Research & Search

jwiegley Skill

The standard tooling and working discipline for planning and executing a coding task -- GitHub CLI, codebase search, the language -pro agents, web research, sequential thinking, context7, and lint/type-check gating. The /medium and /heavy effort-tier commands build on it; load it when told to apply the standard toolkit.

jwiegley Bundle

Offload safe, independent subtasks to concurrent subagents while continuing your own work as the coordinator, then integrate what they return. Use when mid-task and some work could run in parallel without conflicting -- research, generating a standalone new file, tests for a stable interface, docs, or isolated analysis -- to accelerate without races. The coordinator alone runs git and mutates shared state; subagents read freely but write only to isolated namespaces and hand back artifacts. Triggers include "parallelize this", "spin up subagents to help", "do these in parallel", "fan this out".

lingwei-zheng Bundle

Use when the user wants to resume a research or paper project across devices, initialize a clean research-project workspace, reconstruct recent analysis or writing state from project files, or leave a concise cross-device handoff without relying on chat history.

lingwei-zheng Bundle

Use only when the user explicitly asks to be grilled, interrogated, pressure-tested, or challenged about a plan, design, decision, or idea. Best for software, product, workflow, operational, or general project decisions with unresolved branches. Do not auto-trigger for routine planning, clarification, academic research-question development, proposal or manuscript evaluation, or literature review; use good-question or academic-advisor for those academic tasks unless the user explicitly invokes grill-me.

lingwei-zheng Bundle

Use when the user asks to find, sharpen, evaluate, rewrite, or explain the story in scientific or scholarly materials across disciplines, including manuscripts, grants, paper outlines, abstracts, figures, results, discussions, cover letters, research pitches, high-impact writing, journal fit, significance, novelty, mechanism, paper logic, or why a result matters.

lingwei-zheng Bundle

Search and read Xiaohongshu content through the user's logged-in Chrome session. Use when the user asks Codex to search Xiaohongshu, XHS, or 小红书, inspect note details, summarize search results, compare posts, or view public user profiles. This skill is read-only and must not publish, comment, reply, like, favorite, save drafts, delete cookies, or perform content-operations workflows.

lingwei-zheng Bundle

Use when a researcher is choosing, framing, refining, or stress-testing a research question, hypothesis, thesis topic, project idea, grant direction, paper angle, or stalled research direction.

gurudevvv Bundle

Штурм идеи или решения по рельсам: рамка → 9 вариантов с обязательной еретической полкой → 3 финалиста → независимая проверка вслепую (свежий подагент + Codex) → решение с признаком смерти и датой. Use when the user wants to think through an idea, a choice, or a next move and needs more than the first consensus answer: «давай поштурмим», «поштурмить», «устроим штурм», «штурманём», «побрейнштормим», «накидай идей», «давай подумаем», «помоги решить», «какой вариант выбрать», «что дальше делать», «раскачай», «растормоши», «выйди за рамки», «идеи по карьере», «не знаю, куда двигаться», «дай второе мнение», «поспорь со мной», brainstorm this, help me decide, what are my options, push back on this, give me a second opinion. Универсально: карьера, продукт, бизнес, личные решения. Do NOT use for: проектирование кода и фич (это superpowers:brainstorming), оценку уже готовой продуктовой гипотезы (product-check), сбор фактов из интернета (deep-research), написание спеки нового проекта (spec-first), ревью готового ТЗ (mu

gurudevvv Bundle

Transforms raw meeting transcripts into high-fidelity, structured meeting minutes (notes / summaries). Use when (1) a meeting transcript is provided and meeting minutes, notes, or a summary are requested; (2) multiple versions of minutes must be merged without losing content; (3) existing minutes need review against the original transcript for missing items; (4) the transcript has anonymous speakers like "Speaker 1/2/3" or "发言人1" that need identifying (optionally mapped via a context.md team directory). Triggers on 会议纪要 / 会议记录 / 整理纪要 / 妙记转纪要, "write meeting minutes", "summarize this meeting", "merge these minutes", "what's missing from these notes". For fixing ASR/STT recognition errors in the raw transcript first, use transcript-fixer; this skill structures clean transcripts into minutes.

vikast908 Bundle

Help the user turn voice-of-customer research into a clear message hierarchy and converting copy. Ground every recommendation in named principles from Finding the Right Message by Jennifer Havice (cite concept + section only if present in references/book-passages.md). Use when the user runs /right-message or /finding-right-message, or discusses: copy, messaging, VOC, landing page, value proposition, Havice.

shinpr Skill

Orchestrate hypothesis validation through type-appropriate methods — prototypes, code analysis, market research, and expert review

ferroxlabs Skill

Generate optimized project context from codebase scan. Trigger: new project, no CLAUDE.md, /ijfw-summarize

pyfagorass Skill

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.

aifinlab Skill

当用户需要做行业研究、赛道分析、市场扫描、竞争格局分析、公司对标、商业模式拆解、政策影响分析、投融资趋势梳理、行业报告提纲撰写或研究结论总结时使用。适用于输出行业研究框架、研究计划、信息清单、访谈提纲、公司对比表、SWOT、PEST、波特五力、产业链地图、市场规模测算思路和正式研究报告初稿。

entropy-r Bundle

Query recent Codex update logs and summarize what changed using official OpenAI Codex changelog, GitHub releases, GitHub compare patches, and an optional X/Twitter search entry. Use when the user asks to view recent Codex updates, Codex release notes, Codex changelog content, or the current machine's Codex version.

