Research & Search

lilac-labs Skill

Operator's guide to the YC CLI (`yc`) for the Gini batch demo — scoped to the yc commands the demo actually uses: the validated browser-forward login flow (tmux + browser_connect) and investor research against Bookface. Assumes yc is installed but NOT logged in yet. Load before staging or running the demo.

meganz Skill

Summarise a release's Failed / Feedback TestRail cases and post the standard "Android team" notice to Slack. Takes a version (e.g. v16.8), finds the matching release run in TestRail project 5, collects every test marked Failed or Feedback (excluding automated-test failures), groups them by assignee with Slack @-mentions and TestRail links, then sends the message to a given #channel or thread reply. If no Failed/Feedback cases are found, it sends nothing.

mfwarren Skill

Market Research

miles990 Skill

研究分析：文獻回顧、競品分析、市場調研、數據分析方法論

open-coder-ai Skill

trigger: web research where a direct fetch fails, is blocked, or needs JS rendering. avoid: reaching for the Firecrawl connector as the default fetch path.

xucroyuri Bundle

需要广泛的剧本理论或研究支持地图（而非即时剧本产出）时使用。

qball-inc Bundle

Structured multi-viewpoint research using 5 parallel Sonnet sub-agents. Use when deep research is needed on a complex topic before implementation planning.

bsamiee Bundle

Executes Tavily AI search, extraction, crawling, mapping, and deep research via Python CLI. Use when web search, URL content extraction, site crawling, or multi-step research needed.

bsamiee Bundle

Queries Perplexity AI via sonar/sonar-pro/sonar-deep-research/sonar-reasoning-pro models. Use when conducting cited web research, deep technical reports, or complex reasoning problems requiring up-to-date sources.

bsamiee Skill

Orchestrates concurrent workstreams via Task tool, decomposing non-trivial requests into 3-10 parallel agents with independent scopes. Use when multiple investigative paths, validation layers, research/analysis/debugging exceed trivial scope, or implementation planning requires facet exploration.

immamdouhaboammar Bundle

Use when the user needs to design research that reveals customer progress, switching triggers, language, and decision criteria; route here only when this decision boundary is the clear owner.

laststance Skill

Multi-tool cited research

laststance Bundle

Cited research briefs

allenai Bundle

Plan and execute autonomous research as a graph of typed tasks tracked in beads. Use when working from a mission.md to drive multi-step research with explicit dependencies and structured outputs.

allenai Skill

This skill should be used when the user asks to "find papers", "search for papers", "what does the literature say", "find research on", "academic papers about", "literature review", "cite papers", or needs to answer questions using academic literature.

allenai Bundle

Summarize a research project conducted with Asta skills and submit it to the asta-research-challenge repository. Use when the user wants to reflect on a finished (or in-progress) project and/or share it with the Asta team. The user may say "reflect on this project", "submit my research challenge", or "write up what we did".

allenai Skill

This skill should be used when the user asks to "generate theories", "theorize about", "what theories explain", "form scientific theories", "literature-driven theories", "hypothesize", "form hypotheses", "generate hypotheses", "what hypotheses explain", "run the theorizer", or wants AI-generated, literature-grounded scientific theories or hypotheses about a research question.

andysolomon Skill

Investigates a reported bug (often from a screenshot) through exhaustive repo search and online research, isolates the root cause, recommends the best possible fix, then files it as a bug in the tracker the codebase already uses (GitHub Issues, GitLab, or Linear). Delegates story formatting to arc-creating-user-stories and plan formatting to arc-planning-work. TRIGGER when: user reports a bug, shares a screenshot of broken behavior, asks "why is this happening", or asks to file/triage/research a defect. DO NOT TRIGGER when: user asks to implement a fix (use arc-bug-fixer), or to plan greenfield features (use arc-defining-work).

koinod Bundle

Prospect Research

matellez Skill

AUTO-TRIGGER: Apply this skill automatically when the user pastes or shares a job posting, job description, or any role they are considering applying for. Also trigger when the user asks Claude to review, tailor, score, or optimize their resume against a role. Trigger when the user asks "how well do I match," "am I a good fit," "should I apply," or shares a LinkedIn job posting, job board listing, or recruiter message containing a role description. Do NOT trigger for general career advice, salary research, or interview prep questions that do not include a specific job posting. This skill scores the user's fit against the role, selects the right resume version, and delivers a tailored resume ready to submit. The user has two resume versions on file. The skill selects and tailors the right one automatically based on the job posting.

