Research & Search

hhfinai Skill

Systematic framework for analyzing corporate networks to generate investment alpha. Use when analyzing supplier-customer relationships, director interlocks, executive networks, insider holdings patterns, or identifying M&A signals through board connections. Triggers on supply chain analysis, customer momentum, board interlock, director network, connected party analysis, relationship mapping, or network-based investment research.

hhfinai Bundle

Comprehensive framework for conducting institutional-quality thematic investment research. Use when the user asks to: (1) Identify and validate investment themes, (2) Analyze thematic market opportunities and value chains, (3) Build a thematic stock universe and screen candidates, (4) Conduct company deep dives with thematic focus, (5) Value companies using theme-appropriate methodologies, (6) Assess theme-level and company-level risks, (7) Write thematic research reports, (8) Design portfolio implementation and monitoring frameworks. Triggers on phrases like thematic research, investment theme, secular trend analysis, theme validation, thematic universe, value chain mapping, or requests for structured investment research methodology.

zhangfengcdt Skill

Recall facts from past sessions via memoir for questions or tasks that may depend on prior preferences, decisions, conventions, or knowledge. Use one fast summarize/get pass by default, exclude metrics unless requested, never call legacy `memoir recall`, and defer repo-structure onboarding questions to memoir-onboard.

englandtong Bundle

Route complex AI-assisted work across project lifecycle guidance, formal project governance, coding execution, session memory, web-research intake, and cross-source synthesis without creating competing state. Use when a request spans two or more of these surfaces, the user is unsure which workflow skill applies, or a combined research-to-project-to-handoff flow needs clear authority and ordering. Typical triggers include 我这个需求该用哪个 skill, which skill should handle this, 研究和开发一起做, research then implement then hand off, 这个项目该怎么管, orchestrate this across skills, 从头到尾帮我跑一遍, and end-to-end AI workflow. Delegates to specialized skills when installed and uses bundled modules only as reduced-fidelity fallbacks. Applies a subtraction-first guard so a combined request does not silently become new scope.

pax-k Bundle

Maintain a durable multi-session decision map when the destination is meaningful but the implementation path cannot yet fit in one trustworthy planning session. Use only when the user explicitly invokes this skill for a foggy effort that needs research, prototypes, founder decisions, or technical decisions before feature planning.

konata9 Bundle

基于调研资料，用"故事化"手法撰写中文科普/历史类长文初稿。 当用户要求写故事、故事化写作、根据调研写文章、创作正文、写初稿时触发。 也应在写作流程中 research 完成后自动调用。 覆盖标题设计、导读块、开篇钩子、叙事技法、AI 痕迹规避和小红书配文。 润色（humanize-plus）和平台合规（publish-guard）不在本技能内执行，由主编排技能随后调用。

konata9 Bundle

对文章创作前的调研事实进行交叉验证和来源可靠性评级，输出结构化验证报告。 当用户要求验证事实、交叉验证、检查来源可靠性、fact-check、核实资料， 或提到"交叉验证""来源可靠性""验证来源""fact-check"时触发。 也应在写作流程的调研阶段自动调用：research 完成后、story 动笔前， 对 research 中的关键事实逐条做交叉验证。

lechuanwang Bundle

Evidence-led China and cross-asset investment research. Use for A-share, Hong Kong, or US equity research; all-market financial-statement screening; China macro analysis; ETF, fund, index, futures, spot commodity, option, convertible-bond, or foreign-exchange research; technical or catalyst screening; entry or exit analysis; portfolio review; price or news attribution; research planning; decision evaluation; or research-source archival. Use persistent research memory only when the user explicitly asks to read, reuse, save, ingest, or update it.

lechuanwang Bundle

Independent investment research cross-examination for explicitly requested deep research, review, or challenge of evidence, assumptions, valuation, competition, governance, and tail risks.

lechuanwang Bundle

Evidence-led long-horizon investment research for multi-year holdings, company quality, financial quality, governance, capital allocation, and long-term valuation.

