All categories
Research
Research, evidence gathering, literature, reports, investigation, and synthesis
- 30,315
- 1,264
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse research skills
Showing 11,113–11,136 of 30,315 skills
- Autoresearchclaw Autonomous ResearchFully autonomous research pipeline that turns a topic idea into a complete academic paper with real citations, experiments, and conference-ready LaTeX.Votes: 0GitHub stars: 81
- Autoresearch GenealogyStructured prompts, vault templates, and autonomous research workflows for AI-assisted genealogy using Claude Code.Votes: 0GitHub stars: 81
- Signal Integrity ReviewRAG-backed. Review DipTrace PCB impedance, stackup, routed geometry, return paths, and configured external-solver evidence without inventing targets. Use when the user says “Review impedance and return-path evidence for these PCB nets.”Votes: 0GitHub stars: 23
- Coval Eval StartChoose the next useful step for evaluating a voice or chat agent with Coval. Use for getting started or deciding what to do next; use a specific skill directly when the task is already clear.Votes: 0GitHub stars: 2
- Coval Discover FailuresDiscover failure modes in Coval runs, uploaded conversations or local conversation exports using scoped sampling and transcript, audio and trace evidence. Prepare human review without inventing ground truth or launching new runs.Votes: 0GitHub stars: 2
- InvestigateRoot-cause debugging before any fix: scope lock, hypothesis testing, debug report. Triggers: \"debug this\", \"why is this broken\".Votes: 0GitHub stars: 86
- HumanizeRevise human-facing prose to remove AI tells and match the intended voice.Votes: 0GitHub stars: 86
- HandoffPreserve session state for a follow-up agent with handoff files and commits.Votes: 0GitHub stars: 86
- GardenAudit HQ content for stale, duplicate, or inaccurate information.Votes: 0GitHub stars: 86
- CheckpointSave a lightweight session checkpoint.Votes: 0GitHub stars: 86
- BrainstormCompare approaches, surface unknowns, and draft a recommendation before PRD work.Votes: 0GitHub stars: 86
- Mine My TicketsGo through your recent tickets and pull out what customers are actually saying. Clusters the verbatim pains, feature requests, friction points where your messaging doesn't match reality, and quotes worth stealing for your landing page. The single best input for your next roadmap conversation, positioning tweak, or investor update.Votes: 0GitHub stars: 117
- Research An AccountResearch a target account or contact at the depth you need: a 30-second qualify on a URL, a full cited brief with site scrape and twelve weeks of news, an enrichment on a named person, or a warm-paths search across your CRM and LinkedIn. Every claim cites a real source - no invented news, funding, or connections.Votes: 0GitHub stars: 117
- Build A BattlecardBuild a battlecard for one specific deal versus one specific competitor - not a generic comparison sheet. Three-criterion grid anchored in what this prospect cares about, three trap-set discovery questions, three objection rebuttals grounded in your real differentiators, and two proof points from anchor accounts. Every claim cites a source.Votes: 0GitHub stars: 117
- Score An InboundScore any inbound that needs your decision against a real rubric instead of going by gut. Drop in an advisor pitch, a partnership ask, a press request, or a generic vendor application and I run it against your saved criteria, gather public-signal evidence, and produce an approve / decline / more-info recommendation with the one line of evidence that matters most.Votes: 0GitHub stars: 117
- Find My BottlenecksFind what's actually slowing your company down so you can unblock it. I cluster evidence from your recent reviews, pending decisions, open anomalies, and off-track goals into named bottlenecks, each with a hypothesis and a proposed owner to unblock it. Use this when something feels stuck and you can't put your finger on why.Votes: 0GitHub stars: 117
- Analyze My DataGet a rigorous readout on what your data is actually telling you. Pick what you need: an experiment readout with lift, significance, confidence intervals, and an explicit ship / kill / iterate / inconclusive call; an anomaly sweep that flags metrics deviating past rolling baselines with hypothesized causes; or a data-quality audit that checks nulls, dupes, freshness, and referential integrity on the tables you care about.Votes: 0GitHub stars: 117
- Track Deadlines And SignaturesKeep tabs on what's outstanding on the legal side. Pick what you need: chase pending signatures, log a freshly signed agreement, see what deadlines are coming up, or get a Monday rollup of the week. I keep a running list so nothing slips.Votes: 0GitHub stars: 117
- Encontrar Mis Cuellos De BotellaDescubre qué está frenando realmente a tu empresa para que puedas destrabarlo. Agrupo evidencia de tus revisiones recientes, decisiones pendientes, anomalías abiertas y metas fuera de curso en cuellos de botella con nombre, cada uno con una hipótesis y un responsable propuesto para destrabarlo. Úsalo cuando algo se sienta estancado y no puedas identificar por qué.Votes: 0GitHub stars: 117
- WritingALWAYS use for ANY substantial prose a human will read - "write the article", "draft this section", "outline the paper", "turn these notes into prose", "write up the memo", "draft the comment letter", "write the brief", "expand this into a chapter", "I need a few pages on X", "put this argument in writing", "/writing". Use proactively even when the user asks casually and never says "article" - do not start drafting paragraphs first. NOT for code, data work or course materials.Votes: 0GitHub stars: 22
- Writing EconALWAYS load BEFORE drafting, revising or grading FINANCE or ACCOUNTING journal prose — 'write the paper', 'draft the introduction of my JF submission', 'revise Section 3', 'polish the job-market paper', 'does this read like a finance paper', 'tighten the abstract', 'is this well written for JFE/RFS/JAR/TAR', 'should I write we find or the paper shows', 'do I cross-reference by Section or Part', 'is agents jargon'. Covers Journal of Finance, JFE, RFS, Journal of Accounting Research, The Accoun...Votes: 0GitHub stars: 22
- WorkshopALWAYS use when the deliverable is a research talk - Typst slides and teleprompter speaker notes built from a paper. Use when the user says \"create workshop slides\", \"build the deck\", \"make slides for my paper\", \"presentation from this paper\", \"write the speaker notes\", \"I'm presenting this at a seminar\", \"turn the paper into a 40-minute talk\", \"I have a workshop next week and nothing to show\", or \"/workshop\". Use proactively whenever a conference, seminar, job talk or brown...Votes: 0GitHub stars: 22
- Source VerifyUse when the user says 'verify my sources', 'check the citations', 'fact-check the footnotes', 'are my cites real', 'did I make this cite up', 'does the source actually say that', 'check this quote against the source', or 'source check before I submit'. Use proactively whenever a draft's citations or quotations have not been checked against the actual sources. NOT for Bluebook formatting - use bluebook or bluebook-audit.Votes: 0GitHub stars: 22
- ResearchALWAYS use for ANY request to find academic papers - "find papers on X", "what does the literature say about X", "is there research on this", "who has written about X", "find me cites for this claim", "literature search", "any papers in the journals I like", "top journals only", "recent work on X", "has anyone studied this". Use proactively before answering an empirical or doctrinal question from memory, and never run scholar/consensus/paperpile by hand in sequence - this skill parallelizes t...Votes: 0GitHub stars: 22