matellez Skill

AUTO-TRIGGER: Apply this skill when the user mentions a company they are interviewing with, preparing for an interview at, or researching for a job application. Trigger phrases include: "I have an interview at," "I'm interviewing with," "tell me about [company]," "research [company] for me," "what do I need to know about [company]," or any request to prepare for a specific company meeting or interview. Also trigger when the user shares a company name alongside a job title, job posting, or recruiter name -- these signals indicate interview prep. Do NOT trigger for general industry research, trend analysis, or news requests that are not tied to a specific company and interview.

wwwroot Skill

Conducts first-principles technical research, mathematical derivations, algorithm design, and cross-domain invention for complex engineering challenges. Generates timestamped research specifications and mathematical models inside codex-drive/specs/.

nob-git-dev Bundle

「バナナの魅力を100文字で伝えてください」の36法則を体系的に適用し、任意のコンテンツを指定文字数で「伝わる要約」に変換するスキル

liujiayi3703 Bundle

UZI stock-research suite root. Use when the user mentions UZI, UZI-Skill, deep stock research, valuation, investor panel, hot-money/LHB analysis, trap detection, IC memo, Bloomberg-style equity research, A-share, HK, or US stock analysis.

xplore-lab Bundle

Personal knowledge base for capturing and retrieving information about people, places, restaurants, games, tech, events, media, ideas, and organizations. Use when: user mentions a person, place, restaurant, landmark, game, device, event, book/show, idea, or company. Trigger phrases: "remember", "note that", "met this person", "visited", "played", "what do I know about", etc. Brain entries take precedence over daily logs for named entities.

jtsang4 Bundle

Build a topic-centered research memo from the user's Readwise Reader documents and Readwise highlights. Use this whenever the user asks what they have already read, saved, highlighted, or been reading about a topic, wants a reading brief or research memo from their own library, wants evidence and tensions synthesized across Reader and Readwise, or wants topic-based shortlist/later/archive or tag suggestions. Use it even when the user does not say "Readwise" explicitly and instead says things like "I've been reading a lot about X" or "help me organize what I've read on Y." Prefer this skill over inbox-style triage when the task is organized around a theme, argument, project, or decision rather than chronology. Default to analysis first and only modify Reader after explicit user confirmation.

atmosphere Bundle

Write well-formatted notes to the atmosphere-vault Obsidian knowledge base. Use this skill whenever creating or updating an ADR, runbook, plan, API doc, guide, session output, or any structured document that should land in the vault — even when the user doesn't say "Obsidian" explicitly. Delegates to obsidian:obsidian-cli to write to the live vault and applies Atmosphere frontmatter and formatting standards.

voidverse-xyz Skill

Research a task and produce a decision-complete implementation plan without carrying out the implementation. Invoke explicitly with /skill:plan, or use the Pi /plan mode wrapper.

voidverse-xyz Skill

Plan non-software initiatives such as operations, research, process changes, programs, events, or organizational work. Use when execution needs coordinated decisions, ownership, dependencies, risks, and verification. For code changes or software architecture, use software-implementation-planning instead.

nicholashidalgo Skill

Use Python to profile exports, find data quality issues, inspect bad records, and summarize findings in plain language.

taleshagn-horushub Bundle

Realiza pesquisa aprofundada de mercado (Wide Research) de competidores e cria estratégia completa de ofertas escaláveis (Value Ladder). Use para: analisar concorrentes, identificar falhas no mercado, estruturar pacotes produtizados e criar estratégias de precificação.

wukongnotnull Bundle

Run fast, source-grounded UX research on the highest-signal problems users are experiencing with a user-specified digital product. Use when the user asks to research user pain, UX friction, onboarding issues, docs/help problems, developer experience friction, support pain, product workflow issues, or current user complaints for a named product.

stunspot Bundle

🔍 Retrieval evidence and citation auditor.

stunspot Bundle

🔎 Broad source inquiry and long-form reports.

fengqiliu Bundle

用户研究技能。设计并执行用户访谈，运用5WHY追问法深挖需求，绘制痛点热力图，通过需求反推确定产品方向。适用于需求调研、体验优化、方向验证等场景。当用户需要了解目标用户、挖掘深层需求、分析行为动机时使用此skill。

getcargohq Skill

Research one company before a meeting and hand back a briefing, powered by Cargo — what it does, what it publicly says is hard right now, and who it names as competition, each line traceable to where it came from. Triggers: "research this company", "brief me on this account", "prep me for this meeting", "what should I know about them", "write me a one-pager on", "what are they struggling with", "who do they compete with". Meeting prep, briefing, dossier, talking points. Skip when: you want many companies filtered rather than one understood — use build-tam-list; or you want the people to contact there — use find-stakeholders.