Research & Search

itsual Skill

Perform efficient desk research using public and proprietary secondary sources to answer questions quickly without primary fieldwork. Use when you need fast situational awareness, market context, or fact-finding before deeper primary research.

itsual Skill

Run diary studies that capture experiences over time — habits, journeys, and intermittent behaviors interviews cannot reach. Use when researching longitudinal experience, episodic events, or behaviors that are hard to observe live.

itsual Skill

Research Jobs-to-be-Done — the progress customers seek in specific circumstances — to inform product and messaging strategy. Use when uncovering why customers hire products, mapping job stories, or reframing markets around outcomes.

itsual Skill

Design surveys that produce reliable, interpretable data — with clear questions, sensible scales, and bias-aware structure. Use when building questionnaires for customers, employees, research panels, or market studies.

joshuashepherd Skill

Summarizes, condenses, or extracts text, transcripts, and key points from URLs, articles, web pages, PDFs, podcasts, YouTube videos, and local files. Handles transcript extraction, transcript-to-document conversion, and acts as a fallback transcription tool when the user asks to transcribe, digest, recap, or get the gist of a link, video, or document.

joshuashepherd Skill

Scrape podcast episodes, sermons, and audio sources — discovers via iTunes Search API, parses RSS feeds, downloads audio, transcribes via OpenAI Whisper, chunks for search, and upserts into the podcast_episodes table.

joshuashepherd Skill

Map relationships, co-authorships, endorsements, and organizational connections across movement leaders. Reads existing per-leader research in docs/movement_leader_research/ and writes a cross-leader graph. Output table schemas align with the `movement-leader-substrate` Network graph section so per-leader substrate files can be regenerated from this data.

joshuashepherd Skill

Scrape YouTube channel videos — fetches metadata, downloads transcripts via yt-dlp, chunks for search, and pulls comments. Upserts into the videos table.

joshuashepherd Skill

Extract a plain-text transcript from any YouTube video URL. Returns timestamped and full-text versions of the transcript saved to a local file.

concertonotes Bundle

Глобальный навык для Яндекс.Директ/Wordstat/Roistat/Метрики: сбор новой семантики, аудит и оптимизация действующих кампаний, live-валидация, media-plan, competitor research и client-overlay контракт для любого локального проекта.

testdouble Skill

Build work collaboratively in reviewable pieces, handing each piece back for review before starting the next, so the person stays in the lead and steers while the work happens instead of reviewing a finished result. Use when someone says to pair with them on something, asks to collaborate rather than direct, wants to review as it goes, or wants to guide the work piece by piece — on code, on a design decision, or on writing. For a test-first build it runs tdd, for restructuring it runs refactor, for an interface contract it runs design-an-api, and for plan work it runs iterative-plan-review or plan-implementation, each collaboratively; invoke any of those directly instead to run it straight through without pausing. Does not pace someone through code that already exists and builds nothing — use code-walkthrough. Does not explain, summarize, or research something instead of producing it — use code-overview or research.

testdouble Bundle

Evidence-based investigation of issues, bugs, API calls, integrations, and other aspects of software development that need a deep dive to find the root cause and solutions. Use when you need to debug, troubleshoot, diagnose, or figure out why something is broken. Does not review code for quality or style — use code-review for auditing changes or post-code-review-to-pr for posting review feedback to GitHub. Does not assess architectural health or structural risk — use architectural-analysis for architectural concerns. Does not research open-ended options, prior art, or how something works when nothing is broken — use research for that. Does not plan the structural change a root cause calls for — use plan-a-change. Does not map bounded contexts or domain boundaries — use ddd-analysis. Does not capture feedback on Han's own skills — use han-feedback for that.

testdouble Skill

Capture structured feedback on the Han skills and agents used in the current session and optionally post it as a GitHub issue to testdouble/han. Use at the end of any session where one or more han-* skills or agents ran, to rate a run, log what worked and what didn't, or submit observations for maintainers. Does not review code, investigate bugs, or research options; use code-review, investigate, or research for those. Does not provide feedback on skills or agents from non-Han plugins.

