Research & Search

aaron-he-zhu Skill

`serp-analysis` has moved

aaron-he-zhu Skill

`keyword-research` has moved

aaron-he-zhu Skill

`competitor-analysis` has moved

aaron-he-zhu Skill

`content-gap-analysis` has moved

howells Skill

This skill should be used when the user asks to "write a chapter", "write prose", "continue the story", "develop a character", "review my chapter", "critique my manuscript", "write a synopsis", "summarize my story", "plan my novel", "outline my book", "check for consistency", or mentions fiction writing, novels, short stories, scenes, or narrative craft.

ifuryst Bundle

Create analytical charts, data visualizations, diagrams, dashboards, and Sankey or flow visuals from research data. Use when a task asks to draw, plot, graph, visualize, chart, compare, summarize data visually, build an analysis figure, create an interactive chart, or choose the right visualization method.

ifuryst Bundle

Collect and analyze recent company news, press releases, media narratives, executive changes, product updates, regulatory events, and dated catalysts for an investment target. Use for information-side or news-side research such as "what happened recently with Intel" before thesis synthesis.

ifuryst Bundle

Analyze earnings releases, earnings-call transcripts, management commentary, analyst Q&A, guidance changes, and language shifts for investment research. Use when the user asks about quarterly results, management tone, guidance, or what changed in the latest earnings call.

ifuryst Bundle

Collect, read, and summarize company filings and formal disclosures for investment research. Use for SEC filings, annual reports, 10-K, 10-Q, 8-K, proxies, risk factors, management discussion, regulatory notices, and disclosure-change analysis.

ifuryst Bundle

Resolve an investment research target into canonical identifiers and initial context. Use when a user names a company, ticker, sector theme, watchlist item, or ambiguous phrase such as Intel, INTC, Apple, chip stocks, or AI infrastructure before running AIFi research workflows.

ifuryst Bundle

Orchestrate a full AIFi company research workflow from a user request such as "understand Intel recently" into target resolution, evidence archiving, news, filings, earnings, financials, market signals, competitive landscape, and investment thesis synthesis. Use when multiple AIFi research skills must be combined into one application-like workflow.

carapace-sh Bundle

Use when creating a compound skill — a structured knowledge base for a project or topic that uses a SKILL.md routing table and reference documents. Covers the research phase, topic decomposition, SKILL.md frontmatter and routing table format, reference document structure, cross-referencing, and maintenance. Triggers on: "compound skill", "create skill", "write skill", "skill template", "skill structure", "routing table", "reference document", "skill authoring", "skill creation guide".

caufieldz Bundle

Answers factual, conceptual, and decision-making questions about TRTC from authoritative sources. Use when the user asks about pricing, quotas, error codes, API usage, product comparisons, migration, or how something works conceptually — in any phrasing (e.g. "how much does X cost", "多少钱", "X vs Y", "对比", "error code 6206", "错误码", "does TRTC support Y", "配额", "the correct way to use X", "X是什么", "how does X work", "migrate from V3 to V4", "迁移"). Retrieves answers from DocsBot knowledge base (fact/decision/path questions) and local knowledge-base slices (error-code / API-pattern lookups) — never training-data synthesis.

frankxai Skill

Use when collecting web/design references, competitive visuals, licensed examples, product captures, moodboards, and exactly three original visual directions with traceable sources and rights boundaries.

gnurio Skill

Represent messy work as durable obligations, workflow building blocks, fragments, AI/automation insertion points, and exception queues. Use this whenever the user wants to analyze interviews, messy notes, customer research, operational workflows, PM workflows, vertical SaaS opportunities, AI insertion points, automation opportunities, "durable obligations", fragmented work, hated execution burden, or where AI should fit into an existing workflow. This skill is primarily a thinking and workflow-mapping tool, not a startup idea generator.

gonglingrui Skill

市场调研/行业研究报告写作（含 TAM/SAM/SOM、PESTLE、波特五力、SWOT）。涉及文件解析、数据建模、图表与长文输出时，委托 OpenCode 执行。

ibm Skill

Understand the work done in an ado project/context: recent activity, research underway, study documents, spaces and operations over time, experiments and configs used. Use when the user asks for the latest or recent activity in a project; what research strands, studies, or work are underway; a project or context overview or status; trends across spaces/operations/studies; or to onboard onto an ado project.

ibm Skill

Describes how to create documents (document resources) that track an in-progress research study: motivation, question, objectives, materials, study labels, and a todo list of next steps. Use when starting a study, creating a study document, updating study todos/objectives, or when the user mentions a study document by name (e.g. study-$ID) or asks about study tracking.

ichangyou Bundle

Use when starting a new project, exploring a product feature, evaluating technical directions, or planning content strategy - especially in early research phase where options are unclear and structured divergent thinking is needed before committing to a path.

jakkaj Skill

Craft structured, domain-aware research prompts to leverage deep research agents for solving coding challenges. V2 with domain boundary awareness.

jakkaj Skill

Deep shopping research skill for finding products similar to a reference link or image, benchmarking global pricing, comparing quality/provenance, and creating a reusable buying dossier with links, per-item prices, shipping notes, and value-focused recommendations.

