Research & Search

shep-ai Skill

Fast-track feature creation that collapses new-feature, research, and planning into a single autonomous pass. Produces all spec YAMLs (spec, research, plan, tasks, feature) in one go with minimal user interaction. Triggers include "quick feature", "fast feature", "rapid spec", or explicit /shep-kit:new-feature-fast invocation. Part of the Shep autonomous SDLC platform — https://shep.bot

azhi-ss Skill

Deep travel research workflow for museums and ancient architecture. Input a city name, auto-generates structured knowledge document (org-mode) + portable reference cards (PNG). Covers historical background, museum highlights, archaeological significance, and architectural heritage. Use when user says '旅行研究', '博物馆功课', '古建功课', 'travel research', '出发前功课', or provides a city name with intent to do deep cultural travel preparation.

adhi-jp Bundle

Use when coordinating subagents for coding, research, repair, or review work where delegated workers may drift, stall, crash, duplicate, or edit a shared workspace and the coordinator must preserve scope, verification, and user-consent boundaries.

alex-macra Skill

Research a task before building: codebase prior art first, then docs and web, separating facts from assumptions, ending in a short findings brief that feeds a plan or ticket. Use for research, investigate, look into, find out how, what's the best way, compare approaches, spikes, or feasibility checks.

alex-macra Skill

Repository-grounded research for DGX Spark and Qwen3-Coder-Next implementation work: verify files, symbols, versions, dependencies, commands, and risks before task planning. Use for DGX Spark task research, Qwen task research, or preparing repository evidence for implementation packets. Task decomposition belongs to spark-task-planning.

amcamargoc Skill

Read and search before writing any code. Prevents hallucinations and costly corrections. Use when starting any implementation task.

opelpleple Skill

Distills a long conversation or working document down to its load-bearing essence — decisions, constraints, open questions, and current state — while discarding resolved chatter and noise, so a long-running task stays coherent without exhausting the context window. Use this skill when the user says "compact this", "summarize where we are", "condense the thread", or "let's reset and continue"; when a conversation has grown long and unwieldy; when context is filling up before a big next step; or whenever earlier turns are crowding out the signal the task actually needs.

pablostanley Bundle

Turn your AI into a full design team — 17 specialists that research, strategize, write, design, build, and review.

sunchenzheng Bundle

水利基础设施建设投融资模式研究技能。用于撰写水利基础设施投融资相关研究报告、银行调查报告、实施方案等文档。当用户提供水利项目背景时，自动调用本技能完成文档撰写任务。触发场景：（1）撰写'水利基础设施建设投融资模式研究'类研究报告；（2）撰写水利工程银行调查报告（如鄂北水资源工程二期）；（3）分析水利项目投融资方案；（4）水利行业政策研究。

techhorizonlabs Bundle

Brand mention and authority scanner for AI visibility. Analyzes brand presence across platforms that AI models rely on for entity recognition and citation decisions. Produces a Brand Authority Score (0-100) with platform-specific recommendations.

tjxj Bundle

Use when user wants to read emails, check inbox, fetch emails via IMAP, download email attachments, extract inline images, or summarize email content. Also supports real-time polling for new emails with system notifications. Triggers include read emails, check inbox, fetch emails, email summary, email attachments, mail listener, IMAP, QQ邮箱, Foxmail, 读邮件, 查看邮件, 收件箱, 邮件摘要, 邮件总结, 查收邮件, and 监听邮件.

restarter Bundle

Dynamic Workflow asset for /lets:research --workflow. Not auto-triggered - a workflow script invoked via scriptPath by /lets:research. Holds the off-context per-sub-question web research -> per-claim skeptic cross-check -> synthesize chain.

riteshkew Bundle

Given a company or person, run structured prospect research and synthesize a brief covering what they do, recent signals, likely pain points, and a tailored outbound hook.

rowankid Skill

新技术研究与 POC 分析技能。对新技术、新框架、新工具进行系统性调研，输出技术成熟度分析和引入建议报告。适用于 CTO 和架构师探索新技术方向、评估 POC 可行性。

sciman-top Bundle

Use when current primary-source evidence can materially change a decision. Default to read-only research; delegate only independent bounded work, and write a repository research note only when the user explicitly requests persistence.

sheng1111 Skill

Quick single-step app operations like launch, tap, type, swipe. Use for simple actions. For research, browsing, or multi-step tasks, use app-explore skill instead.

