opensquilla-original",
        "license": "Apache-2.0"
    },
    "description": "Deterministic pre-compile gate for meta-paper-write. Enforces length\/citation verdicts and rejects unsupported empirical-result claims when no user evidence was supplied.",
    "user-invocable": false,
    "disable-model-invocation": true
}

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.