Research & Search

dokhacgiakhoa Skill

🧠 Strategic Research & Wisdom Engine

diegojcn Bundle

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth....

pramoddutta Skill

Log and summarize the execution of a test cycle. Use when a tester says "log this run", "track execution for the sprint", or reports results case by case and wants them recorded. Captures pass / fail / blocked / not-run per case with evidence links and environment, then rolls up progress — completion %, pass rate, blockers. Records only what actually happened; anything unverified is marked "not run", never assumed green.

arcadeai Skill

Extract tacit knowledge through non-obvious microquestions — things only the user knows that can't be found in code, docs, or research. Use when you're about to guess at intent, context, or constraints during SAFEWORD's understanding flow. Also use when user says 'ask me', 'what do you need to know', or when another skill (bdd, brainstorm, debug) needs user context before proceeding. Do NOT use for questions answerable by reading the codebase or searching the web.

arcadeai Skill

Tests whether a proposed product bet has credible demand. Use when Why now depends on an unresolved, decision-critical demand claim or when the user explicitly asks for demand research. Do NOT use for child features, mandated work, parity work, or when a cheaper experiment can answer the question before research.

axross Bundle

Handling what you do not know, and handing back what you found — the conduct baseline underneath whatever else a session is doing, applying to a question answered in one turn as fully as to a feature built over many. Triggers on any uncertainty about facts, scope, or intent; on "are you sure", "don't guess", "what's the latest"; before asserting a version, API, price, or date; before putting a decision to the human; and whenever a result is reported. Not a change-loop skill — it governs conduct within work already underway. Covers the three-source triage (look it up, research it, ask), the clarifying interview, accuracy discipline, and reporting that leads with the answer in the human's own language.

zh30 Bundle

Use when an independent developer needs public market research to decide whether an early product idea is worth deeper validation. Scans communities and competitors for demand, objections, alternatives, solo-founder fit, entry wedges, and a go, narrow, or stop recommendation.

zh30 Bundle

Use when an independent developer needs public market research to decide whether an early product idea is worth deeper validation. Scans communities and competitors for demand, objections, alternatives, solo-founder fit, entry wedges, and a go, narrow, or stop recommendation.

zh30 Bundle

Use when an independent developer needs public market research to decide whether an early product idea is worth deeper validation. Scans communities and competitors for demand, objections, alternatives, solo-founder fit, entry wedges, and a go, narrow, or stop recommendation.

zh30 Bundle

Use when an independent developer needs public market research to decide whether an early product idea is worth deeper validation. Scans communities and competitors for demand, objections, alternatives, solo-founder fit, entry wedges, and a go, narrow, or stop recommendation.

kbarbel640-del Bundle

High-velocity research orchestration engine. Manages persistent state, synthesis, and autonomous verification for agents.

compozy Bundle

Create or update a requested CompozyOS spec and its applicable companion contracts, reusing current decisions and research. Not a prerequisite for ordinary coding tasks.

dnyoussef Bundle

Opentelemetry Observability

elzawarudo Bundle

Triage pull request review feedback, plan response work, apply approved fixes when requested, verify the result, draft clear reviewer replies, and optionally publish approved review-thread replies or resolutions. Use when a user asks to address PR comments, summarize review feedback, resolve GitHub review threads, prepare reply text, decide which comments are blocking, apply fixes from review comments, or turn review feedback into commits and responses. Runtime aliases may expose this as krt:review-herald.

davepoon 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.

leeovery Bundle

Act as **precise intake coordinator**. Follow each step literally without interpretation. Do not engage with the subject matter — your role is preparation, not processing.

leeovery Bundle

Research Process

fdu-ins Bundle

God-level internet research and data synthesis for any topic. Use when the user wants to research, compare, analyze, or find the best options for anything: business ideas, products (phones, laptops, gadgets), services (credit cards, banks, insurance), travel (hotels, flights, destinations), market trends, industry data, competitor analysis, pricing comparisons, consumer reviews, emerging opportunities, or any general-purpose research task. Triggers on: 'research', 'find the best', 'compare', 'what's the best', 'top 10', 'under X price', 'market data', 'industry trends', 'alternatives to', 'reviews of', or any request requiring internet research and data gathering.

shenjj2025-oss Skill

orchestra-research-skills

acaprino Skill

Maintenance protocol for hand-authored plugins that have no upstream to diff against: the four freshness risk classes and their cadences, where hard-coded versions hide, the re-research and surgical-edit update protocol, the refresh commit tag, and triage for picking what to refresh next. TRIGGER WHEN: the user asks to refresh, re-research, or fact-check a plugin that is not in the sync table of the `upstream-sync` skill; asks which plugins are stale or overdue; or asks about version drift in plugin knowledge bases. DO NOT TRIGGER WHEN: the plugin IS upstream-synced (use `upstream-sync`), the task is a first-time vendor of external content (use `external-repo-intake`), or the task is mirroring our content outward (use `downstream-exports`).

acaprino Bundle

Knowledge base loaded by the stripe-integrator and revenue-optimizer agents, also consumable directly. TRIGGER WHEN: working with the Stripe API (Payment Intents, Customers, Subscriptions, Checkout Sessions, Connect, webhooks, tax, usage-based billing), Firebase integration, pricing strategy, or revenue modeling.

acaprino Bundle

Knowledge base for OTel in Python: async gotchas, non-HTTP transports, production patterns. TRIGGER WHEN: working with OpenTelemetry, distributed tracing, span instrumentation, context propagation, OTLP exporters, sampling strategies, or observability pipelines.

