Research & Search

microsoft Bundle

Browse and query the shadow knowledge base: overview, search for files or symbols or text, view preferences, or see recent discoveries. Invoke when the user wants to see what's in the shadow, get an overview, or find specific knowledge.

microsoft Bundle

Clean and consolidate the shadow knowledge base. Scans all shadow files for duplicate discoveries (same claim, different wording), near-duplicates (one extends another), and conflicting entries (contradicting claims). Merges duplicates, resolves conflicts by investigating the code, and asks the user only when resolution is unclear. Invoke periodically to keep the shadow focused and free of noise.

justtyashh Bundle

Stress-tests competing options by searching for counterexamples and surfacing the strongest downside before recommending a choice. Use when evaluating decisions, tradeoffs, architecture options, vendor selection, hire/no-hire calls, research conclusions, or any recommendation that needs adversarial scrutiny before commitment.

formars0309-cloud Bundle

Verify that biomedical citations are real, correctly attributed, and not retracted, by resolving DOIs/PMIDs/PMCIDs against PubMed, Crossref and Europe PMC. Use when writing, reviewing, or fact-checking a medical or scientific manuscript, when the user says "인용 검증", "레퍼런스 확인", "이 논문 실제로 있는지", "check citations", "verify references", "is this paper real", "retracted", "PMID 확인", "DOI 확인", or before delivering any text that contains references. Also use to FIND a correct citation to replace an unverified one.

alharkan7 Bundle

End-to-end bibliometric analysis (science mapping) of a research field — collect scholarly metadata from OpenAlex, screen it into a coding sheet, compute structured indicators, generate an academic chart suite (trends, themes, keyword co-occurrence, co-citation, collaboration networks), and write insight-driven reports. Use whenever the user wants to map a body of academic literature, run a quantitative or systematic literature review, analyze citations, keywords, journals, authors, or countries, build co-citation / keyword / collaboration networks, find research gaps, or says things like "bibliometric analysis", "science mapping", "lembar koding bibliometrika", or "what does the literature say about X, quantitatively".

alharkan7 Skill

Guidelines for creating, reading, or editing Excalidraw whiteboard diagrams (.excalidraw JSON files). Use for flowcharts, research-design sketches, and system diagrams.

haitranatwork Bundle

Implement one unit of a ticket from the knowledge base, commit it, and write a handoff file so any future session can resume cold without re-reading the docs or scanning the repo. Use whenever a developer says "implement WM-123", "continue", "next unit", "keep going", "carry on with the ticket", or asks to pick up where they left off. This is the developer-facing execution skill for the AI-Native SDLC chain and reads tickets.yaml from the knowledge base, not Jira. Do NOT use for planning, writing specs, or generating tickets.

haitranatwork Bundle

Review and apply pending doc-requests that developers raised during implementation — proposed corrections to spec.md, contracts, plan.md, or the context and architecture docs. Use whenever the user says "apply doc updates", "any doc requests", "process the doc requests", "what did the developers flag", or asks to review proposed knowledge base corrections. Only the knowledge base owner runs this. Do NOT use for implementing or for writing new artifacts.

synthesisengineering Bundle

Capture durable session facts in an OKF knowledge base with corpus-wide deduplication, confidentiality routing, conflict reconciliation, provenance, validation, and repository-aware shipping through synthesis-kb-edit. Use at session end, when asked to capture or update knowledge, merge facts into ai-knowledge, or preserve corrected facts about people, organizations, products, decisions, or strategy.

synthesisengineering Bundle

Find authoritative hyperlinks for people, organizations, and entities mentioned in content; recover dead URLs in archives via Wayback / Wikipedia / strip prioritization. Use when asked to: find links, hyperlink, research links, find URLs, gather references, look up websites for people or organizations, recover dead links, fix link rot, find archived versions.

brianggggg Skill

Condenses a meeting transcript or raw notes into decisions, action items with owners, and open questions. Use when a user pastes a transcript, forwards meeting notes, or asks "summarize this meeting" / "what did we decide".

nahid-sparktales Bundle

Investigate an open question properly — frame it as a decision, work from primary sources, sweep from several angles including the disconfirming one, and stop on a rule rather than on fatigue. Use when a question's answer will change what gets built or bought, when the material is unfamiliar or contested, or when someone asks for a recommendation with evidence behind it. Not for looking up a single fact you can confirm in one place, not for mapping the local codebase, and not for judging one source in isolation.

synthesisengineering Bundle

Five-phase workflow for creating high-quality thought leadership articles: reader briefing, research and validation, strategic writing, pre-publication critical review, and publication-package review (title, metadata, and batch gates). Includes anonymization protocol, credibility assessment, substance density checks, engagement optimization, the title-only stranger test, the title/description/body truth contract, batch headline monotony budgets, and the slug/metadata closure invariant. Use when asked to: write article, thought leadership, blog post, article workflow, write blog, draft article, create thought piece, write opinion piece, leadership article, headline review, title review, publication readiness, article package review.

sinnlosses Bundle

docs/（history/ 以外）・README.md・CLAUDE.md を10個の検査にかけ、スキルが定めた置き場・索引・「## タスク運用」節の形とのズレ、実物とのズレ、正典の二重化を洗い出して直す。ユーザーが「ドキュメントをメンテして」「docs と CLAUDE.md を点検して」「CLAUDE.md が実態と合っていない気がする」「docs/README.md が古い」と言ったとき、正典を書き換えたあとの追随漏れを洗いたいとき、ドキュメントが散らかってきた・どこに何を置くか分からなくなったと漏らしたときは、「点検」「棚卸し」という言葉が無くても必ずこのスキルを使う。docs/ に新しく中身を書くのは architecture-proposal・domain-modeling・research の仕事で、このスキルは書き足さない。

demondamon Bundle

Use when deeply researching an open-source GitHub repository for AgenticX adoption, selective mechanism internalization, gap analysis, or an evidence-backed implementation proposal.