laimis91 Bundle

Gather and synthesize source-backed information. Use for explicit research, topic investigation, current evidence, or requests to compare options.

lawzava Skill

Use to research a decision that needs evidence beyond the repository, such as current upstream behavior, historical rationale, cross-system incidents, or contested claims. Do not use for repository-only code tracing or a summary of provided material.

aiyo28 Skill

Composable decision skill. Core OODA loop: present options, assess confidence, record reasoning artifact with priority matrix. Modes: default (decide from current context), --research (ingest source first, then decide), --reframe (force perspective shift before options). Triggers: "decide", "should we", "which option", "evaluate", "compare", "research this" (with decision intent), "let's think about".

bongsuchoi Bundle

Analyze public video URLs and local video files from frames plus timestamped captions or authorized transcription. Use for YouTube, Vimeo, TikTok, X, Twitch, and local .mp4, .mov, .mkv, .webm, .m4v, .avi, .flv, or .wmv when the user asks to summarize, inspect a moment, diagnose a screen recording, compare visual and spoken claims, extract a structure, or answer questions with timestamped evidence. Do not use for ordinary webpage interaction or a final rendered-product UI verdict; route those to cx-browser-automation or cx-visual-qa.

bongsuchoi Bundle

Perform deep, source-backed research only when the user explicitly requests research, deep research, evidence-based investigation, careful comparison, or citation-heavy multi-source synthesis. Do not use for an ordinary current-fact lookup, a simple web question, or reading one accessible page.

epistates Skill

Research trending topics, conversations, and content opportunities for X posts. Use when the user wants content ideas, wants to know what's trending in their niche, or needs to research what to post about.

haochenhust Skill

This skill should be used during daily research scanning, or when the user asks '最近有什么新消息', '扫描一下XX的最新动态', '帮我看看雪球上在聊什么'. Scans Xueqiu, Eastmoney, 10jqka, and web search for investment-related news filtered by the industry-chain keywords you track. Outputs HIGH/MEDIUM findings only — signal, not noise.

haochenhust Bundle

This skill should be used when the user asks '查一下XX的行情', '拉一下财务数据', '估值数据', 'PE/PB多少', '股东变化', '业绩预告', or when any analysis/research task needs A-share market data, financial statements, valuation metrics, or shareholder data. Tushare Pro is the PRIMARY structured data source — more stable and comprehensive than AKShare. Requires a TUSHARE_TOKEN env var (your own Tushare Pro token).

haochenhust Skill

This skill should be used when the user asks to '梳理一下XX产业链', '这个行业的上下游是什么', '哪个环节弹性最大', or when starting research on a new industry theme. Builds and maintains persistent industry-chain maps (upstream/midstream/downstream, key companies, market share, investment-elasticity ranking). Artifact-focused; complements the process-focused industry-chain-research skill.

haochenhust Bundle

产业链研究：从宏观趋势拆解产业链、定位瓶颈环节、找到具体标的、交叉验证风险。核心理念——不问AI"买什么"，在结构化框架里让AI做产业链研究员。Use when user says 产业链分析, 拆产业链, 产业链研究, 瓶颈分析, 景气度投资, supply chain analysis, industry chain, "帮我拆一下XX产业链", "XX赛道有哪些机会", or wants to systematically research an industry theme for A-share investing.

helloweit Bundle

深度研究某主题，输出结构化研究文档，包含可落地建议。Use when user says "/research", "研究", or wants to do deep research on a topic.

helloweit Bundle

从研究成果中抽象出可复用的知识模型，写入知识库供后续引用。Use when user says "/knowledge", "知识沉淀", "抽象模型", or wants to extract reusable knowledge from research.

manazoid4 Skill

Answer questions using the Obsidian wiki vault. Reads hot cache first, then index, then relevant pages. Synthesizes answers with citations. Files good answers back as wiki pages. Supports quick, standard, and deep modes. Triggers on: what do you know about, query:, what is, explain, summarize, find in wiki, search the wiki, based on the wiki, wiki query quick, wiki query deep.

manazoid4 Bundle

Autonomous iterative research loop. Takes a topic, runs web searches, fetches sources, synthesizes findings, and files everything into the wiki as structured pages. Based on Karpathy's autoresearch pattern: program.md configures objectives and constraints, the loop runs until depth is reached, output goes directly into the knowledge base. Triggers on: "/autoresearch", "autoresearch", "research [topic]", "deep dive into [topic]", "investigate [topic]", "find everything about [topic]", "research and file", "go research", "build a wiki on".

manazoid4 Skill

Hybrid retrieval primitive for the Compound Vault. Replaces the v1.6 static hot→index→drill read order with contextual-prefix + BM25 + cosine-rerank, modeled on Anthropic's Sept 2024 Contextual Retrieval research (35-49-67% retrieval-failure reduction). Opt-in via `bash bin/setup-retrieve.sh`; feature-detected by wiki-query and autoresearch. Triggers on: retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, search the chunks, chunk search, vault search, semantic search, what chunks match, find relevant passages.