Research & Search

caixinyu2017-star Skill

<!--

caixinyu2017-star Skill

<!--

caixinyu2017-star Bundle

<!--

caixinyu2017-star Skill

<!--

caixinyu2017-star Skill

<!--

caixinyu2017-star Bundle

<!--

caixinyu2017-star Bundle

<!--

caixinyu2017-star Skill

<!--

caixinyu2017-star Skill

<!--

caixinyu2017-star Skill

<!--

caixinyu2017-star Skill

<!--

caixinyu2017-star Skill

<!--

caixinyu2017-star Skill

<!--

caixinyu2017-star Skill

<!--

aiocean Bundle

Search YouTube and extract video transcripts/subtitles/metadata via yt-dlp. Use whenever the user mentions a youtube.com URL, asks to summarize a video, pull a transcript, fetch video metadata, list a channel/playlist, or download subtitles in any language.

themarmack Bundle

Adversarially verify a single load-bearing claim by spawning N independent refuters (default 3) and killing the claim at ≥2/3 refute. Returns `{verdict, vote_breakdown, evidence}`. Reusable everywhere a claim needs scrutiny — Category 1 research synthesis, memory-curator before promoting to facts/, weekly-intelligence-digest before publishing a "what changed" item. Lifted from the built-in deep-research skill's verification pattern. Composes on claim-extractor (its input shape). Use after claim-extractor during any Category 1 research or scheduled digest run, before a load-bearing claim is published in a digest or promoted to vault/facts/.

themarmack Skill

OB1-borrowed weekly review skill. Scans the vault's writes from the past 7 days (across digests/, research/, events/, decisions/, facts/, insights/, _inbox/, people/, projects/) and produces an end-of-week synthesis at vault/digests/weekly/YYYY-MM-DD-weekly-review.md with the OB1 structure (Week at a Glance / Themes / Open Loops / Connections / Gaps / Focus). Unlike weekly-intelligence-digest, the source is the vault itself, not external feeds. Runs on Sunday PM by default (configurable). Use when the user asks to run the weekly review or synthesize what the vault accumulated this week — and on its Sunday-evening schedule.

themarmack Skill

On-demand Category 1 researcher focused on Dependabot best practices for a regulated organization — triage workflows, grouped-update strategies, auto-merge gates, ecosystem coverage, private-registry integration, cooldown periods for zero-day waiting, and the auto-triage rules that turn alert volume into actionable signal. Enforces Obsidian-first contract. Findings land at vault/research/dependabot/YYYY-MM-DD-{slug}.md; verified facts get staged for memory-curator promotion to vault/facts/ghas-dependabot/. Used by dependabot-config-helper as the source of defaults. Use when the user asks a strategic, policy, triage, or tooling question about Dependabot that needs a research-grade answer with citations — not when generating or reviewing a concrete dependabot.yml (dependabot-config-helper) or researching a non-Dependabot GHAS feature (ghas-feature-research).

themarmack Bundle

Turn an existing research note into a 1-page executive summary personalized to a named audience (e.g. `ciso`, `vp-eng`, `ceo`, or `default`). **Invoke ONLY when the user explicitly asks for an exec summary** — never as a post-write step in a Category 1 researcher flow. Loads audience preferences — length, voice, format, emphasize/avoid lists, special interests, section toggles — from `~/Obsidian/Research-Brain/_config/exec-preferences.md`. Writes the summary to `vault/insights/YYYY-MM-DD-exec-summary-{audience}-{slug}.md` via `vault-writer.write_insight`, then composes with `email-sender.prompt_then_send` to optionally deliver via Gmail. The 8-section structure (BLUF, Why This Matters Now, Key Findings, Implications, Recommended Action, Risks, Next Decision Point, Sources) is the spine — three sections are mandatory; the other five are toggleable per audience. Stop-and-reports on missing source note, missing prefs file, missing `## Default` section, or unknown audience. Use when the user asks to summarize a r

jpcaparas Bundle

Use for safe chezmoi setup and migration, daily dotfile sync, templates, secrets, scripts, drift/recovery, or official-doc research.

seemseam Skill

Run or read full-project architecture analysis and summarize structural weaknesses, hotspots, and maintainability risks.

craftos-dev Skill

Research topics thoroughly and provide summarized findings. Use when researching a topic, gathering information, comparing options, or learning about something new.

jpcaparas Bundle

Convert a YouTube video transcript into a structured dossier: metadata, executive summary, timestamped key topics, notable quotes, takeaways, follow-ups. Trigger on: YouTube dossier, video to notes, transcript to summary, summarize YouTube video. Do NOT trigger for non-YouTube video, audio transcription, or downloading video files.