lechuanwang Bundle

Evidence-led short-term trading research for one-month events, technical analysis, momentum, factor screens, entries, price dislocations, and price-led 1-3 month decisions.

lechuanwang Bundle

Evidence-led medium-term investment research for 3-6 month earnings, order, supply-demand, policy, product, or valuation catalysts and catalyst-led 1-3 month decisions.

ootto-ai Skill

Turn a long email thread into key points and the decision needed. Use when the user says "summarize this thread", "catch me up on this email", "what's this thread about", "TL;DR this thread", "what do I need to do here", or "summarize this email chain".

poisoneddiety Bundle

Verify citations in a legal draft — court level, reporter, neutral citation, pinpoints, and whether each authority was actually retrieved. Catches court-level misattribution, which is the error most likely to survive proofreading and destroy a paper in a viva. Use this on any paper, response paper, memo, or footnote set before submission, and whenever the user asks to check, verify, or clean up citations or footnotes. Do NOT use to generate new citations.

poisoneddiety Bundle

Extract the argument, evidence type, concessions and citable propositions from a journal article, book chapter, working paper, or assigned reading, and place it on a map of the debate. Produces material a literature section can argue with rather than a summary. Use this whenever the user uploads or names scholarship, asks what a piece argues, or is gathering sources for a paper. Do NOT use for case law, statutes, or drafting prose.

poisoneddiety Skill

Explain a legal doctrine, concept, case, statutory provision, or assigned reading in full depth for note-making and comprehension. Produces the reasoning a summary leaves out — the problem the doctrine solves, the facts that shaped it, the competing formulation, and the boundary conditions. Use this whenever the user asks to explain, unpack, walk through, or make notes on a legal concept, reading, or judgment, even if they just say "explain X". Do NOT use for exam answers, drafting, or research.

poisoneddiety Bundle

Research Indian law online — case law, statutes, regulatory material, recent doctrinal developments, or academic literature. Enforces a source hierarchy, targeted search operators, currency checks, and per-citation retrieval status so nothing unverified reaches the page. Use this whenever the user asks about Indian cases, statutes, sections, judgments, regulators (SEBI, RBI, MCA, CCI, IBBI), law reform, or wants sources for a paper or seminar — even if they do not say "research". Do NOT use for non-Indian law or for drafting prose.

rkelln Skill

Build and publish production-ready Hermes skills — research, author, review, ship.

rkelln Skill

Research existing Hermes skills before building — search all registries, GitHub topics, and awesome lists to find duplicates, adjacent tools, and gaps.

skillmedev Skill

Structures and writes authoritative B2B whitepapers - a standalone executive summary, a data-sized problem statement, methodology, evidence-driven findings, recommendations, and a soft call to action - flagging every claim that needs a real citation. Use when a marketer asks "write a whitepaper on this topic", "turn our research into a lead-gen asset", "make this credible enough for executives", or a draft reads like a product pitch instead of analysis. Do NOT use for customer-story-driven proof - use case-study-builder instead; for policy audiences, use policy-brief.

azhi-ss Bundle

Analyze ML, AI4Science, Systems, and research repositories into an evidence-backed semantic architecture graph for paper figure planning. Code serves as supporting evidence; paper narrative and user intent remain the primary source of truth.

bayramannakov Bundle

Apply Karpathy's autoresearch loop (goal + mechanical fitness + mutable surface + keep-or-revert iteration) to ANY measurable workflow - code, content, sales, research, design, operations, not just ML or software. Use when the user asks to set up an overnight improvement loop, a keep-or-revert experiment workflow, iterative optimization, or asks "can I autoresearch this?". Includes a pre-loop triage that refuses fat-tailed, reflexive, or slow-feedback problems without adapting the mode.

bitcoin21ideas Bundle

Interviews the user relentlessly about a plan, design, or proposal until shared understanding is reached, walking the decision tree branch by branch and resolving dependencies one at a time. Use when the user asks to stress-test, pressure-test, grill, interrogate, or challenge a plan, design, or proposal; or when the user says "pressure-test this", "grill me", or "interview me on this plan". Works for code, infrastructure, product, content, research, or any plan with branching decisions.

