Local-first semantic image search — index folders of images and search them by natural-language description (SigLIP/CLIP embeddings + LanceDB, fully offline, no API keys).
用于撰写或修改《管理世界》稿件的文献综述章节，建立国际脉络—本土研究—本文位置的三层对话式结构。Use when…
Run this repo’s Units+Checkpoints research pipelines end-to-end (survey/综述/review/调研/教程/系统综述/审稿), with workspaces + checkpoints.
Designs graphics for thumbnails, social media, banners, and presentations. Applies design principles (CRAP, Gestalt, visual hierarchy) with research-backed techniques.
Designs graphics for thumbnails, social media, banners, and presentations. Applies design principles (CRAP, Gestalt, visual hierarchy) with research-backed techniques.
Use when a task needs nanosystems-engineer judgment — choosing a nanofabrication process for a target production volume, diagnosing an ALD or lithography conformality/overlay…
Token deep dive — info, OHLCV, holders, flows, flow intelligence, who bought/sold, DEX trades, PnL, perp trades, perp positions, perp PnL leaderboard.
Analyze NASH simulation results. Use when the user asks to analyze results, validate a simulation, verify a hypothesis, check convergence, visualize data, plot results, interpret…
Multi-source literature search, citation verification, MeSH search strategy, citation file management (.nbib/.ris/.bib conversion), and reference management (BibTeX, related…
Prepare, audit, or revise Nature-ready Data Availability statements, data repository plans, dataset citations, and FAIR metadata checklists for manuscripts.
Build a source-grounded deep-reading Paper Card for one scientific paper, preprint, PDF, DOI, arXiv page, publisher article, or pasted paper text.
Convert scientific papers, theses, technical reports, source code, figures, or research manuscripts into evidence-grounded Chinese invention patent drafts.
Polish, restructure, or translate academic prose into Nature-leaning English using the paper-architecture and writing-strategy principles from Scientific English Writing — from…
Use for experimental studies submitted to 《南开管理评论》 (Nankai Business Review) — design (between/within, scenario/vignette, lab/field), manipulation checks, randomization and…
Use to develop hypotheses for 《南开管理评论》 (Nankai Business Review) so each is backed by an explicit theoretical mechanism, not intuition.
Use for qualitative theory-building submitted to 《南开管理评论》 (Nankai Business Review) — multi-case comparison (replication logic, case selection), grounded-theory coding (open /…
Use to draft the revise-and-resubmit (R&R) response letter for 《南开管理评论》 (Nankai Business Review) — addressing reviewer concerns on theoretical contribution, mechanism logic,…
Use to confirm clinical ethics and research-integrity requirements for an NEJM submission — IRB/ethics-committee approval and informed consent per the Declaration of Helsinki,…
Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding re — from…
Grounds a coding agent's architecture decisions in real arXiv prior art before it builds something new.
비어있는 현재 디렉토리를 "누구나 술술 읽고 이해되는" 논문 학습 환경으로 부트스트랩한다. PDF 전체 + 필요한 외부 배경지식까지 조사해 notes 7개와 glossary를 서사형으로 채운다. 결과물은 원문 대신 이 파일들만 읽어도 이해되게 만드는 것이 목표.
Scaffold a new paper-plane tutorial content file with schema-valid frontmatter for championnatavionpapier.fr. Use when creating a new tutoriel under src/content/tutoriels/.
Use when defending the research design of a New Media & Society (NM&S) manuscript — informant/site logic for interviews and digital ethnography, sampling and coding for…
Use when handling research ethics, transparency, and data sharing for a New Media & Society (NM&S) manuscript — consent and anonymization, the ethics of scraping and platform ToS,…
Generate self-contained HTML broadsheet newspapers to explain any subject worth reporting — project status, reviews, dispatches, reports, or anything else.
Structured research summarization agent skill for non-dev users. Handles academic papers, web articles, reports, and documentation.
Map open problems where this repo can advance SOTA. Use when scoping research. Do not use to run the campaign; use night-market-completion-integrity-campaign.
Turn hunches into accepted results: worthiness score, evidence bar, research-to-rules. Use when vetting ideas. Not for QA; use night-market-validation-and-qa.
