Research & Search

dcouple Bundle

Creates a reconciled implementation plan by combining a structured plan draft with a normalized intent brief and a PRP-style research dossier, then auto-reviews the final plan. Use when planning a new feature or significant change.

m-sec-org Skill

Payload crafting and bypass research for vulnerability verification

nightdreams-bat Skill

Surface the few passages from a world-class expert's body of work that hit the user's exact current situation — with verbatim quotes and source pointers — plus at least one gap where the expert shows the user is wrong or missing something. Use when the user says "signal from expert", "what would <person> say about this", "pull <expert> on <topic>", or wants an outside authority pressure-tested against their own raw thinking. Invoke with /signal. Differentiator vs /research: not a neutral memo — a targeted match between one expert's real words and the user's real notes, ending in a challenge.

hhhh124hhhh Skill

Context7 Auto Research

sidiangongyuan Bundle

Use when exploring, continuing, or accepting a deep-learning or computer-science research idea. Converts claims into pilot-first experiment matrices covering diagnostics, failure analysis, authorized execution, evaluation, and paper-story viability.

sidiangongyuan Bundle

Search, screen, deeply read, synthesize, and publish recent research papers for a user-specified topic, window, count, quality/attention balance, and language. Use for evidence-anchored literature digests, cross-paper comparisons, original-language excerpts, Chinese explanations, guided Feishu setup, or Feishu research reports.

sidiangongyuan Bundle

Use when preparing or publishing a local project as a clean GitHub repository. Covers new repositories, private staging releases, public README cleanup, updates to existing remotes, and research-code packaging without datasets, checkpoints, papers, or generated artifacts.

sidiangongyuan Bundle

Use when refining research-paper prose or section logic, including abstracts, introductions, related work, methods, captions, conclusions, and rebuttals. Improves clarity, concision, transitions, terminology, notation, and venue-appropriate style without inventing evidence.

silvio-l Bundle

Fetch a shared AI chat link (chatgpt.com/share, gemini.google.com/share, claude.ai/share) without a browser and distill it into a structured knowledge base by default. Use for share links, 'Wissensbasis erstellen', 'Chat aufbereiten'.

silvio-l Bundle

Extract the full conversation from a ChatGPT/Claude.ai/Gemini chat open in Safari's frontmost tab when no share link exists. Use when the user wants to read/summarize/save a Safari chat tab, "diesen Chat aus Safari holen", or sharing is unavailable.

sipengxie2024 Bundle

Turns a chosen research area into publishable directions through three internal phases. It generates candidates with named lenses and FINER scoring, adjudicates novelty per technical claim against prior work, then evaluates against a top-venue bar with a fatal-flaw short-circuit. All verdicts stay advisory. Use when a research direction is undecided, when choosing a topic, when evaluating an idea, or when checking novelty (查新).

sipengxie2024 Bundle

Polish prose in three passes: strip AI-writing tells, apply Strunk's rules for clarity, then hold every research claim to its evidence. Two modes: edit in place, or diff-first where the original is untouched until the user approves each change. Use when the user asks to 润色 / 改写 / 精修 / 打磨 a draft, or says "polish", "refine", "tighten", or "improve". Preserves meaning, numbers, citations, and [NEEDS-EVIDENCE] markers; never smooths an unsupported claim into a supported-sounding one.

sipengxie2024 Skill

Use when starting a new paper or when `.writing/outline.md` is missing or needs a major restructure. Converts a research idea into an IMRAD outline plus a per-section claim list, sharpened through an interleaved interview. Produces `.writing/outline.md` (structure + key claims), `.writing/claims/section_*.md` (claim stubs), and a filled `.writing/metadata.yaml`. No manuscript prose is written here, this is the spec phase before drafting.

sipengxie2024 Bundle

Use whenever a writing task will span more than 5 tool calls, multiple sessions, or risks hitting context-window limits, writing a paper, a long literature thread, a multi-section revision, anything where losing mid-task state would hurt. Creates a persistent `.writing/` directory that acts as working memory on disk, so the outline, claims, findings, and progress survive context resets. Every other superpower-writing skill assumes this directory exists; initialize it first. Trigger even when the user does not explicitly ask for "planning".

tavily-ai Bundle

Migrate an existing integration from a competing web-search/research API — Exa, Firecrawl, Perplexity, or Parallel — over to Tavily, preserving behavior while swapping calls, imports, environment variables, and error handling. Use this skill when the user has working code against a competitor's SDK and wants to switch providers, or says "migrate this to Tavily", "switch from Exa/Firecrawl/Perplexity/Parallel to Tavily", "replace this competitor API with Tavily", or "port this integration over". Do NOT use this for greenfield Tavily integrations with no existing competitor code — start with tavily-best-practices instead.

tavily-ai Skill

Screen vendors, merchants, suppliers, counterparties, companies, executives, and related entities for vendor risk, KYC, adverse media, sanctions, regulatory actions, litigation, recalls, supplier risk, cybersecurity incidents, and compliance concerns. Use when the user asks for vendor onboarding research, KYC screening, supplier due diligence, merchant case research, or a source-grounded risk brief.

tavily-ai Skill

Create concise investment research briefs, company memos, sector snapshots, portfolio monitoring updates, earnings/news summaries, risk and catalyst briefs, and market thesis support. Use when the user asks for an investor-focused brief on a company, sector, public/private market, comparable set, or portfolio theme.