faces-sh Skill

Use this skill when the user wants to create an AI persona from scratch — a digital twin, an archetype, a composite, or a face of a public figure. Invoke as /facemake "Name" for quick mode (skip interview, go straight to research), or /facemake with no argument for the full guided flow. This skill walks through the entire process: interview, research real source material, sketch a FACE.md recipe, iterate with the user, compile, and optionally Trigger when the user says "create a face", "I need a persona", "make me a digital twin", "build a face for", or names a person they want to turn into an AI. Also trigger on /facemake.

fradser Skill

Harvest problems (from ~/.Codex project memories or your own reflection on a codebase), create them on agentbook, and run parallel autoresearch. Trigger on "harvest", "scan problems", "agentbook research".

fw-ai Bundle

Diagnose Fireworks training and deployment issues, including stuck or failed jobs, error messages, poor quality, checkpoint and resume problems, and deployments that are ready but not serving. Use for systematic read-only triage before retrying. Use configure for a new or approved retry run; use research when the starting method, data, or cookbook example is unclear.

fw-ai Skill

Deprecated redirect — use research instead. Renamed in v2.2.0 to match Tinker cookbook conventions. For exploring method, data, eval, and cookbook entries use research; for training execution use configure; for failures use debug.

fw-ai Bundle

Compatibility redirect and shared reference carrier for the Fireworks training skills. Use research to choose method, data, evaluation, and a cookbook entry; use configure to plan and run training; use debug for stuck, failed, or low-quality runs. Keep this skill installed so the three entry skills can load its progressive references.

gexijin Skill

Search PubMed for scientific literature. Use when asked to find papers, search literature, look up publications, or gather references on a topic. Returns article titles, authors, abstracts, and PMIDs.

ghost-him Bundle

总结当前代码更改，生成结构化的 commit message 或变更摘要；变更结束后直接调用时结合对话上下文精准提炼改动目标

convergeai-labs Bundle

Run explicit AnyCap multi-source investigations, market or competitive research, technical deep dives, literature/state-of-the-art reviews, evidence-backed comparisons, and the specialized football/World Cup dossier and entertainment-only prediction route. Not for local code analysis, single-source lookup, ordinary article drafting, or betting advice.

datalayer Bundle

Summarize text from a file or inline input. Use for concise summaries and key-point extraction.

dbhq-uk Bundle

Produce a plain-English status digest of a Trello board - lists and their cards, what is due or overdue, and what moved recently. Trigger on phrases like "board status", "trello standup", "what's happening on the board", "board digest", "summarise my board".

vanillaflava Bundle

Distil a chat thread, research session, or working document into a structured wiki page capturing the current state of knowledge. Always use this skill when the user says /wiki-crystallize, 'save this to my wiki', 'capture what we've worked out', 'write this up as a wiki page', 'update my wiki from this conversation', 'we've covered a lot', 'before I close this chat', or 'let's wrap up this thread'. Also use proactively when the conversation has covered significant ground and capturing the findings would orient future sessions, the context is getting heavy and insights risk being lost, or the user signals they are ending a working session - even if they don't say 'wiki'. The chat is the scaffolding; the wiki page is the artefact. When in doubt whether a session wrap is being requested, use this skill. Requires filesystem read/write access.

jackywxsz Skill

把 AI 对话中有价值的内容沉淀到 Obsidian 知识库。 检索知识库内容回答问题，只基于已有内容，不杜撰。 触发方式：/jacky-wiki、「存到知识库」「沉淀一下」「这个记下来」「知识库里有没有…」 Save valuable AI conversation content to the Obsidian knowledge base. Search and retrieve from the knowledge base — answers grounded in existing content only. Trigger: /jacky-wiki, "save to KB", "remember this", "search KB", "知识库里…"

jezweb Skill

After a customer call (transcribed or hand-noted), file a structured summary to wiki/research/ and trigger extract-commitments. Use when founder finishes a call and says "@customer-success file this call" or similar.