slogsdon Skill

Mine one external source — GitHub, Google Drive/Gmail, ChatGPT or Perplexity history, or the local filesystem — into attributed vault notes on a fixed schema. Use when Shane says "mine my GitHub", "pull context out of my ChatGPT history", "what's in ~/Code that isn't in the vault", "extract X into the knowledge graph", or when bootstrapping vault context for a new project. Do NOT use for a single document or article (use /ingest), for reading the vault itself (use /vault-retrieve), or for web research on a topic (use /research-sweep).

arthurzakirov Bundle

Give concise spoken feedback before invisible work during realtime voice. Use when the user is away from the screen and the assistant will research, edit files, inspect tools, change settings, or coordinate subagents/tasks by voice.

bryceewatson Skill

Take a build task from first read to a shipped, reviewed PR — the full research → plan → review-the-plan → implement → test → PR → review-the-PR chain, looping each checkpoint until the definition-of-done holds. Fires on any end-to-end build intent: an issue to take all the way, or a freeform goal stated with the whole chain. Unlike typing the chain by hand, it adversarially reviews the PLAN before code is written, gates plan-approval through the operator, exercises the REAL app, and never silently de-scopes.

naoray Bundle

Create or update release/changelog artifacts using Keep a Changelog. Use when the user asks to create a changelog PR, update a changelog, refresh a release PR body, summarize changes since a tag, or prepare a PR description from a branch diff. Inputs - source/target branches (or current branch → main default), repo merge style (squash or regular), and existing CHANGELOG.md / release PR if updating. Do not use when the PR is non-release (write a normal PR body), the user wants raw commit summaries (use git log), the work is cutting a new release branch (separate workflow), or the request is a one-off email/note. Produces a Keep a Changelog-formatted PR body OR updated CHANGELOG.md [Unreleased] section, with sections only for categories that have entries. Escalate if merge style cannot be detected, existing manual release notes are present and may be stale, or source/target branches are ambiguous.

naoray Bundle

Use when the user asks to enable research mode, turn research mode on/off, require citations, fact-check claims, review technical specifications, or work where source grounding and anti-hallucination constraints matter. Inputs - research question, documents or sources to inspect, citation expectations, and whether mode should persist. Do not use when the task is creative brainstorming, drafting fiction, or casual ideation without factual claims; use normal generation instead. Produces cited answers grounded in verified sources and direct quotes when analyzing documents. Escalate if sources conflict, reliable evidence is unavailable, citations cannot be verified, or the user asks to present uncertain claims as fact.

juanca202 Bundle

Tomar un requerimiento en bruto (idea, ticket, correo, transcripción, diseño, wireframes) y estructurarlo como una Especificación de Requisitos de Software (SRS-XXX) siguiendo ISO/IEC/IEEE 29148: alcance, FR-XXX y NFR-XXX priorizados y verificables, interfaces externas, datos, cumplimiento normativo, riesgos, stack (investigar con /work-research o ya decidido), repositorios y proyecto base, equipo. Lee y entiende imágenes y diagramas adjuntos, como /work-define. Guarda el requerimiento original en references/; si tiene UI, genera wireframes SVG enlazados para revisión y usa las observaciones para cerrar el SRS. Cierra lagunas con preguntas estructuradas como /work-define o /work-plan. Activar con «refina este requerimiento», «crea un SRS», «especificación de requisitos», «/requirement-refine», o al describir una necesidad cruda antes de historias de usuario. No crea US ni AC-XXX (handoff a /work-define en Ready) ni documentación técnica de modelos/APIs (eso es /design-define).

khanhvo2172-dotcom Skill

Searches Gmail for email threads related to a link exchange partner (by domain, email address, or subject keyword) and produces an instant briefing: who the partner is, what was agreed, current link placement status, last contact date, and the recommended next action. Use this skill whenever the user wants to look up a link exchange partner, recall email history with a partner, check the status of a link swap, or needs context before replying to a partner email. Also trigger when the user says things like 'what did we agree with X', 'catch me up on X', 'what is the status with X', or 'I got a reply from X'.

khanhvo2172-dotcom Bundle

Generate concise, reporter-ready email replies for PR opportunities, especially HARO, MentionMatch, Qwoted, or similar requests. Use when Codex needs to draft, refine, summarize, or create a response email from reporter questions, source notes, brand references, TrueProfit articles, customer examples, or expert quotes.

