Research plugins

Review a manuscript PDF with N core reviewers, six specialist tracks and an editor, every finding anchored to a quotation, on a Claude Code subscription login

3 skills · 10 agents · 1 MCP server

Academic research skills including paper analysis, literature search, preprint discovery, grant management, and meeting minutes

8 skills

Trading strategy builder for Codex, Claude Code, Cursor, and other agents. Turn a trading idea into Evidence, an inspectable Signal, and a private Replay. Publish only when asked. Stingray does not place trades. Token-scoped, opt-in, Apache-2.0.

1 skill

Read AgentNews finance and macro context boards before answering market questions.

1 skill

Governed agent skills for medical research, healthcare education, and responsible health AI. Clinical risk classes, permission gates, and human-review requirements on every skill.

84 skills

The research lifecycle for a master's thesis or paper: research question and proposal, multi-source literature search, structured paper notes, a verified BibTeX bibliography, citation verification with a hook that catches invented keys as they are written, argument-first literature synthesis, research design and design science, statistics planning and reporting, PRISMA systematic reviews, citation-graph expansion, reproducible experiments and benchmark reporting, section-by-section academic writing, LaTeX and Word toolchains, publication figures, an examiner-style reviewer and a paper critic, proofreading, supervisor updates, a research log, and progress tracking.

21 skills · 3 commands · 2 agents · hooks

Academic paper Word document agent with specialized modules for document analysis, formatting, content editing, reference management, table/figure formatting, review handling, quality checking, and submission preparation.

9 skills · 9 agents · hooks

Source-cited deep dives across agriculture, operating systems, cognition, civilization, politics, science, technology, storytelling, and integrated systems.

18 skills

Read, write, review and contest on Scio with live rank and permissions.

1 skill · 8 commands · 4 agents · 2 MCP servers · hooks

Freeze a plan before running, seal a run's inputs, bind every number and quotation in a manuscript to what backs it, and check that each still resolves before submitting. Bundles prereg, citations, results and repro.

7 skills · 4 commands · hooks

Investigate TRON addresses, fund flows and contracts across the full chain history, with reproducible evidence. Includes skills, agents and commands for investigations and TRON developer docs.

6 skills · 2 commands · 3 agents · 1 MCP server

Web search, content extraction, library docs & media — configurable search backends and local retrieval

6 skills · 1 MCP server · hooks

Currency Research: auditing an evidence-grounded reference for staleness — the durability tiers, deciding whether a finding warrants an edit at all, web search and source-quality practice, dating a claim, the fabrication failure mode, editing a SKILL.md without disturbing its structure or cross-references, and opening the weekly pull request.

4 skills

Stanford STORM-style PhD-grade research in one prompt: grounded multi-perspective web interviews, contradiction map, cited Wikipedia-style report, synthesis briefing and self peer-review.

2 skills · 2 agents

Look up computational-pathology datasets in PathTrove, in Chinese or English: table search and statistics, resource reports (value, text, source), download plans, label summaries. The data package (~14 MB) is downloaded from the public Hugging Face repo Dearcat/PathTrove on first use and cached locally (no key, no server); raw label files are downloaded one at a time.

3 skills · 1 MCP server

Investigation toolkit: a deep-research subagent for multi-source work with citations, plus name-clearing skills for software projects (registries, app stores) and for businesses (social handles, storefronts, company registers).

2 skills · 1 agent

agent-forward science

Runs an econometrics methods check (AESDK) before AI agents write or run regression and causal-inference code, enforces it with hooks, and archives AI provenance.

19 skills · 2 commands · 1 agent · 1 MCP server · hooks

Search SciX (formerly NASA ADS), read each paper in full once, and silently build a classified literature library of whole-article digests: one-line and paragraph summaries, a summary of every section, and citable findings with key values, locators, and verbatim anchors. Later work starts from the stored record, rereads only the exact paragraph behind a citation, browses with adslib, and exports citations.

1 skill · 7 commands

Hosted PapersFlow MCP tools plus guided Codex research agents for search, citation graphs, and DeepScan.

4 skills · 1 MCP server

Capture and compare AI answers and citations, then verify each claim with authoritative evidence.

5 skills

Community guidelines for empirical SE studies involving LLMs. Use /llm-guidelines:review to check a paper draft and its supplementary material against the eight guidelines, or /llm-guidelines:explore to discuss the guidelines and your study design.

1 skill · 2 commands

Board-ready competitive-intelligence and due-diligence dossiers on any legal entity — 23 sections, cross-validated sources, red-flag scan, HTML/PDF export.

1 skill

顶会 rebuttal 助手：拆解审稿意见、按优先级分配字符预算、14 类异议打法、英文句式库、可检索的 CCF-A 会议规则库。

1 skill

Karpathy's autoresearch as a Claude Code plugin — autonomous fixed-budget optimization for ML training, code performance, prompt engineering, and more. Apple Silicon (MLX), NVIDIA CUDA, and RunPod cloud.

The ARIS skill set as a plugin — every mainline skill under skills/, plus /aris:setup, which registers the bundled Codex reviewer bridge (mcp-servers/codex-exec/) and points helper resolution at the plugin.

89 skills · 1 command

59 skills for evidence-first research: source evaluation/verification, evidence-claim graphs, calibration and forecasting, OSINT, literature review, and decision-support synthesis

60 skills · hooks

59 skills for evidence-first research: source evaluation/verification, evidence-claim graphs, calibration and forecasting, OSINT, literature review, and decision-support synthesis

60 skills · hooks

Eight skills for sourced competitive decisions: portfolios, triage, corroboration, battlecard edits, rep answers, patterns, updates, and call mentions.

8 skills

NewsAPI.ai hosted MCP server and six research skills: news, due diligence, risk, markets, political and source analysis

6 skills · 1 MCP server