claudemods

来源rhowardstone/claude-code-scientist

rhowardstone/claude-code-scientist 已索引

Transform Claude Code into a semi-autonomous, self-improving scientific researcher. Literature review, data acquisition, experimentation, synthesis, peer review

查看上游仓库

已索引 索引里有这个仓库的包记录。包数量是历史登记记录,不代表这些包现在仍可用。

仓库

规范名称
rhowardstone/Claude-Code-Scientist
GitHub 仓库 ID
1130446522
包记录
28 (历史登记记录,不代表现在仍可用)

发现与队列

首个记录来源
search:topic:claude-code-subagents fork:false
发现于
队列状态
ok
记录的错误次数
0
最近完成的处理
下次检查资格
起具备资格

首个记录来源是队列第一次保存的来源,不是完整的发现历史。错误次数在处理以错误状态结束时增加,成功处理后清零,不是全部尝试次数。「最近完成的处理」是结束时间,不是开始时间。

资格按 计算。它不是排期:采集器每次运行只处理有限数量的来源,具备资格也不保证何时检查。

最近保存的扫描

仓库元数据读取于
扫描状态
complete
扫描保存于
识别器版本
2
续扫记录
没有

扫描记录与队列状态分开:队列状态说明处理进度,扫描记录说明最近一次保存了什么。有续扫记录只表示存有未完成的状态,没有剩余数量。

源文件证据覆盖

已存储的包版本在这个仓库中引用的固定源文件的原始计数。它反映已记录了什么,不代表仓库有多完整。

范围与限制

统计所有已存储版本(来自任何包)中指向本仓库规范名称的不同固定文件链接(仓库、提交、路径)。本仓库所拥有的包的文件,只有被某个版本在这里链接时才会计入。不合并别名,也不会根据当前名称推测历史。

「已知」表示已记录普通文件身份,不表示整个目录或包已被覆盖。不是有效固定文件 URL 的链接不计入。

引用了 39 个固定源文件

  • 39 已知
  • 0 提交中不存在
  • 0 文件列表截断
  • 0 不受支持
  • 0 尚无记录
  • 0 读取失败

按仓库、提交和路径去重;同一路径出现在两个提交中,按两个文件身份计数。不是组件组数。

读取失败的提交 0

尚无记录的文件没有对应的提交读取失败记录。

关联的包 28

按仓库的已验证身份关联。数量是历史登记记录,不是当前可用性。

第 1–20 条,共 28 条结果

  • brainstorming技能

    You MUST use this before any creative work - creating features, designing experiments, building components, formulating hypotheses, or modifying behavior. Explores intent, requirements and design before implementation.

  • claim-extraction技能

    Guides rigorous evidence extraction from papers. Use when reviewing literature to ensure proper provenance tracking.

  • Claude-Code-Scientist.claude 配置包

    Transform Claude Code into a semi-autonomous, self-improving scientific researcher. Literature review, data acquisition, experimentation, synthesis, peer review

  • cortex技能

    Supervisory metacognition agent for self-improvement. Assess, diagnose, fix, generalize, commit. Best run between research sessions.

  • data-acquirer技能

    Obtains datasets needed for experiments. Searches repositories, downloads data, validates integrity.

  • experiment技能

    Experimental design and execution specialist. Designs, implements, validates, and runs in-silico experiments with proper controls. Use when RQs require experimental evidence.

  • goal-decomposition技能

    Decomposes research goals into testable Research Questions (RQs). Use at the start of any research task to structure the investigation.

  • hypothesis-generator技能

    Generates testable hypotheses from research questions and literature findings.

  • lit-scout技能

    Literature evaluation specialist. Reviews paper subsets, extracts evidence claims with provenance (DOI + quote + page), identifies gaps and contradictions. Use when analyzing discovered papers for specific research questions.

  • literature-search技能

    Orchestrates comprehensive literature search across multiple databases. Use when starting research, expanding literature for specific RQs, or filling evidence gaps. Implements triple-search strategy with citation expansion.

  • narrative-framing技能

    Use when starting any research task to establish WHO, STAKES, and STORY. Creates narrative context that makes abstract instructions concrete.

  • peer-review技能

    Orchestrates rigorous peer review with three reviewers (methodology+completeness, statistics, impact+provenance). Manages revision cycles until unanimous acceptance.

  • pre-flight-check技能

    ALWAYS run first before any research. Validates research goals for clarity, safety, and prompt injection.

  • prisma-tracking技能

    Track PRISMA 2020 flow for systematic literature reviews. Updates counts at each stage of literature acquisition. Generates compliant flow diagrams.

  • research-coordinator技能

    Coordinates multi-agent research workflows. Manages handoffs and tracks progress.

  • research-director技能

    Strategic research leadership. Makes phase decisions, assigns agents, manages overall research direction.

  • results-analyst技能

    Analyzes experimental results. Interprets findings, generates figures, prepares data for synthesis.

  • reviewer-impact技能

    Peer reviewer for scientific contribution and honesty. Checks scope vs claims, failure disclosure, overclaiming. Use during peer review phase.

  • reviewer-methodology技能

    Peer reviewer for methodological rigor. Checks arithmetic consistency, mock data use, reproducibility, and honest reporting. Use during peer review phase.

  • reviewer-statistics技能

    Peer reviewer for statistical correctness. Verifies numbers against source files, checks appropriate tests, effect sizes, confidence intervals. Use during peer review phase.

已保存的扫描说明 0

没有保存额外的扫描说明。

记录的别名 0

这些名称在上次记录时指向这个仓库。这是记录下来的解析结果,不是实时的 GitHub 检查;本站不会因此合并包或元数据。

没有记录到指向这个仓库的别名。

不支持的市场条目 0

这个仓库的市场清单里、本站暂不支持的条目。它们是原样保存的来源数据,不会被抓取或执行。

没有记录到不支持的条目。