Research & Search

tsingyuai Bundle

渐进式研究当前产品，并把已经稳定、可追溯的产品认知增量写入根目录 SOUL.md。首次接入产品代码、原型或线上 URL，需要确认产品形态与已有能力，或某个增长 loop 在执行中发现新的产品事实、用户场景、问题与价值证据时使用。不得一次性臆造完整产品画像，也不得仅凭代码功能推断用户、问题或价值。

tsingyuai Bundle

Collect Weibo posts and creator evidence with MediaCrawler using search, exact post IDs, comments, optional media, and creator IDs. Use for discourse, trend, messaging, audience-language, or account research requiring preserved provenance and risk-aware detail enrichment.

tsingyuai Bundle

Collect Zhihu answers, articles, videos, comments, and creator evidence with MediaCrawler through search and exact URLs. Use for expert discourse, problem framing, objections, terminology, topic, or creator research where content type and question context must remain explicit.

tsingyuai Bundle

Collect Douyin competitive evidence with MediaCrawler using keyword search, exact video detail, comments, media, and creator profiles. Use for trend, hook, format, audience-language, or creator research that needs reproducible raw evidence and a documented selection method.

tsingyuai Bundle

Collect Bilibili video and creator evidence with MediaCrawler through search, exact BV detail, comments, dynamics, contacts, and optional media. Use for topic, format, title, creator, or audience research with explicit time-range and quality controls.

tsingyuai Bundle

Collect Kuaishou competitive evidence with MediaCrawler using keyword search, exact video detail, comments, media, and creator profiles. Use for trend, format, audience-language, or creator research requiring reproducible source records and explicit collection limits.

ttttstc Bundle

当用户的产品、工程、设计、写作或 AI 编程请求存在不确定性时，作为“Unknown 阶段诊断器 / 分诊器 / 提示词交接器”使用。它不替代 brainstorming、office-hours、grill-me、review、QA、research、prototype 或实现类 skill；只负责基于当前输入、对话上下文和可访问文件诊断当前主 Unknown、次级 Unknown、阻塞程度，推荐处理模式，生成下一阶段中文任务包，并支持“继续”在本对话承接上一轮推荐处理模式。注意：“继续”不是推进到下一个 Unknown；只有再次运行 /ni-unknown-first 才重新诊断并判断是否推进 Unknown 队列。

vinceservidad Bundle

Researches and validates Shopify product opportunities using customer, demand, competitor, supplier, economics, operations, and risk evidence. Use before listing or sourcing.

ben2pc Bundle

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+ tool calls. Supports automatic session recovery after /clear.

maoyadongsh Skill

Review selected GitHub files with source evidence.

oppo-mente-lab Skill

Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.

rimagination Skill

Systematic evidence-bounded literature review across a selected ScanSci library, including scope definition, thematic synthesis, evidence gaps, citation checks, and review-ready output. Use for literature reviews, state-of-the-art surveys, scoping reviews, or research-gap analysis.

rimagination Skill

Use when a ScanSci user wants to search, compare, or answer questions from a bound local knowledge library with traceable evidence.

rimagination Skill

End-to-end academic research orchestration from question formation and literature search through evidence review, statistics, figures, manuscript writing, peer-review response, data availability, and paper-to-PPT delivery. Use when a task spans multiple research stages.

rimagination Skill

Evidence-bounded scientific ideation for research questions, hypotheses, mechanisms, experiments, and falsifiers. Use for research brainstorming, study design, gap analysis, or turning observations into testable ideas.

janellecipriano Skill

Distill a detailed program update, document, or set of notes into a one-screen executive summary written for leadership — headline, status, key points, and decisions needed. Use when the user says "exec summary", "summarize for leadership", "TL;DR for the VP", "make this executive-ready", or needs to compress detail into a decision-focused brief.

jiahao-shao1 Bundle

Fetch BibTeX entries from arXiv / Semantic Scholar. Triggers: 'fetch bibtex', 'cite this paper', 'arXiv bibtex', '拉 bibtex', '获取引用', '引用这篇论文'. Not for citation format conversion (APA/MLA) or literature review.

freecodecamp-universe Bundle

**Dra. Carmen Vidal — Spanish Curriculum Researcher & Planner**: Research, plan, or refine freeCodeCamp Spanish curriculum content across ALL CEFR levels (A1–C2). Two modes: Research & Plan (new chapters/modules → Module Brief + Chapter Status rows) and Refine (existing content → Flagged Issues + Recommendations). Always checks prior levels for coherence. Invoke with /carmen. Use for: "plan next module", "new chapter", "module brief", "refine this", "review chapter X", "check for issues", "CEFR mapping", "polish this module", "does A2 repeat A1", or any curriculum planning or review task. Carmen only acts when explicitly asked.

gitt510 Bundle

Summarize a YouTube video from its transcript (subtitles) fetched with yt-dlp, without watching it; never downloads the video or audio. Use when a YouTube URL (youtube.com / youtu.be) is shared and the user wants the content, key points, or a transcript — including vague asks like "what's this about?" as long as the target is a YouTube video.

haaaiawd Bundle

Precise, instant code structure queries for active development — answer 'who depends on this interface before I refactor it', 'how many modules break if I change this', 'what is the real impact radius of this feature change', 'which module is the true high-coupling hotspot in this legacy codebase'. Essential before any interface change, continuous refactoring task, sprint work estimation, or when navigating unfamiliar or large legacy codebases. Requires Python 3.10+ and shell. Use nexus-mapper instead when building a full .nexus-map/ knowledge base.