ewaugh2 Skill

Time-efficient tutor for busy professionals that builds both top-down (the map — where a topic sits, why it exists, how its parts relate) and bottom-up (the mechanism — first principles, how it actually works) understanding of any topic in a 20-30 minute Socratic session. No memorization, no spaced repetition, no homework. Use this skill whenever the user says "teach me X", "explain X to me", "help me understand X", "walk me through how X works", "I need to get up to speed on X", "what should I know about X before my meeting", or attaches a document (deck, memo, paper, term sheet) they need to understand rather than just summarize. Trigger even when the user doesn't say "teach" — any request to genuinely understand a concept, market, instrument, technology, or document (as opposed to a quick factual lookup or a summary) is in scope. Also covers non-interactive requests like "write me a briefing on X I can read on the flight" via its briefing mode.

caneff Bundle

Make a demo of a research paper in a marimo notebook fully automatically without extra user input.

caneff Bundle

Implement a research paper as an interactive marimo notebook together with the user. Start by understanding what the user wants to explore, fetch the paper via alphaxiv, then build a focused notebook.

undertone0809 Skill

Gather and cite evidence before reaching a conclusion.

undertone0809 Skill

Synthesize evidence into a concise conclusion.

xju2 Skill

Produce a high-quality, constructive red-team review of a research proposal (DOE, NSF, NIH, or any competitive grant). Use this skill when the user asks to "red-team", "review", "critique", or "give feedback on" a proposal, grant application, or research plan, or when they want a reviewer's-eye view of how a proposal will be received. The review should be the kind of rigorous, expert, constructive critique that a strong panel reviewer would write — identifying real weaknesses, suggesting concrete fixes, and foregrounding genuine strengths.

undertone0809 Bundle

Use when the user asks how Rudder works; needs current Rudder docs, exact behavior, commands, contracts, APIs, or source evidence; asks to create, hire, or configure Rudder agents; or asks to scaffold, develop, or verify Rudder plugins. For explicit creation requests, verify the current interface before acting within existing authorization. Do not use for greetings, ordinary work merely running inside Rudder, routine actions already clear from the active context and typed tools, non-Rudder plugin work, or general coding and research tasks that do not ask about Rudder.

hanzhenlin Bundle

Darwin Skill 2.0 (达尔文.skill 2.0): autonomous skill optimizer, v2.0 integrates Microsoft Research SkillLens (arXiv 2605.23899) 9-dim rubric + SkillOpt (arXiv 2605.23904) validation-gated design + human-in-the-loop checkpoints. Evaluates SKILL.md files using a 9-dimension rubric (structure + effectiveness + meta-skill blacklists), runs hill-climbing with git version control, spawns independent judge agents for blind evaluation, validates improvements through test prompts with auto-break on diminishing returns, and generates visual result cards. Use when user mentions "优化skill", "skill评分", "自动优化", "auto optimize", "skill质量检查", "达尔文", "darwin", "帮我改改skill", "skill怎么样", "提升skill质量", "skill review", "skill打分".

robertoatila Skill

Conducts deep technical research, literature synthesis, paper analysis, and citation verification.

robertoatila Skill

Searches biomedical literature and extracts structured experimental data via BGPT.

robertoatila Skill

Escalation browsing for Cloudflare/WAF-protected, login-gated, or JS-rendered pages.

legalquants Bundle

Use when the user asks to find, read, or cite U.S. case law on a question — locating controlling or persuasive decisions via CourtListener, reading the opinion text, and grounding any statement in what the source actually says.

promptpartner Skill

Start a durable research / source note that captures what you read and found — fires on "start a research note", "capture these sources", "log my research". Part of the Agentsmith harness; scaffolds docs/research/<slug>.md so findings live in the repo, never in disposable memory (R9), and are never silently deleted.

jialuohu Bundle

Choose research graph colors or create one/two-ink editorial images: mono-color, duotone posters, risograph, and zine covers.

jialuohu Bundle

Use for the private Obsidian Lab Wiki mirror of Docmost: sync, query, synthesize, lint, or rebuild its local index. Never mutate Docmost.

jialuohu Bundle

Use when a user asks to set up, create, prepare, or start a brief Obsidian PaperRead draft or paper-reading note.

jialuohu Bundle

Use when a user asks to review, critique, fact-check, strengthen, or annotate an existing Obsidian PaperRead or paper-reading note by adding source-backed comments inside that note.

jialuohu Bundle

Prepare or repair one confidential assigned-review page under the matching Docmost conference, using its exact Paper Number and a blank review form.

jialuohu Bundle

Check or reconcile confidential Docmost review assignments with Todoist, Zotero Research/PaperReview, and matching review-comment pages.

jialuohu Bundle

Use bounded Jev evaluations to rank public research passages or check claim-source support, after readiness and pilot gates. Excludes private material and application development covered by the upstream TypeSafe skill.

jialuohu Bundle

Create, inspect, revise and export editable OmniGraffle .graffle diagrams with genuine LaTeXiT equations. Use for explicit OmniGraffle requests or existing .graffle artifacts, including English, 中文 and mixed-language research figures.