Research & Search

andremoreira73 Bundle

Conduct structured market research for strategic decisions. Use when the user needs market analysis, competitive intelligence, or business research with formal deliverables.

mrbinnacle Bundle

Tracks AZIMUTH's 8 primary citation source families for new publications or significant updates. Stages validated findings in research/staged-findings.md for human review before promotion to references/base-rates.md. Invoke with 'run the research scout' or 'promote staged findings'.

mrbinnacle Skill

Authoring discipline for new AZIMUTH reference files and templates. Use when adding a new domain reference file, extending an existing one, or creating a new template. Covers: (1) EXTEND vs. CREATE decision heuristic, (2) the Module 7 vocabulary header pattern that prevents domain-gap recurrence, (3) the sourcing caveat pattern for narrow-evidence-base files, (4) pre-verdict gate structure for templates. Validated by research-mpbaese4 (2026-05-18).

ashishgoswami01 Bundle

Super Manager meta-skill that automatically finds, fetches, creates, and improves Claude skills on demand. ALWAYS use this skill when: - User asks to "add a skill", "install a skill", "find a skill for X", or "teach yourself to do X" - A task would benefit from a skill that isn't currently loaded - User says "learn how to do X" or "get better at X" - A skill execution fails or produces poor output and needs improvement - User says "search GitHub for a skill", "fetch skill from GitHub", or pastes a GitHub skill URL - Any request where Claude says "I don't have a skill for that" Works in BOTH Claude.ai (/mnt/skills/) AND Claude Code (~/.claude/skills/). Auto-detects environment and installs to correct path. Searches GitHub skill registries, fetches SKILL.md files, creates new skills via web research, and automatically improves existing skills after execution via feedback loop. This is the self-growing brain of Claude's skill system. Use aggressively.

ashishgoswami01 Skill

Deep quantum physics reasoning, explanation, and problem-solving skill. ALWAYS use this skill when: - User asks about quantum mechanics, quantum computing, quantum logic - Questions involving superposition, entanglement, wave function, qubits - Schrödinger equation, Heisenberg uncertainty, quantum tunneling - Quantum gates (Hadamard, CNOT, Pauli X/Y/Z), quantum circuits - Bell states, quantum teleportation, decoherence, measurement collapse - "Explain quantum [anything]", "how does qubit work", "what is superposition" - Quantum chemistry simulations, quantum error correction - Any topic where classical logic breaks down and quantum logic applies Works in: Claude.ai + Claude Code Source: created-fresh via web research (May 2026) Version: "1.0"

visionairelabs Skill

Collect and log feedback from [your name] after delivering significant work. Use after completing any meaningful deliverable — strategy docs, content drafts, brand work, code specs, research, creative briefs. Triggers when work is delivered and a response is received. Ask for a rating and optional comment, then log it. This feeds the self-study feedback-analysis loop.

modalitydance Skill

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

xiaolai Bundle

Research Skill

zakirkun Skill

Automatically persist useful context — research, decisions, learnings, templates — to workspace files so knowledge survives across conversations.

rawkode-academy Bundle

Research, validate, and set up technology profiles in Rawkode Academy content/technologies. Use when adding a technology, checking an existing technology profile, or updating its metadata and content.

1596941391qq Skill

Explain and summarize token consumption from lifecycle reports.

2389-research Skill

Use when a question needs parallel deep analysis from multiple perspectives - code reviews, architecture decisions, research synthesis - spawn specialized agents as a clearness committee rather than doing everything in one context

avyanshkatiyar Bundle

Build an adversarially-verified interview dossier on a company and one named interviewer for a specific high-stakes interview — four tiers from verified facts to a night-before decision frame, heavy web research, every claim sourced. Use when the user says "interview prep for <company>", "build a dossier", "I have a founder round", "research this company for my interview", "prep me for the CEO round", or wants serious research before a final/skip-level/founder interview rather than generic question lists.

brikerman Skill

Fetch internet content or conduct deep multi-source research. Quick access: search the web, read pages, extract video transcripts/subtitles from YouTube/TikTok/Twitter/Twitch/Vimeo/Bilibili/1700+ sites via yt-dlp, convert and compress media via FFmpeg. Deep research: collect multi-source data, cross-check facts, produce structured reports. Triggers: 下载, 获取, 提取, 下载字幕, 下载视频, 转换, 压缩, read web, fetch, search, research, investigate, YouTube, Bilibili, TikTok, Twitter, Twitch, Vimeo, Dailymotion, media, convert, compress, 抓取.

cabbagecachekid Skill

Use when any writing, review, research, or shipping task begins — reviewing, polishing, or shipping human-facing writing or web pages, mapping a user journey, or protecting creative work. Routes to the right neon-jetpack skill (line-edit, ai-written-check, cringe-check, full-review, ux-web-design-review, journey-map, copyright-creative-work) and defines how they chain, so the right depth of review runs in the right order.

cabbagecachekid Bundle

Use when reviewing a website, web page, screenshot, or web copy against UX best practices grounded in human behavior rather than current fashion — auditing readability, scannability, visual hierarchy, cognitive load, or trust, separating what's evidence-backed from what's merely in style, with every claim tied to a real cited source. Triggers include "how strong is this page," "review my site's UX," "is this good design or just trendy," "evidence-based UX check," or asking whether a layout/copy follows web usability research.