rwilson504 Skill

Parse and summarize a Dataverse Classic Workflow XAML file (WF4, the `workflow` table) into a human-readable narrative. Use when user says "what does this workflow do", "summarize this workflow", "explain this XAML", "walk me through this workflow", "what triggers this", "what are the steps", "extract the trigger info", "is this real-time or background", "what scope does this run at", or pastes/points at a `.xaml` file from `pac solution clone` or `unpack`. Produces trigger + scope + mode + run-as details and a step-by-step narrative, resolving `mxswa:ActivityReference` wrappers and `[bracket]` VB.NET expressions into plain language. Do NOT use for editing XAML (use dataverse-classic-write), diffing two versions (use dataverse-classic-compare), or gap analysis against requirements (use dataverse-classic-analyze).

acaprino Bundle

Knowledge base for web research: query formulation, source authority ranking, the two search backends (native WebSearch, optional serper.dev through websearch.py), reading pages with WebFetch and the webfetch.py bot-block fallback, and the anti-loop rules. Used by quick-searcher, deep-researcher and /research:team-research. TRIGGER WHEN: performing web research with WebSearch, WebFetch, or the research plugin's scripts. DO NOT TRIGGER WHEN: searching a local codebase (use Grep or Glob directly).

acaprino Bundle

Knowledge base for shipping production games from one Java or Kotlin codebase. TRIGGER WHEN: building, optimizing, debugging, or scaffolding libGDX games; migrating libGDX versions; choosing libGDX architecture patterns.

acaprino Bundle

Knowledge base for production crawlers, from target assessment through observability. TRIGGER WHEN: building, debugging or optimizing a Python web scraper, or working on anti-bot bypass for Cloudflare, DataDome or PerimeterX, CAPTCHA solving, proxy architecture or rate limiting.

acaprino Skill

Knowledge base of the 24 catalogued patterns, each with a natural-sounding rewrite. TRIGGER WHEN: editing or reviewing text to remove AI traces, or when asked to humanize text.

waterplanai Skill

Core specification workflow engine. Supports CREATE, GATHER/RESEARCH, CONSOLIDATE, SUCCESS_CRITERIA, CONFIRM_SC, PLAN, IMPLEMENT, REVIEW, FIX, TEST, DOCUMENT, SENTINEL, SELF_VALIDATION, and compatibility stages.

hk-hub Bundle

Knowledge Base (知识库)

darthlinuxer Skill

Use when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable.

liangdabiao Bundle

对任何亚马逊卖家店铺进行全面的深度研究。当用户提供店铺URL时使用此skill，包括研究亚马逊店铺、分析卖家 storefront、 调查亚马逊品牌、研究竞品店铺，或提供亚马逊店铺URL（amazon.com/stores/...）。也可在以下请求时触发： "调研这个亚马逊店铺"、"分析这个Amazon卖家"、"深度调研Amazon店铺"、"分析亚马逊品牌店铺"、 "Amazon店铺调研"、"调研这个卖家"、"分析竞争对手店铺"，或任何研究/分析/调查亚马逊卖家店铺或品牌 storefront 的请求。

liangdabiao Bundle

亚马逊卖家关键词研究和市场机会分析。获取自动完成建议（长尾关键词），分析竞争格局，并评估12个亚马逊市场（美国/英国/德国/法国/意大利/西班牙/日本/加拿大/澳大利亚/印度/墨西哥/巴西）的任何关键词的市场机会。无需API密钥。当用户提到亚马逊产品研究、寻找在亚马逊上销售的产品、亚马逊关键词创意、利基分析、亚马逊竞争分析、亚马逊市场机会、比较亚马逊关键词、评估产品是否值得销售、亚马逊自动完成数据、亚马逊产品的季节性需求，或任何与研究在亚马逊上销售什么相关的内容时，确保使用此技能 — 即使他们没有明确说'关键词研究'。当用户问模糊问题时也触发，如'这是一个好的销售产品吗？'、'X在亚马逊上的竞争如何？'、'我应该卖X还是Y？'，或'人们在亚马逊上搜索什么？'。

liangdabiao Bundle

全面的亚马逊选品与机会分析。评估市场需求、竞争强度、利润潜力和进入壁垒，适用于任何产品类目或细分市场。基于BSR数据、评论分析和定价模式。

liangdabiao Bundle

对任何亚马逊畅销榜类目进行全面的深度研究。当用户提供类目URL时使用此skill，包括研究亚马逊产品类目、分析亚马逊畅销榜、 调查亚马逊细分市场、为亚马逊销售进行市场调研，或提供亚马逊畅销榜/gp/bestsellers URL。也可在以下请求时触发： "调研这个亚马逊品类"、"分析这个Amazon类目"、"深度调研Amazon Best Sellers"、"分析亚马逊畅销榜"、 "Amazon品类机会分析"，或任何研究/分析/调查亚马逊类目或畅销榜的请求。

okhp3 Bundle

Validate a project change, draft, research packet, skill, promotion package, or handoff before it is treated as complete. Use after meaningful work and before handoff, graduation, publication review, or reliance on an artifact. Run the identified project validator when one exists, then add judgment checks the script cannot prove.

okhp3 Bundle

OverKill Hill P³ ChatGPT project migration. Use when migrating, preserving, extracting, inventorying, normalizing, reconciling, or incorporating ChatGPT project threads, conversation exports, or complete chat histories into a repository. Also activate when a user needs a lossless thread archive, project-to-export crosswalk, provenance ledger, or public-safe distillation workflow. This is the authoritative capture and reconciliation process for ChatGPT project material in this repo -- use it even when the user asks only to "save", "review", or "summarize" a large set of threads.