haaaiawd Bundle

Generate a persistent .nexus-map/ knowledge base that lets any AI session instantly understand a codebase's architecture, systems, dependencies, and change hotspots. Use when starting work on an unfamiliar repository, onboarding with AI-assisted context, preparing for a major refactoring initiative, or enabling reliable cold-start AI sessions across a team. Produces INDEX.md, systems.md, concept_model.json, git_forensics.md and more. Requires shell execution and Python 3.10+. For ad-hoc file queries or instant impact analysis during active development, use nexus-query instead.

zeikar Skill

Use on-demand to extract evidence-anchored repo-local knowledge candidates from accumulated .hyperclaude/ artifacts (plans/done, plan-reviews, research) and curate them. Also when the user invokes /hyperclaude:hyper-memory. Orchestration-only — no Codex spawn.

zeikar Skill

Use when starting a non-trivial task and want prior-art, pitfalls, or recommendations before designing. Also when the user invokes /hyperclaude:hyper-research. Runs Codex and Claude in parallel by default, producing two artifacts in .hyperclaude/research/.

zeikar Skill

Use when starting from a vague or under-specified idea and want requirements clarified before planning — "interview me", "ask me what you need", "clarify requirements first", "I'm not sure exactly what I want", "make sure you understand before building". Also when the user invokes /hyperclaude:hyper-interview. Runs a short one-question-at-a-time interview and writes a spec to .hyperclaude/specs/ — the front-end input to /hyperclaude:hyper-research and /hyperclaude:hyper-plan. Distinct from /hyperclaude:hyper-plan, which decomposes an ALREADY-CLEAR task into tasks.

zeroclaw-labs Bundle

Deep web research with source citation. Summarizes findings privately. Finds, evaluates, and synthesizes information from the web, delivering accurate, well-sourced answers. Use when the user wants to research a topic, find information online, or compare technologies.

adityahegde712 Bundle

Perform evidence-grounded research or retrieve references for implementation. Invoke whenever the user asks to research, investigate, compare external evidence, look something up for implementation, gather references, perform a literature or technology review, or make claims that should be grounded in retrieved source material. Retrieved evidence must take precedence over pretrained knowledge.

invergent-ai Skill

Hard-gated ideation for an Arbor research run. Load at the START of every IDEATE round, before drafting any hypothesis. Enforces the PI mindset (mechanism over knob), the four-question first-principles probe, the kill-filter, and the four-line hypothesis format. Ported from Arbor's idea_drafting + first_principles_probe.

invergent-ai Skill

The Arbor research-coordinator protocol: the OBSERVE -> IDEATE -> SELECT -> DISPATCH -> DECIDE cycle over a durable Idea Tree. Preloaded automatically on /auto-research sessions. The coordinator never edits code or runs commands — executors do that in isolated worktrees; the coordinator steers the tree with idea_tree / dispatch_experiments / merge_experiment.

az9713 Bundle

Workflow for turning meeting transcripts or notes into decisions, action items, unresolved questions, risks, and follow-up artifacts. Use for prompts like "summarize this meeting", "extract action items", "what did we decide", or "draft the follow-up". Best when you have notes or a transcript, attendee context, and the reason the meeting happened. Optional Open Brain search and capture can pull surrounding context and store the final synthesis or decisions.

az9713 Bundle

Decision-grade workflow for synthesizing a source set into clear findings, contradictions, confidence markers, gaps, and next questions. Use for prompts like "synthesize these sources", "turn this research into a brief", "what are the key findings", or "where do these sources disagree". Best when you have a research question, a defined audience, and a set of source materials. Optional Open Brain search and capture can pull prior context and store the final synthesis.

vladsez Skill

Discover keyword opportunities, evaluate metrics and SERPs, and save/tag promising terms.

fadil369 Skill

Conducts multi-step web research with source synthesis and citations.

beskars-code Bundle

Stateless task analysis returned in chat. One-off research with promote-to-task handoffs, or nested under a parent (write-ticket, just-do-it, review remediation). Does not write tickets or automatic artifacts.

bsamiee Skill

Owns live-web retrieval through Tavily CLI (`tvly`), search, extract, map, crawl, research, on the cheapest verb that answers: relevance resolved server-side, not post-filtered locally, and bulk page content routed to disk, never the context window. Beats blind single-URL fetching, which ranks and scopes nothing. Any current-web question routes here.

chainsafe Skill

How to open and shepherd a pull request at ChainSafe — language-agnostic PR authoring guidance. Use this skill whenever the user is opening a PR, drafting a PR description, deciding how to scope a PR, handling reviewer comments, structuring commits within a PR, declaring AI-generated content, or shepherding a PR through review. EVEN IF the user does not explicitly say "PR" — triggers on "open a pull request", "draft a PR description", "what should I put in the PR", "PR is too big", "split this PR", "how do I respond to this reviewer comment", "self-resolve threads", "AI declaration in PR", "scope drift", "commit message", "stack of PRs". For the actual code-change workflow that produces the PR, use chainsafe-research-plan-implement. For PR review (incoming), use chainsafe-code-review.

chainsafe Skill

Research-first coding workflow that gates ALL non-trivial code changes behind a human-approved written plan. Use this skill whenever the user asks for any substantive code change — implementing a feature, refactoring, fixing a multi-file bug, adding an endpoint, integrating a service, migrating systems, or changing how an existing system works — EVEN IF they do not explicitly ask for "research" or a "plan." It enforces three artifacts (research.md, plan.md, annotated plan) that gate implementation behind operator approval. Triggers on "implement", "refactor", "fix this bug", "add a feature", "integrate", "migrate from X to Y", "rewrite", "wire up", "extend", "I want to add". Also covers breaking planned work into tracked units — "break this into issues", "decompose this", "create the epic", "what milestones do we need", "is this issue too big". Do NOT use for one-line typo fixes, pure formatting, lint-only changes, or other trivial single-file edits.