hbui290 Skill

Protocol for token-efficient web research. Use when accessing URLs, GitHub repos, or running search queries. Prevents full-page fetching waste.

benkapner Bundle

Use when starting work in a repository under repositories/ that may lack CI configuration. Detects missing CI workflows (GitHub Actions, GitLab CI, CircleCI) and alerts the user to add one. Skips repos marked as research-only.

software-mansion-labs Skill

Search the ExecuTorch tribal knowledge base covering QNN, XNNPACK, Vulkan, CoreML, Arm, and Cadence backends, quantization recipes, export pitfalls, runtime errors, and SoC compatibility. Use when debugging ExecuTorch errors, choosing quantization configs, checking backend op support, or answering questions about Qualcomm HTP / Snapdragon / Apple Neural Engine behavior.

fantasymax Bundle

{Skill 标题，人话版，对应 H1}

fantasymax Bundle

{Skill 标题}

fantasymax Skill

{Skill 链标题}

fantasymax Skill

{Coordinator 标题：N 视角并行 review/分析}

aboudjem Skill

Use when the user types /recap, /recap topic, /recap "<subject>", or asks Recap Studio to "make a one-page explainer", "summarize a topic", or "build a visual page about X". Routes to /recap session when the input is "session", "repo", or empty inside a git repo with uncommitted changes.

aboudjem Skill

Use when the user types /recap session, /recap repo, /recap session --deep, or asks Recap Studio to "explain my coding session", "summarize this branch", "wrap up what we built", or "explain what changed". Produces a one-page page that explains a large coding session or repository change to a smart beginner in under 5 minutes.

agentlyhq Skill

Build and query a knowledge bank from Google Docs meeting notes. Use when the user wants to ingest meeting notes from Google Drive, or when answering questions about previously ingested meeting notes. Trigger on phrases like "ingest my meeting notes", "load meeting notes from folder", "what did we discuss about X" (after ingestion), "find information about Y in meeting notes", "build knowledge base from meetings". Always use this skill when working with a corpus of meeting notes that needs to be searchable.

agentlyhq Skill

Use this skill whenever the user wants to summarize, digest, recap, or get a briefing from WhatsApp group chats using the `wacli` CLI. Trigger on any mention of WhatsApp summaries, group chat digests, catching up on WhatsApp, or briefing from chats. Also trigger when user wants to export or save WhatsApp chat history. Always use `wacli` — no exceptions, never use other methods.

emlembow Bundle

Coordinate complex tasks through verified completion using subagents, an adaptive dependency plan, durable task records, and steady progress readouts. Use when explicitly invoked as $divisible-work or when a complex user task warrants sustained planning, delegation, monitoring, and integration, including research, implementation, and existing task lists. Decide what can run in parallel and revise the path as results arrive. Do not trigger for simple requests, explanations of Divisible Load Theory, or worker assignments already being executed under this coordinator. Requires writable durable storage and usable subagent capabilities.

howillmakeit Bundle

BibiGPT 风格视频总结：输入 Bilibili / YouTube 视频链接，快速抓取字幕/转写文本，并生成结构化总结（TL;DR、核心要点、章节时间线、金句，支持中英文）。Use when the user shares a video link (bilibili.com, b23.tv, youtube.com, youtu.be) and asks to summarize it, extract key points, get subtitles/transcript, 总结视频, 提炼要点, 视频笔记.

rlin1027 Skill

Transform a vague interest into an answerable, significant research question for philosophy or humanities scholarship. Use when the user wants help choosing a topic, narrowing a research question, selecting methodology, or planning a paper structure.

rlin1027 Skill

Map existing scholarship, identify gaps, and position the user's contribution in philosophy or humanities. Use when the user needs a literature review, wants to find relevant sources, needs to understand the state of a scholarly debate, or wants to identify where their argument fits in the field.

codingrajan Bundle

Write or rewrite academic and scholarly text so it reads as a careful researcher's work, not a chatbot's, while keeping a formal register. Use for research papers, theses and dissertations, journal articles, literature reviews, abstracts, conference papers, and grant proposals, whether you are editing existing text or the user asks Claude to draft or compose scholarly writing directly. The rules apply equally to your own output. Targets significance inflation, vague attributions ("studies show" with no citation), em dashes, rule-of-three, AI vocabulary like delve / landscape / underscore, promotional adjectives, and "Challenges and Future Prospects" filler sections, without flattening legitimate hedging, methods-section passive voice, citations, or discipline-specific vocabulary. Based on Wikipedia's "Signs of AI writing" guide.

conorbronsdon Skill

Summarizes uncommitted changes and flags anything risky. Use when the user asks what changed, wants a commit message, or asks to review their diff.

couzip Skill

Summarize entire session and save to index as compact Q&A pairs

cycleuser Skill

Simulate peer review with severity-graded feedback and revision plan.

cycleuser Skill

Run a thorough, source-heavy investigation on any topic. Produces a cited research brief with provenance tracking.