verifier

Abductive analysis (Timmermans & Tavory) for theory-generating qualitative research. Theory-first approach with anomaly detection, theoretical casing, and rhetorical abduction for publication.

1 skill

Build bibliographies from manuscript citations by extracting in-text citations, matching them against a references.bib file, identifying issues, and generating a formatted reference list.

1 skill

Develop causal diagrams (DAGs) from social-science research questions and literature, then render publication-ready figures using Mermaid, R, or Python.

1 skill

Pragmatic qualitative analysis for interview data. Supports theory-informed or data-first approaches with systematic coding, quality indicators, and publication-ready synthesis.

1 skill

Build systematic literature databases using OpenAlex API. Phased workflow for search, screening, snowballing, annotation, and synthesis with structured user interaction.

1 skill

Deep reading and synthesis of literature corpus. Theoretical mapping, thematic clustering, and debate identification using local library of markdown-converted papers.

1 skill

IoT device lifecycle, telemetry anomaly detection, fleet management, and witness chain verification for Cognitum Seed hardware

5 skills · 1 command · 4 agents

The manufacturing plugin. Skills for the work a plant actually runs on: joining the exports and systems into one dataset, quoting make-to-order jobs from drawings, writing nonconformances and 8Ds, diagnosing breakdowns, and reporting the morning numbers. Works with Microsoft 365, Oracle NetSuite, Infor M3 and Autodesk Fusion once connected, connects anything else through custom-connector, and runs on scheduled file exports when a system has no connector at all. Install and then ask Claude to help you get onboarded.

17 skills · 1 MCP server

Portable operating method: session lifecycle agents, pre-ship code review, deploy with live verification and state doc update, and production log health check

5 agents

Answer questions about past agent runs from the recording, not from memory. Three read-only stdlib scripts over the session transcripts Claude Code and Codex already write: a finder that locates the run by repo, time window, touched file or command text; a timeline that numbers every step with its exit code, lists every file changed (flagging changes the agent never mentioned) and walks back from any step with each causal edge labelled recorded or inferred by a named rule; and a claim checker that tests a summary's claims (ran, passed, edited, not-edited, read) against the run and catches tests that passed before a later edit and exit codes that belong to the last command of a pipe. Secrets are always redacted. A UserPromptSubmit hook gives the agent this session's transcript path when a prompt asks about past work. Ships cs-run-forensics agent, /cs-run-forensics and /cs-check-claims commands and 3 cited references.

1 skill · 2 commands · 1 agent · hooks

Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Includes LaTeX templates, citation verification, reviewer guidelines, publication-quality figure generation, systems paper structural blueprints, and conference presentation slides.

98 skills

理论溯源与案例重释。审查 PPT、课程、文案或方法论中的经验判断，先判断命题是否成立，再匹配并核实可信理论，用该理论重释案例并标明边界。适用于给自创理论找依据、给 PPT 补理论来源、判断一句话能否上升为理论、检查是否硬套名人；聚焦单次理论锚定，不默认展开历史同构研究。

1 skill