traderalice Skill

Subjective retrospective / time-machine analysis: rewind a name to a past point, reconstruct what it looked like THEN (no future knowledge), align the news catalysts to the price path, and pressure-test "if I'd entered there, would it have worked?". Use when the question is about a past moment or a hypothetical entry: "rewind XLE to early April", "what did NVDA look like before earnings", "if we'd bought energy after the Iran headline, easy money?", "replay the SMH spike — policy or earnings?", "was there an entry signal at the time", "would an 8% trailing stop have saved me", "event study on the Hormuz escalation". It strings together the as-of snapshot, the date-windowed news, and Workspace research code into one honest replay — and it is ruthless about data freshness, because a retro built on a stale or future-leaking price is worse than no retro.

traderalice Bundle

Delegate reproducible quantitative research from a general Chat Workspace to the durable AutoQuant desk and consume its evidence-bound handoff. Use when a request needs a quantitative Project, historical data intake, factor or portfolio research, backtesting, governed experiments, robustness evidence, or an AutoQuant follow-up. Do not use for ordinary market commentary, broker state, order execution, or a question Chat can answer directly.

amatray Skill

Use when the user wants to stress-test, critique, or pressure-check a plan document — catch blind spots, missing steps, and unstated assumptions. Triggers on "review my plan", "stress-test the plan", "critique this plan", "what am I missing", "expert review of the plan", or "/review-plan". Runs structured expert critique, best-practice research, and optional fresh-context subagent review.

librefang Bundle

Expert knowledge for AI deep research — methodology, source evaluation, search optimization, cross-referencing, synthesis, and citation formats

materialofair Skill

Adaptive development workflow that runs discover -> research -> plan -> implement -> verify with explicit quality gates.

mrilikecoding Skill

Creative writing coaching orchestrator. Manages a multi-phase workflow for projects that interweave prose narrative, art-as-code, and research-grounded theoretical discussion. Coaches structure, voice, and critical quality — the user does the writing.

mrilikecoding Skill

Systematic literature review and synthesis for a research topic or draft paper. Use when asked to find related work, build a literature map, survey a field, or synthesize research on a topic. Produces a structured narrative synthesis, not just a reference list.

fanchengchen1-collab Bundle

Super Director System (English edition) — a film-craft knowledge base and director workflow for AI video creation. Use when the user wants storyboards, AI video generation prompts (Sora/Kling/Veo/Seedance/Runway), cinematography design (lighting, composition, camera moves, blocking), short-drama or film development, aesthetic style bibles, fight choreography, or narrative pacing — and communicates in English. Outputs production-ready Six-Block prompts in English. For Chinese-speaking users, prefer the cinema-director skill.

jpvarbed Bundle

Turn a research paper's finding into a concrete change to our skills/agents — distill the claim, map it to where it applies, design the change, and prove it helps. Use when the user says "apply this paper", "what would <paper> change for us", "turn this finding into a skill change", or when triaging a paper in docs/papers.md from "interesting" to "shipped". NOT for summarizing a paper (just read it) or general literature review. Pairs with linting-and-scoring (score the result), adversarial-review (red-team the change plan), and goal-spec (if the change is big enough to dispatch).

muhammadali-k Bundle

Research, verify, compare, and rank U.S. residency programs for an applicant profile, including current-cycle eligibility, visa policy, signaling, interview metrics, international-medical-school representation, medical-school-country ties, fellowships, and reach/target/safety tiers. Use for application lists, signal allocation, or vetting programs; compose with current web search and the Browser skill for signed-in or JavaScript pages.

tandregbg Bundle

Process and summarize transcriptions from calls, meetings, or voice recordings. Use when user provides a transcription, mentions processing a transcript, or wants to summarize a recorded conversation.

agnik47 Bundle

Converts raw user interviews, research transcripts, support conversations, and customer feedback into structured insights, themes, pain points, and Jobs-to-be-Done outputs.

avisheku Bundle

Scan pack components + frontier watchlist; research upgrades; stage via /learn.

avisheku Bundle

Research with dual gates; fan-out depth one; synthesize for ShortPlan.

w5711112 Bundle

Use when creating, restructuring, formatting, linking, illustrating, or maintaining Chinese Obsidian research notes, especially when concepts need prerequisite hierarchy, formula explanation, cross-course connections, evidence layers, WikiLinks, or media cleanup.

w5711112 Bundle

Use when searching, auditing, merging, summarizing, or periodically reviewing UAV/drone perception-control literature under strict official-source, single-UAV, compute, and deployment gates.

hyqibot Skill

Look up the latest news for the user from specified news sites. Provides authoritative URLs for politics, finance, society, world, tech, sports, and entertainment. Use browser_use to open each URL and snapshot to get content, then summarize for the user.

yevhens-hue Skill

Programmatic GEO & AEO Content Engine Architecture using AirOps, n8n, Claude 3.5, and Headless CMS. Automates structured research, inverted pyramid drafting, Schema.org JSON-LD entity injection, and citation tracking across Perplexity & Google AI Overviews.

cnfjlhj Skill

Use only when the user explicitly asks for help drafting or revising an AI/ML research paper in LaTeX, including structure, BibTeX, formatting, or academic-writing checks.

soapwong Bundle

为 A 股、港股或美股公司生成一页纸深度研究，压缩商业机制、竞争核心、扩张边界、现金流、估值、催化与证伪条件。用户提供公司名称并要求分析、研究、one-pager 或判断是否值得关注时使用；不适用于非上市公司、纯技术面复盘或个性化买卖建议。

soapwong Skill

单一标的事件驱动交易的多空自证一致性分析法：定性、机械资金流、利率regime、轮动方向、有边界结构，防自相矛盾。