Research

Generate launch-companion content for books — blog posts, author notes, and dogfooding angles that demonstrate the book's thesis through its own production. Use when a manuscript is approaching publication submission (KDP, agent query, prelaunch).

Query Google NotebookLM notebooks for source-grounded, citation-backed answers from user-uploaded documents. Manages notebook library, handles Google authentication, and supports smart discovery. Works standalone via /blog notebooklm or internally from blog-write and blog-researcher for Tier 1 research data. Falls back gracefully when not configured. Use when user says "notebooklm", "notebook", "query notebook", "ask notebook", "notebook research", "source grounded research", "document query"...

Query bioRxiv/medRxiv preprints via REST API. Search by DOI, category, or date range; retrieve metadata (title, abstract, authors, category, DOI, version history) and PDFs. No auth. For peer-reviewed biomedical use pubmed-database; broader scholarly search use openalex-database.

Extracts structured citation data from academic repositories using BeautifulSoup4 with lxml parser. Parses DOI metadata, author affiliations, and reference lists from PubMed, arXiv, and Semantic Scholar HTML.

Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl) and per-user profiles across runs, with privacy guardrails baked in. Use when the user asks to "总结群聊", "群聊精华", "群聊摘要", "summarize group chat", "group chat digest", mentions a WeChat group name with a time range, says "帮我看看 XX ...

AWN CLI — standalone binary for world-scoped P2P messaging between AI agents. Ed25519-signed, zero runtime dependencies.

Use when determining author order on research manuscripts, assigning CRediT contributor roles for transparency, documenting individual contributions to collaborative projects, or resolving authorship disputes in multi-institutional research. Generates fair and transparent authorship assignments following ICMJE guidelines and CRediT taxonomy. Helps research teams document contributions, resolve disputes, and ensure equitable credit distribution in academic publications.

Turns reviewer comments into structured, professional point-by-point responses linked to manuscript revisions, clarifications, rebuttals, and additional analyses.

Audit open dependabot PRs in this repo. Spawns one investigator per PR (each with a codebase-walk sub-agent), produces a comparison table with per-PR risk + recommendation, and proposes a merge order that minimizes rebase churn. Audit-only — stops at recommendations; user authorizes execution. Use when dependabot has stacked up multiple open PRs and you want a structured pass before merging.

Search and retrieve scientific preprints from arXiv; use it when you need to find papers by keyword/author/category, fetch metadata (abstract, DOI, PDF URL), or download PDFs for offline reading.

Detect reviewed or repeated project processes that are candidates for automation, classify whether they are seed-ready, and route them to the right owner layer without granting schedule or mutation authority. Use when a reviewed session or repeated project slice reveals a recurring manual route and the honest question is whether it should stay manual, become a bounded skill, or become a playbook automation seed candidate. Do not use for one-off exploratory work, creative synthesis with no sta...

Formátování nálezu (z bug-hunter / dead-code-hunter / perf-hunter / security-auditor / ručního pozorování) do bloku v <connector>/docs/anomalies.md + draft Jira issue body. Přiděluje [CONN-NNN] ID lokálně per connector podle pořadí v existujícím anomalies.md.

Use this skill when reviewing English prose — essays, blog posts, opinion pieces, README sections, design documents, technical arguments, or any text that defends a thesis — in order to find flaws in the argumentation. Map the argument before judging it, name each flaw with a quoted snippet and a one-line explanation, and report findings as a structured list. Do NOT rewrite the prose, soften the author's tone, or replace the conclusion with your own opinion; the job is diagnosis, not surgery.

Analyse Mitre ATT&CK tactics, techniques and sub-techniques. Use when performing analysis of threat detections, threat models, security risks or cyber threat intelligence

Copyedit and proofread academic manuscripts for clarity, APA 7th compliance, and production readiness

All-in-one academic research với 28 tools. Kết nối arXiv, PubMed, Semantic Scholar, bioRxiv, medRxiv, Google Scholar. Hỗ trợ auto-cite và AI scientific figure generation.

Use when reviewing eval YAML files for quality issues, linting eval files before committing, checking eval schema compliance, or when asked to "review these evals", "check eval quality", "lint eval files", or "validate eval structure". Do NOT use for writing evals (use agentv-eval-writer) or running evals (use agentv-bench).

Plural Technology Researcher (⿻) for 0xagentprivacy. Activates for quadratic mechanism design, intersectional identity resolution, cross-difference collaboration, plurality-privacy synthesis, or any task exploring how privacy preserves the difference that plurality requires. Audrey Tang / Glen Weyl lineage.

Orphic hydrology of the sovereignty lattice — Lethe (the river of forgetting, named Blade 38) and Mnemosyne (the pool of chosen memory, still unnamed). Activates when designing systems where the witness must be held by flow rather than by a still pool, or when distinguishing architectures that "forget by design" from those that "keep by design."

Infinite witness space from toroidal topology. Activates when discussing cyclic paths through the lattice, unbounded witnesses, computational hardness from path enumeration, toroidal wrap, or why witness extraction is infeasible.

Story fracture and principle convergence methodology for 0xagentprivacy idea propagation. Activates when discussing how a single technical concept appears as different narratives across grimoires, designing multi-frame explanations for the same principle, or building organic trust graph formation through narrative variation. Triggers: "story fracture", "principle convergence", "narrative variation", "multi-frame", "idea propagation", "diffusion strategy", "different audiences".

Proverb lifecycle and the 5-phase proverb evolution for 0xagentprivacy RPP. Activates when discussing proverb formation (reception→compression→regeneration→propagation→inevitability), proverb-as-authentication, wisdom compression, or the Relationship Proverb Protocol as an anti-extraction mechanism.

Promise Theory foundations for 0xagentprivacy bilateral relationships. Activates when discussing polarity (±), cooperation semantics, conditional promises, VRC-as-promise architecture, or Jan Bergstra / Mark Burgess promise frameworks. Use when designing bilateral trust relationships or consent infrastructure.

Narrative compression methodology for 0xagentprivacy spellbook system. Activates when discussing 70:1-125:1 compression ratios, story-as-documentation, proverb extraction, symbolic notation, emoji spell encoding, or how complex cryptographic concepts compress into regenerative narrative.