Research & Search

questflowai Bundle

Use when evaluating investments through Zhang Lei / Hillhouse Capital's long-term research-driven value lens: deep research, do time's friend, invest in great companies, and actively help them grow.

topprismdata Skill

Use when: (1) Entering a new Kaggle competition and unsure what type it is, (2) Need to choose between forking public kernels vs building custom, (3) Deciding how to allocate submission quota across the competition lifecycle, (4) Determining which evaluation/validation strategy to use. Covers 6 competition types (Standard Tabular, Code Competition, Simulation, Research, Prediction, Playground), each with distinct: submission mechanism, scoring system, public kernel value, GPU requirements, and optimal strategy. Includes a decision tree for first-48h actions and a quota allocation framework. Validated across 20+ competitions Jun-Sep 2026.

internscience Skill

Search PubMed for scientific literature. Use when the user asks to find papers, search literature, look up research, find publications, or asks about recent studies. Triggers on "pubmed", "papers", "literature", "publications", "research on", "studies about".

pinocpie Skill

เขียน methodology

pinocpie Skill

เตรียมสอบ defense thesis

pinocpie Skill

สรุป Research Paper

pinocpie Skill

โครงร่างวิทยานิพนธ์

pinocpie Skill

ทำ Literature Review

pinocpie Skill

ตั้ง research question

pinocpie Skill

จัด citation APA/MLA/Chicago

jimmc414 Bundle

Deep Research Skill

ptreezh Bundle

Use when needing advanced CLI assistance with persistent planning and research capabilities - provides automated context injection and skill orchestration

ptreezh Bundle

Case Study expert. Provides case selection, data collection, thematic analysis, cross-case synthesis, and theoretical contribution assessment. Suitable for qualitative research, business case analysis, and empirical investigation.

ptreezh Bundle

Ethnography expert. Provides participant observation, field note writing, cultural immersion assessment, thematic analysis, and ethnographic validity checking. Suitable for anthropological research, cultural studies, and qualitative field work.

ptreezh Bundle

Digital Marxism expert. Provides class analysis, surplus value calculation, alienation assessment, and crisis trend prediction. Suitable for digital labor research, platform economy analysis, and critical theory studies.

wanghaisheng Skill

当用户需求不明确、假设需要验证或设计简报识别理解差距时使用 - 规划需要学习什么、使用哪些方法以及从谁那里学习。

jmsktm Skill

Conduct qualitative user research, synthesize insights, and inform product decisions through interviews, usability testing, and behavioral analysis

jmsktm Skill

Academic research synthesis, paper analysis, and comprehensive literature reviews across disciplines

jmsktm Skill

Deep competitive research and monitoring using OSINT techniques and automated tracking

carta Skill

Researches a company by fetching its website and returning structured profile data. Use this skill when the user says things like "enrich this company", "look up company info", "research this company", "what does [domain] do", "get company details for [url]", "find info on [company]", or "/enrich-company". Input: target (domain name or website URL). Output: structured JSON with name, industry, tags, description, and website. Saves the result locally at ~/.carta-crm/enriched-companies/ for auditing.

notysoty Skill

Converts reviewed X/Twitter evidence into compact source packets for research and writing workflows.

qte77 Skill

Integrate Phase 0 and Phase 1A outputs into TAM/SAM/SOM sizing, buyer personas, and market entry signals. Run after `analyzing-source-project` and `researching-industry-landscape` (Phase 1B).

qte77 Skill

Score product-market fit from Phase 1B market analysis; produce PMF score, evidence matrix, and risk register. Run after `researching-market` (Phase 2).

frankxai Skill

Use when you need to find, retrieve, or research anything across vaults, repos, or the web — executes semantic search with full provenance, deduplicates across sources, flags contradictions, and returns ranked results sourced to the exact vault atom, file, or URL. Default skill for Starlight Hermes; callable by all agents.

frankxai Bundle

House of On-Chain skill. Auto-activates on /crypto-onchain-* commands or work within verticals/crypto-intelligence/onchain/. Enforces R5 non-advisory clause inline, chain-data source citation, mechanism-context grounding, named output artifact discipline.

frankxai Bundle

The <SUB-SYSTEM> skill inside the <DOMAIN> Domain Sub-Stack. Loads when any /<SLUG>-* command fires or when <SUB-SYSTEM> keywords are detected. Carries the research-grounded protocol this sub-system runs.

arcadeai Skill

Extract tacit knowledge through non-obvious microquestions — things only the user knows that can't be found in code, docs, or research. Use when you're about to guess at intent, context, or constraints during SAFEWORD's understanding flow. Also use when user says 'ask me', 'what do you need to know', or when another skill (bdd, brainstorm, debug) needs user context before proceeding. Do NOT use for questions answerable by reading the codebase or searching the web.

arcadeai Skill

Tests whether a proposed product bet has credible demand. Use when Why now depends on an unresolved, decision-critical demand claim or when the user explicitly asks for demand research. Do NOT use for child features, mandated work, parity work, or when a cheaper experiment can answer the question before research.

8421bit Bundle

Analyzes market opportunity and sizing using TAM/SAM/SOM framework with supporting data research. Use when evaluating market potential, creating business cases for new products, preparing investor presentations, or assessing business opportunities.

valentinnikolaev Bundle

Create, tailor, revise, or critique truthful cover letters, covering letters, motivation letters, and job-application letters from a job description plus verified candidate evidence. Use when Codex should analyze role requirements, map a resume, CV, portfolio, or brag document to them, research company-specific motivation, or produce an application-ready letter. Do not use for resume-only work, recommendation letters, or generic business correspondence.

l4ci Bundle

Use when the user wants deep, PhD-level research on a topic. Runs a STORM-style multi-perspective investigation by fanning out parallel expert subagents (each doing its own retrieval), mapping where they contradict, synthesizing a CEO-grade briefing, then peer-reviewing it with a panel of independent critics that assign confidence scores and name the gaps.

sylphxai Bundle

Assess one product or operations domain into ranked findings for a named go/no-go, hold, or risk decision. Use when the user asks for a domain review or assessment that no dedicated review listing covers. Do not use to design the system under review, critique a single claim, or synthesize a literature.

sylphxai Bundle

Synthesize multi-source evidence into one bounded brief with residuals, conflicts, and the next observation worth buying. Use when a consequential question needs a traceable literature or evidence synthesis. Do not use for a single-claim critique, a domain go/no-go review, or ordinary product implementation.

xopoko Bundle

Route broad or ambiguous Swift and Apple-platform work to a focused skill; this router does not implement domain work. Covers iOS, macOS, SwiftUI, Xcode, Simulator, App Store Connect, Tuist, SwiftPM, signing, profiling, and Apple research.

xopoko Bundle

Apple developer articles: search Swift, SwiftUI, Xcode, iOS, and macOS community blogs, tutorials, and write-ups, not official docs.

carlheath Skill

Evaluation skill for AI output: apply measurable criteria to text/code/ research/policy. Supports four eval types: rubric-based (1-5 scale), pairwise (A vs B), checklist (binary), and red-team pass (uses thinking-redteam). Output: score + reasoning + improvement suggestions. [WHAT] Structured way to answer "is this good enough?". Uses domain rubrics: chronicle quality, memo rigor, academic precision, OSINT credibility. Eval is a feedback mechanism, not a gate. [WHEN] Use when: evaluate, score, judge, "is this good enough?", "rate this", quality check, compare A vs B. NOT for: fact-checking (use fact-check), academic peer review (use academic-opponent). [LANGUAGE] English and other languages; matches input.