Research & Search

mervinpraison Skill

Summarise SBML structure and annotations

anotb Bundle

Develop evidence-backed points of view, white papers, case studies, industry briefs, and research reports for a consulting audience. Use to turn research or permitted engagement experience into a useful, defensible argument.

dkharlanau Skill

Improve website content for search, AI search, citation, and recommendation surfaces without AI-generated filler. Use when asked to optimize articles, docs, landing pages, comparisons, answer pages, or knowledge content for Google Search, AI Overviews/AI Mode, ChatGPT Search, Bing/Copilot citations, or ARWP content quality. Preserve human usefulness, evidence, originality, and clear entity/topic structure.

antjanus Bundle

Use this skill for deep, multi-source web research with cited synthesis whenever the user wants to "research X", "deep research on Y", "deep dive on Z", "investigate this topic", "compare X and Y", "pros and cons of X", or "survey the landscape of Y" — even if they never say "research", any ask needing several independent sources cross-referenced and cited counts. Do NOT use this skill for a single fact one WebSearch answers, for reviewing code (see code-review), or for exploring files in the current repo (use Explore).

zhihaoairobotic Skill

Fetch arXiv papers by date range and topics, rank them for research value, and produce introduction digests. Use when the user wants a literature sweep, daily or weekly paper triage, or a written overview of the best papers in a niche — without relying on the arxivterminal local database.

zhihaoairobotic Skill

Autonomous ML research loop — modify train.py, run 5-min GPU experiments, track val_bpb, iterate overnight. Invoke when the user wants to run self-directed architecture search on the autoresearch repo.

zhihaoairobotic Skill

Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.

alexeykrol Skill

Сбор, проверка и систематизация источников.

jtenniswood Bundle

Summarize user-facing project changes from the last 7 days. Use when the user says "/updates", asks for recent updates, wants a changelog-style summary, or wants the most important feature changes from the past week.

kntnt Bundle

Turn a brief and its source material into one truthful first draft in the target language, and stop there. Start it on your own only when the literal token `/write` appears in the request or in an instruction the request points at — inside a longer message, a document, or a checklist that says to run it. Not for a bare request to write, draft, compose, summarise, rewrite, edit, or review something — without `/write` in it, such a request is answered as it otherwise would be. A user may also invoke it by name at any time.

login-tb Skill

Kundenforschung datensparsam und einwilligungsorientiert planen, durchführen und auswerten. Nutze diesen Skill für Interviewleitfäden, Umfragen, Usability-Tests, die Auswertung vorhandener Gespräche, Support-Tickets oder Bewertungen, und für Personas, Segmente und Jobs-to-be-Done. Klärt vorab Zweck, Rechtsgrundlage, Einwilligung, Aufzeichnung, Pseudonymisierung und Aufbewahrung, wertet nur innerhalb des Stichprobenrahmens aus und trennt Befund von Entscheidung. Beachtet DSGVO, BDSG und Beschäftigtendaten; Österreich und Schweiz werden getrennt behandelt.

marazii Bundle

Draft sections of a grant proposal — specific aims / lay summary / significance / innovation / approach / broader impacts / budget justification / data management plan / biosketch — adapted to the funder's format and review criteria. Supports NSF, NIH (R01, R21, R03, F31, F32, K-series), ERC (Starting, Consolidator, Advanced), Wellcome, Horizon Europe, NSF GRFP, foundation grants, and other major schemes. Works from research-brainstorm and methodology-advisor outputs, plus the funder's published criteria. Trigger when: user mentions "grant proposal", "specific aims", "NSF", "NIH", "ERC", "Wellcome", "Horizon Europe", "research proposal", "fellowship application", "biosketch", "broader impacts", "data management plan", "lay summary", "case for support", or runs /grant.