tavily-ai Skill

Find, screen, and synthesize academic papers, scientific literature, technical reports, preprints, clinical or biomedical publications, and evidence around a research question. Use when the user asks to find papers, summarize literature, compare methods, identify seminal or recent work, extract claims from studies, or build a source-grounded academic/scientific evidence brief.

adjustleads Skill

Use when someone asks what clock applies to a claim in a state. Researches current statute and policy conditions, cites each source, lists deadlines to confirm.

anarefin Skill

Deep-read any article, blog post, or web page and produce a structured expert analysis: concise summary, key bullet points, reader action items, and domain-adaptive expert commentary. Use this skill whenever the user shares a URL (Medium, Substack, dev.to, HN, any blog) or pastes article/post content and asks to "summarize", "analyse", "break down", "review", "read this", "what do you think of this", "give me the key points", "TL;DR this", or similar. Also trigger when the user drops a raw URL without any instruction — assume they want the full analysis. Works for any domain: engineering, product, finance, science, design, business, etc.

atgreen Bundle

Use when a genuine unknown blocks progress — "can this even be done?", an unfamiliar API or library, an uncertain approach — and you're tempted to either research forever or build production code around something you don't yet understand. Not for wiring a known design thinly end-to-end (that's walking-skeleton), nor for polishing working code (whittler)

ericgandrade Bundle

This skill should be used when the user needs to format a curriculum vitae for academic positions including faculty, research, or postdoc roles. Use when organizing publications, grants, teaching experience, presentations, and service for tenure-track, lecturer, or research scientist applications.

ericgandrade Bundle

This skill should be used when the user needs to research market rates, build a salary negotiation strategy, and create counter-offer scripts. Use when preparing to negotiate a job offer, requesting a raise, evaluating compensation packages, or responding to lowball offers with data-backed confidence.

exon-research Skill

Journal sub-skill for focused public/source evidence review and reviewed finding write-back before interpretation or answer synthesis.

michael-f-bryan Bundle

Query a structured repository knowledge base intelligently using ontology-aware routing, manifests, indexes, metadata, shortlist-based retrieval, and bounded deep reads. Prefer navigation and recognition over blind grep.

jiahongc Bundle

Shared research policy and output contracts for the card command suite (card-full, card-transfer, card-rate, card-news, card-credits, card-compare, card-value, card-wallet). Use as background reference, not as a user-facing command.

lassejlv Bundle

Research and implement a comprehensive, evidence-first code-quality cleanup with exactly eight specialized subagents. Use when a user asks to clean up, simplify, modernize, de-slop, or improve an entire repository across duplication, shared types, unused code, dependency cycles, weak typing, defensive error handling, legacy paths, and low-value generated-looking code. Each subagent produces a critical assessment and recommendations, then implements only high-confidence changes after central conflict resolution.

001tmf Bundle

BY Research Skill

cmolg Bundle

Cognitive Extraction Engine for UX researchers — especially the "conductual" (behavioral) kind. Use when a user wants to clone the judgment of a researcher who studies user behavior — how they design studies, frame research questions, interview, observe, synthesize, and influence decisions. Trigger on phrases like "extract my research thinking", "clone our UX researcher", "build an AI that drafts interview guides like me", "interview me about behavioral research", "capture how I synthesize user interviews", "make a UXR cognitive clone". Outputs are tool-agnostic.

pilinux Skill

Precisely read source files or snippets and return concise, citation-backed facts needed for decisions or edits.

pilinux Skill

Produce concise, citation-backed explanations of module behavior, data flow, and important types/APIs.

pivoshenko Skill

Turn rough notes, a transcript, or a URL of a talk/video/book/article/paper into a polished source note in the Obsidian vault's 05 SOURCES. Use when the user says "summarize this talk/video/book/article for my wiki", dumps watch/read notes, shares a YouTube link to digest — and also on wiki-free phrasings like "I just watched/read/finished…", "great talk about X", "notes from the conference". Updates the concept pages the source touches.

poorvith-mp Bundle

Write grant applications for nonprofits, research institutions and social enterprises, including prospect research. Use when authoring grant applications, proposal narratives, or budgets.

scraperapi Bundle

Use this skill whenever the user wants to enrich a contact or company and build a profile. Trigger on: "enrich this lead", "find info about [person or company]", "build a contact card for X", "I have this LinkedIn URL, find more about them", "find the email for [person] at [company]", "research this contact", "I have an email, can you find more details". Accepts any seed input — a name, company name, LinkedIn URL, email address, domain, or any combination. Executes ScraperAPI calls directly to search Google and fetch web pages, then synthesizes all findings into a structured contact card covering person fields (name, title, email, phone, LinkedIn, location, social) and company fields (domain, revenue, funding, employee count, founded year, HQ, tech stack, key investors, recent news, competitors). Note: Transmits user-supplied queries, URLs, and content to ScraperAPI.

scraperapi Skill

Market research powered by live web data. Use this skill when the user wants to understand a market, category, or customer segment — including consumer sentiment, demand and trend signals, price and category structure, or the competitive landscape. Trigger on requests like "research the [X] market," "what do customers think about [category]," "how is [category] priced," "what trends are shaping [industry]," or "who are the players in [space]." Note: Transmits user-supplied queries, URLs, and content to ScraperAPI.

shetengteng Skill

苏格拉底式批判性思维分析。自动识别需求分析、系统设计、技术选型、数据分析四类场景，智能决定快速结论（≤1问）或深度探索（≤5问），防止过度追问与草率结论。Socratic critical thinking for requirements, design review, tech research, and data analysis.