itsual Skill

Create useful personas grounded in research that help teams make better product and design decisions. Use when defining target users, aligning teams on who they are building for, or turning research into practical decision tools.

itsual Skill

Write effective knowledge base and help-center articles that resolve user questions quickly and reduce support load. Use when creating or improving self-service support content, internal wikis, or help articles.

kagenti Skill

Architectural design workflows - research, propose, review, iterate

rulebase-co Skill

Use to check whether what agents actually tell customers matches documented policy, across every conversation where a topic came up. Trigger for "did we give customers the wrong information about X", "are we answering this consistently", "find every instance where agents said X", "check our answers against the knowledge base", answer-consistency audits, or a complaint that hinges on what a customer was told.

tinh2 Skill

Polishes UI primitives one at a time using 2026 research-backed patterns — adds loading/icon states to buttons, replaces inline skeletons with primitives, adds secondary actions to errors, ensures 48px touch targets and visible focus indicators, applies a standard motion token ladder..

projectious-work Bundle

Review and prune the project context — archive completed work, summarize stale entries, and propose disabling unused skills.

projectious-work Bundle

Investigates a question systematically before answering — verifying claims through sources, distinguishing known facts from inferences, and calibrating expressed confidence to actual certainty. Use when asked to research a topic, verify a claim, evaluate a technology, or answer a question where accuracy matters more than speed.

rajanthar Skill

Use when the user asks to make something faster, try many variants, run recursive optimization, benchmark latency/throughput/cost, or choose the best implementation by repeated measured tests.

rajanthar Skill

Research prediction-market events, venues, underliers, liquidity, and news context for Itô basket workflows. Use for read-only market intelligence, API-gated Itô exploration, and source-grounded prediction-market briefings without investment advice or live trading.

rajanthar Skill

Research prediction markets as data sources or oracle signals for products, agents, dashboards, and corporate decision intelligence. Use for source-grounded analysis of market-implied probabilities, caveats, and integration patterns without investment advice.

alexandrbasis Bundle

Run Google Antigravity CLI (agy) for web-grounded research, cross-AI review, or validation when those capabilities are explicitly needed or another skill delegates to agy. One-shot only; do not select it for an ordinary review without an explicit provider choice.

infometa Bundle

知产 · 依据检索与专业库调查

infometa Skill

[DEPRECATED] Merged into earnings-analysis skill. Use earnings-analysis for both pre-earnings preview and post-earnings analysis.

infometa Bundle

South Africa Strategic Knowledge Base

specterops Bundle

Research and draft a target-specific vishing pretext. Use when creating or refining phone-based social engineering scripts for a named company, department, workflow, or event.

specterops Bundle

Research and draft a target-specific phishing email pretext. Use when building or refining a believable lure for a named company, policy change, department, or employee audience and when the work benefits from current public-source research.

specterops Bundle

Research recent public events and brainstorm phishing pretext ideas for a named target organization. Use when the user provides a client name and a phishing goal such as payload delivery or credential capture and wants timely subject ideas.

openaeon Skill

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

openaeon Skill

Skill for implementing the 3-step Memory-First Protocol (Research, Response, Learning). Use when starting ANY task to understand past context, and MUST use when completing a task to save new conventions, architectural decisions, or learned user preferences to the memory/ directory.

iapro-community Skill

Pesquisa temas atuais na web e produz síntese comparável, rastreável, com fontes primárias, datas, incerteza e recomendação.

dirtytrii Bundle

Read and analyze Xiaohongshu comments from the user's signed-in Chrome session. Use to collect, export, summarize, or classify comments for content planning, follow-up posts, audience research, reply strategy, and 引流文案。

pedroiff0 Skill

Conduct an interactive, rigorous architecture interview. Grills the user with probing questions one at a time to clarify ambiguous requirements, design decisions, edge cases, and tradeoffs before coding.

pedroiff0 Bundle

Build or rewrite a GitHub profile README (the username/username special repo) with a personalized theme — animated SVG banner, stats cards, contribution snake, tech badges, project/research tables. Includes the git conflict pitfall when the local clone is stale vs GitHub web edits, and the PyYAML `on:` quirk for workflow verification.