marazii Bundle

Conduct rigorous, fact-checked academic literature reviews. Synthesizes sources, traces citation chains, flags weak claims, and produces structured outputs (narrative, systematic, scoping, or thematic). Trigger when: user asks for a "literature review", "lit review", "background research", "state of the field", "what does the research say about…", "summarize the literature on…", "find sources on…", or runs /lit-review. Works from sources the user provides (PDFs, links, citations) AND from web/database search when allowed.

marazii Bundle

Format citations and bibliographies in any major academic style — APA 7, MLA 9, Chicago (notes-bibliography and author-date), Harvard, Vancouver, IEEE, AMA, and discipline-specific journal styles. Converts between formats, builds reference lists from raw input, validates DOIs, and generates BibTeX/RIS exports. Trigger when: user asks to "format this citation", "convert to APA", "bibliography in Chicago", "reference list", "BibTeX", "fix my references", "is this APA correct", or runs /cite.

marazii Bundle

Advise on quantitative and qualitative research methodology — design, sampling, validity, reliability, measurement, ethics, analysis plan, and — mandatory in every methodology output — creative AI / ML / Big Data extensions tailored to the specific research question. The creative-extensions section is not optional: it forces researchers to consider non-conventional, modern methods before settling on a design. Trigger when: user asks about "study design", "research design", "methodology", "what method should I use", "sample size", "power analysis", "sampling strategy", "validity", "reliability", "IRB", "pre-registration", "RCT vs quasi-experiment", "qualitative vs quantitative", "AI methods for my study", "ML approach", "big data approach", "creative methods", or runs /methodology.

marazii Bundle

Generate, sharpen, and pressure-test research ideas — research questions, hypotheses, study angles, novel contributions, and contrarian framings. Pushes beyond obvious next steps to find what's actually worth studying. Useful at the start of a project or when stuck. Trigger when: user asks to "brainstorm research", "generate research ideas", "research questions", "hypothesis ideas", "what should I study", "I'm stuck on what to research", "thesis topic ideas", "novel angles", "what's interesting about", or runs /brainstorm.

meisterlabs Skill

Summarize what you worked on yesterday and what's planned for today from your MeisterTask activity.

peng-wen Bundle

Apply the house style guide to a document, covering headings, tone, terminology, punctuation, and citation format. Use when the user wants a document brought in line with the style guide or asks for a style pass.

peter537 Bundle

Research and clarify complex software changes before implementation. Use for architecture proposals, migrations and refactors, parity or retirement inventories, sequencing and dependency analysis, scope and tradeoff decisions, ADR candidates, acceptance gates, and other software work that needs repository evidence plus targeted user questions. Do not use for straightforward changes with an already decision-complete specification.

qball-inc Bundle

Manage the CLEAR knowledge base — search, view, capture, index, link, deprecate, and supersede entries. Use when the user asks about knowledge base entries, wants to capture a decision or lesson, search for patterns, or manage entry lifecycle.

qball-inc Skill

Use when PERFORMING knowledge actions: capturing decisions, searching the knowledge base, or creating knowledge entries.

chinkan Skill

Research workflow recipe (frame question → gather sources → synthesize → cite → answer)

abhillashjadhav Skill

Use this skill when the user wants to rewrite, edit, sharpen, humanize, or de-slop product writing such as LinkedIn posts, product memos, launch notes, strategy updates, PRDs, emails, or executive summaries. Preserve the writer's point, evidence, vocabulary, bluntness, uncertainty, and product judgment. Remove recognisable AI-writing patterns without turning the draft into generic polished prose. Do not use when the user only wants factual research, a brand-new document without source material, or a generic grammar check.

othmanadi Skill

Quick one-shot lookup over Ahmad's OpenMark bookmark knowledge graph (15k+ items from Edge, LinkedIn, YouTube, Raindrop). Use whenever Ahmad asks "find my bookmarks on X", "what did I save about X", "anything in OpenMark about X", or any single-topic search where he wants results in under 10 seconds. NOT for newsletter drafting or deep research — for those use openmark-deep-research or openmark-newsletter. Triggers on "find my", "what did I save", "openmark", "my bookmarks", "search bookmarks".