khanhvo2172-dotcom Skill

Crawls unread Gmail from a given start date, keeps only genuine backlink/link-exchange partner emails, and returns an urgency-ranked triage: who is waiting on you (ball in your court), who you're waiting on, and what to close or ignore. Use whenever the user says things like 'summarize unread exchange link mails', 'crawl unread backlink emails from <date>', 'which partners are urgent to reply', 'recrawl and categorize', or wants a fresh inbox triage of link-exchange outreach replies. Handles both fresh partner replies and follow-ups on historical threads, dedupes multi-rep companies, and filters out trackers, auto-replies, and sales pitches.

aroyburman-codes Skill

Synthesize user interviews, survey results, feedback, and support tickets into structured insights. Identifies themes, pain points, and opportunities. Generates research reports ready for stakeholders.

bastienlimbour Bundle

Turns conversation, briefs, research, issues, docs, and codebase context into a canonical implementation spec. Use when the user is ready to formalize what should be built before task splitting or implementation; not for product briefs, validation reports, task creation, or code changes.

cdeust Skill

Turn a pile of sources into a defensible claim. Use for "what does the literature actually say?", conflicting studies or benchmarks, "is this result trustworthy?", arguments that need claim-evidence-warrant structure, qualitative data needing coding, or a theory with no catalog of its own contradicting evidence.

vellum-ai Bundle

Generates GEO/AEO-optimized articles designed to get AI engines (ChatGPT, Perplexity, Claude, Gemini) to cite your brand. Handles research, writing, and file output. Suggests listicle or head-to-head as starting formats if the user is unsure.

wen-chen Bundle

Research intelligence suite for academic writing, literature review, and scientific analysis. Use when users need to write papers, draft grants, polish English/Chinese academic text, review manuscripts, find research gaps, check citations, download literature, design experiments, run bioinformatics analysis, or create scientific visualizations. Triggers on: write paper, grant proposal, rebuttal, cover letter, literature review, research gap, citation check, English polish, Chinese polish, translate, peer review, download paper, bioinformatics, data visualization, 写论文, 基金申请, 文献综述, 英文润色, 中文润色, 翻译, 审稿, 下载文献, 生信分析, 实验设计.

wen-chen Bundle

Draft competitive grant proposals and research funding applications. Use when writing or drafting NSFC grant sections, research proposals, project proposals, or reviewing existing grant drafts. Triggers on: grant proposal, grant application, grant writing, NSFC, National Natural Science Foundation, research proposal, project proposal, 基金申请, 国家自然科学基金, 基金标书, 科研项目申请, 立项依据, 研究方案. Does NOT trigger on manuscript writing (use paper-writer) or journal submission cover letters (use cover-letter-writer).

wen-chen Bundle

Draft academic manuscript sections (IMRaD format). Use when writing or drafting introduction, methods, results, discussion, or abstract sections of a research paper. Adapts to target journal style and research domain. Triggers on: write paper, draft manuscript, write introduction, write methods, write results, write discussion, write abstract, IMRaD, 写论文, 写introduction, 写方法, 写结果, 写讨论, 稿件起草, 论文写作.

wen-chen Bundle

Draft professional peer review response letters and revision rebuttals. Use when writing a response to reviewers, rebuttal letter, point-by-point response, revision letter, or appeal of a rejection decision. Triggers on: rebuttal, response to reviewers, point-by-point response, reviewer comments, revision letter, appeal rejection, 回复审稿意见, 逐条回复, 修改说明, 审稿回复. Does NOT trigger on paper-reviewer (reviewing a paper for others) or citation-checker.

wen-chen Bundle

Synthesize and review academic literature. Use when summarizing multiple papers, extracting themes, creating literature review tables, or preparing systematic/narrative reviews. Triggers on: review literature, summarize papers, literature synthesis, systematic review, narrative review, 文献综述, 文献整理, 综述, 系统综述, 整理文献, 文献分析, 文献总结.

wen-chen Bundle

Identify research gaps and generate research questions from literature. Use when finding unexplored areas, understudied populations, methodological limitations, or conflicting findings in a field. Triggers on: research gap, find gaps, what's missing, unexplored, understudied, research question, hypothesis generation, 研究空白, 未探索, 找差距, 研究问题, 科学假说, 选题建议.

yelban Skill

Deep travel research workflow for museums and ancient architecture. Input a city name, auto-generates structured knowledge document (org-mode) + portable reference cards (PNG). Covers historical background, museum highlights, archaeological significance, and architectural heritage. Use when user says '旅行研究', '博物館功課', '古建功課', 'travel research', '出發前功課', or provides a city name with intent to do deep cultural travel preparation.