teamwiseflow Skill

开展市场研究、竞品分析、投资人尽调、行业情报，附带来源标注和决策导向的摘要。 当用户需要市场规模估算、竞品对比、基金研究、技术扫描或支撑商业决策的研究时触发。

natthasath Bundle

แนะนำรูปแบบการจดบันทึก (Note-taking Pattern) ที่เหมาะสมกับ context ของผู้ใช้ โดยอิงจาก 15 patterns ที่พิสูจน์แล้ว เช่น Cornell Notes, Zettelkasten, PARA, Mind Map และอื่น ๆ ใช้ skill นี้ทันทีเมื่อผู้ใช้ถามเรื่องการจดบันทึก วิธีจด note หรือไม่รู้ว่าควรใช้ pattern ไหน — เช่น "จะจด note ประชุมดีไหม", "อยากสร้าง PKM แบบไหนดี", "จดเรียนแบบไหนให้ทบทวนง่าย", "debug log ควรจดยังไง", "อยากเก็บ knowledge base ระยะยาว" เรียกใช้ผ่าน `/creative:note-taking` เท่านั้น — ไม่ auto-trigger จากบทสนทนา

maziyarpanahi Skill

Apply consistent per-patient date shifting in OpenMed that preserves intervals between events while satisfying HIPAA Safe Harbor's date rule. Use when the user needs to de-identify dates but keep temporal structure for research, shift all dates by the same offset per patient, preserve days-between-events for survival or longitudinal analysis, cap ages over 89, or strip everything but the year. Covers deidentify(method="shift_dates", date_shift_days=..., keep_year=...) and per-patient reproducible offsets via consistent=True, seed=.... Pairs with OpenMed deidentifying-clinical-text and auditing-safe-harbor-checklist.

maziyarpanahi Skill

Searches and fetches PubMed and PMC via NCBI E-utilities (ESearch then EFetch/ESummary) to gather biomedical evidence and build text corpora. Use when the user wants citations for a condition or drug, abstracts to summarize, MeSH-based searches, or a corpus of literature to run NER over. Trigger keywords: PubMed, PMC, NCBI, E-utilities, ESearch, EFetch, ESummary, MeSH, PMID, literature search, abstracts, evidence. Pairs adjacent to OpenMed: fetched abstracts feed openmed.analyze_text for biomedical NER, and OpenMed-extracted diagnoses/drugs/genes become the search terms. E-utilities are public; an optional free API key raises rate limits from 3 to 10 requests/second.

maziyarpanahi Skill

Produces structured, citation-anchored summaries of clinical notes — one-liner, hospital course, and problem-oriented views — where every claim cites a source span so nothing is hallucinated. Use after de-identifying notes when the user wants a discharge summary draft, handoff/SBAR, problem list, or chart-abstraction summary. De-identify FIRST with openmed.deidentify, then anchor summary claims to entity spans from openmed.analyze_text. Trigger keywords: summarize note, discharge summary, hospital course, problem-oriented, one-liner, SOAP, SBAR, handoff, chart abstraction.

xonovex Bundle

Use when researching, creating, critiquing, revising, expanding, continuing, updating, validating, closing out, or distilling an implementation plan. Triggers on plan or subplan work, plan-driven implementation, codebase research explicitly intended to support a future plan, success-criteria validation, cross-session decision context, resuming work from a plan reference, wrapping up or handing over a finished or stalled plan, and turning a completed plan's implementation into reusable skills, even when the user doesn't say 'plan'.

xiaoluolyg Bundle

Research a topic before acting or advising.

lingtai-ai Skill

Operational guide for recording tool-result summaries, applying them with a full rebuild, recovering raw evidence, and choosing summarize versus molt.

lingtai-ai Skill

Safe notification dismissal reference: producer-owned state, atomic targets, stale versions, force, protected channels, post-molt acknowledgement, hooks, and legacy large-result reminders. Read after notification-manual before a clear or when one is refused; compaction belongs to summarize-manual.

zedarvates Bundle

Independent strategic outsider above the blue and red teams. Use for architecture resets, high-cost research decisions, inherited assumptions, and stalled adversarial reviews; do not use for routine review or autonomous mutation.

codealive-ai Bundle

Access premium APIs and curated skills via Orthogonal marketplace. Use when you need external data (scraping, enrichment, search), want to discover new capabilities, or need to call third-party services. For tasks like: find an API, enrich a lead, scrape a website, send SMS, verify email, research a company.

codealive-ai Bundle

Look up a person's background: work history, education, social profiles, contact info. Use when asked 'who is [person]?' or need to research someone before a meeting. For finding their email specifically, see find-email-by-name. For enriching a lead with full contact data, see lead-enrichment.

codealive-ai Bundle

Cron-triggered: query PostHog for new signups, research each by email domain via Exa, alert the CEO when someone interesting signs up. Not for manual use — runs automatically.