othmanadi Skill

Multi-angle deep-research workflow over Ahmad's OpenMark knowledge graph (13k+ bookmarks). Use whenever Ahmad asks anything that requires more than one search to answer well — "what's the landscape of X in my saves", "do a deep dive on Y", "research X across my bookmarks", "compare what I saved about X vs Y", "give me everything on X". Also use when fast-search returned thin results and Ahmad pushed back ("dig deeper", "more results", "actually research it"). Pairs Neo4j graph search with WebFetch on top picks to bring back fresh page content. Triggers on "deep research", "dig deeper", "research", "landscape", "everything on", "thorough", "comprehensive".

othmanadi Skill

Compose a categorical news-roundup newsletter from Ahmad's OpenMark saves. Use when Ahmad wants a scannable "what happened in AI / tools / research / discourse" recap rather than a single-thesis essay. Trigger phrases include "roundup", "news roundup", "this week in AI", "weekly news", "what dropped this week", "category recap", "/newsletter-roundup". Output is bucketed by topic with 3–5 items per bucket, short blurbs, source-tagged for at-a-glance scanning.

othmanadi Skill

Manus-style file-based planning for multi-step work. Keep task_plan.md, findings.md, progress.md in your run workspace so the filesystem is your working memory. Use for any research/build with 5+ tool calls. Adapted for OpenMark sub-agents from Ahmad's planning-with-files v3.0.0.

yzhao062 Bundle

Add or tighten bibliography citations in NSF proposal sections such as the intro, summary, team qualification, evaluation, and thrust files. Use when Codex needs to place bibrefs conservatively, prefer existing local cite keys for the team's own work, respect user-specified citation density, verify every inserted citation against local .bib files or primary-source metadata, and leave visible TODOs instead of guessing.

yzhao062 Bundle

Refine one or more NSF thrust, aim, or study files after the initial scaffold exists. Use when Codex needs to deepen a core proposal unit with sharper gaps, local literature grounding, concrete technical measures, evaluation hooks, reviewer-facing running examples or artifact sketches, figure ideas, or visible TODO placeholders while preserving alignment with the current intro, summary, and evaluation plan.

ajbarea Bundle

Use when a draft research paper needs a pre-submission novelty and reviewer pass — whether its contributions are actually new, what related work it misses, whether its claims hold up, and whether it overlaps a lab or co-author line that must be disclosed. Triggers include "review my paper for novelty", "is this contribution novel", "novelty check before submitting", "what related work am I missing", "verify my citations are real", "paper-review <name>".

analogdevicesinc Skill

Guidelines for using Context7, web search, and other research tools to find solutions outside the Scopy codebase. Loaded when the task involves unfamiliar technology or external libraries.

ship-with-ai Bundle

Use this skill whenever the user wants to get feedback on their MVP, find testers, prepare outreach messages, create test scripts for users, analyze user feedback, or convert feedback into feature specs. Also trigger when the user mentions testers, user research, validation, feedback collection, or wants to know what to build next based on real user input. Use this even when the user says things like "I just built this, now what?" or "should I add more features?" — redirect them to collecting feedback first.

the-fish-salmon Bundle

Interactive research co-pilot. Orients to current state, asks one clarifier per turn, suggests next moves, synthesizes papers, escalates. Use /copilot or "where is my research".

the-fish-salmon Bundle

Verify the Obsidian vault is set up for cross-device research continuity. Use for "sync-check", "is my continuity folder ok", "verify vault for sync".

the-fish-salmon Bundle

Rehydrate a Claude Desktop session from {vault}/00-Claude-Context. Use for "resume research", "where was I", "pick up where I left off", "load research context".

the-fish-salmon Bundle

Snapshot the current research session into the Obsidian vault for cross-device resume. Use for "save research state", "snapshot session", "checkpoint research".