Reference for nimble search command. Load when searching the live web. Contains: all flags, 8 focus modes (general/coding/news/academic/shopping/social/geo/location), sea — from…
Configure TimeGPT fine-tuning on custom datasets with Nixtla SDK. Use when training domain-specific forecast models. Trigger with 'fine-tune TimeGPT' or 'train custom model'.
Provides expert Nixtla forecasting using TimeGPT, StatsForecast, and MLForecast. Generates time series forecasts, analyzes trends, compares models, performs cross-validation, and…
Aligns Python interpreter and pinned deps before installing NLP research repos from requirements.txt or environment.yml.
Summarize and analyze research notes created by research-assistant. Features: generate summaries, extract keywords, search within topics, list all topics.
Create a Notion database for tracking tasks related to a specific research topic. Use when the user wants to set up a Notion research tracker, create a Notion database for a…
Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with — from…
Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with — from…
Searches across your Notion workspace, synthesizes findings from multiple pages, and creates comprehensive research documentation saved as new Notion pages.
Pull up to 5 "To do" tasks from a Notion research tracker database, flip them to "In progress", spawn a planning-then-executing research subagent for each, and write the findings…
Author-guideline skill for nutrition journals from smaller/niche publishers not covered by a dedicated publisher skill: Obesity Facts (Karger), Current Opinion in Clinical…
Research output templates, distillation workflow, and quality standards for evidence-driven research
Map and brief official New Zealand AI policy guidance — public-service AI framework, responsible GenAI guidance, procurement, privacy, algorithm governance, AI strategy, and…
Search publicly available official New Zealand judgments by citation, court, party, judge, date and subject.
Search New Zealand Commerce Commission cases, news, decisions, and reports from comcom.govt.nz. Use when the task involves the Commerce Commission (ComCom), the case register…
List open New Zealand central-government consultations, agencies, topics, deadlines and official submission links. Read-only; does not submit responses.
Search and retrieve authoritative New Zealand Gazette notices by keyword, identifier, date, category and legislation. Retrieval only; not legal advice.
Search official New Zealand parliamentary debates, speeches and oral-question transcripts by speaker, date, topic, bill and sitting.
Track New Zealand Parliament bills and their legislative progress from the public bills.parliament.nz API.
Use when finding or inspecting current official New Zealand Regulatory Analysis Summaries (RAS), Regulatory Impact Statements or Assessments (RIS/RIA), supplementary or…
Track official New Zealand select committees, open submissions, business, public evidence and reports. Read-only; does not submit on a user's behalf.
Guide a person in systematic observation of systems, patterns, or phenomena. AI coaches neutral attention, field notes methodology, pattern recognition, hypothesis formation, and…
Turn a folder of research PDFs into an Obsidian knowledge vault — consistently formatted literature notes with frontmatter, PDF embed links, and cross-referenced atomic concept…
Use when adding/editing/querying content in an existing Obsidian vault, configuring plugins, integrating Claude Code with Obsidian via Local REST API or CLI, automating ongoing…
Use when writing or reviewing any migrations/ upgrade script, when a diff changes a field or model on a module already deployed to a customer, or when porting a module to a new…
Build a source-linked research evidence log with confirmed, inferred, and unknown claims. Use when preparing a research brief, comparison, or decision memo from agreed sources.
Run local-first web research on an OpenClaw agent and return a sourced research packet (findings, evidence tiers, conflicts, gaps) sized for handoff to a drafting or thesis skill.
Extract manually supplied Perplexity conversations into standalone, actionable Markdown. Use when the user pastes a Perplexity Thread, Space excerpt, Research or Create output,…
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from…
OmD Lab #01 — DESIGN.md 유무·생성방식이 UI 결과물에 미치는 영향을 4가지 조건으로 비교. 토스 스타일 모바일 UI를 (V1) DESIGN.md 없이, (V2) 수동 작성, (V3) 자동 생성, (V4) 자동 생성 + 5회 피드백 루프로 만들어 동시 비교 뷰로 시각화.
OmD Lab #02 — 디자인 하네스 정교화 실험. 동일 task를 v1, v2, v3... 버전별 하네스 설정으로 돌려서 산출물 품질·토큰 비용·iteration 수·persona ABANDON 율을 비교.
[omh] Hermes adaptation for durable research-goal execution. Use when the user says: autoresearch-goal, research goal, durable research, critic research.