Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

research-tools

Étoiles2

Forks0

Mis à jour11 mars 2026 à 22:42

Use when researching topics, finding YouTube videos, analyzing sources with NotebookLM, or doing requirements gathering interviews. Triggers on research, find videos, YouTube search, analyze sources, NotebookLM, research pipeline, deep interview, interview me, requirements gathering, Socratic, yt-dlp, transcript, audio overview, infographic, mind map, study guide, FAQ, briefing doc, find and analyze, research for me, analyze these videos, competitive research.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

george11642

george11642/george-plugins

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Analystes en études de marché et spécialistes en marketingProfessions des affaires et des opérations financières·SOC 13-1161

Explorateur de fichiers

5 fichiers

SKILL.md

readonly

name	research-tools
description	Use when researching topics, finding YouTube videos, analyzing sources with NotebookLM, or doing requirements gathering interviews. Triggers on research, find videos, YouTube search, analyze sources, NotebookLM, research pipeline, deep interview, interview me, requirements gathering, Socratic, yt-dlp, transcript, audio overview, infographic, mind map, study guide, FAQ, briefing doc, find and analyze, research for me, analyze these videos, competitive research.
metadata	{"version":"1.0.0"}

Research Tools

Route research, analysis, and requirements-gathering tasks to the correct workflow.

Task Router

Task	Reference	Key Actions
Analyze sources with NotebookLM, generate deliverables	references/notebooklm-workflow.md	Create notebook, add sources, ask questions, generate audio/infographic/FAQ
Search YouTube for videos, fetch transcripts	references/youtube-search.md	yt-dlp search, structured results table, VTT transcript extraction
End-to-end research: YouTube -> NotebookLM -> Obsidian	references/research-pipeline.md	Chain all 3 tools, save structured notes to vault
Socratic requirements gathering, spec crystallization	references/interview-technique.md	Ambiguity scoring, challenge agents, spec document generation

Quick Decision

"Analyze these sources" -> NotebookLM workflow
"Find videos about X" -> YouTube search
"Research X for me" / "find and analyze" -> Full pipeline
"Interview me" / "I have a vague idea" -> Deep interview
URL provided directly -> Skip search, go to NotebookLM or transcript

MCP Tools Required

Use ToolSearch at task start to load:

mcp__notebooklm__* — NotebookLM notebook management and questions
mcp__obsidian__* — Obsidian vault note creation (for pipeline saves)

Shared Principles

Always return full YouTube URLs so they can be passed to NotebookLM as sources
NotebookLM handles its own transcription — do not pre-fetch transcripts when passing to NotebookLM
Visual deliverables (infographic, mind map) can take 5-15 minutes — set expectations
Deep interview: one question at a time, target weakest clarity dimension, never batch
Research pipeline default: 10 videos, analysis only (escalate to deliverable if requested)

Layer 3 Skills

notebooklm-research — NotebookLM MCP workflow for source analysis and deliverable generation
youtube-research — YouTube video search and transcript extraction via yt-dlp
research-pipeline — Full YouTube -> NotebookLM -> Obsidian orchestration
deep-interview — Socratic requirements gathering with mathematical ambiguity scoring

Plus depuis ce dépôt

même dépôt

fpga

george11642/george-plugins

Master FPGA skill covering Vivado, SystemVerilog/Verilog/VHDL, RTL design, timing closure, CDC, AXI interfaces, FSMs, pipelines, memory interfaces, HLS, verification, and hardware optimization. Uses Context7 MCP for up-to-date library docs. Use when FPGA, Verilog, VHDL, HDL, RTL, synthesis, or hardware design mentioned.

2026-03-242

analytics-posthog

george11642/george-plugins

Use when setting up PostHog analytics, feature flags, experiments, or querying PostHog data. Triggers on PostHog, PostHog event, PostHog feature flag, PostHog experiment, A/B test PostHog, HogQL, PostHog funnel, PostHog dashboard, PostHog LLM cost, posthog.capture, isFeatureEnabled, PostHog MCP, PostHog survey, PostHog error tracking.

2026-03-112

auth-clerk

george11642/george-plugins

Use when setting up Clerk authentication, configuring auth middleware, protecting routes, or handling Clerk webhooks. Triggers on Clerk, Clerk auth, ClerkProvider, auth middleware, protected routes, Clerk webhook, Svix, sign-in, sign-up, Clerk token, getToken, Clerk secret key, publishable key, Clerk setup, CAPTCHA signup, Clerk Next.js, Clerk React, Clerk Expo, user.created event, session management, Clerk identity.

2026-03-112

backend-data

george11642/george-plugins

Use for any server-side API or data persistence work. Triggers on REST endpoints, GraphQL resolvers, DataLoader, Node.js, Express, Fastify, API design, pagination, filtering, sorting, databases, SQL, PostgreSQL, indexes, EXPLAIN ANALYZE, query optimization, Prisma, Drizzle, TypeORM, SQLAlchemy, ORM, N+1 queries, migrations, Alembic, schema design, data modeling, normalization, JWT, OAuth, authentication, authorization, rate limiting, Redis, caching, message queues, BullMQ, Kafka, RabbitMQ, webhooks, idempotency, signatures, microservices, multi-tenant, row-level security.

2026-03-112

browser-agent

george11642/george-plugins

Use when automating Chrome browser interactions, taking screenshots, filling forms, or verifying UI visually. Triggers on browser automation, take screenshot, screenshot page, fill form, click button, navigate to URL, Chrome DevTools, use_browser, visual verification, desktop and mobile screenshot, OAuth flow in browser, email verification flow, extract page content, DOM inspection, multi-tab browsing, form submit, CSS selector, headless Chrome, browser profile, login flow, signup flow.

2026-03-112

cloud-infra

george11642/george-plugins

Use when working with Docker, Kubernetes, Terraform, CI/CD, cloud providers (AWS/GCP/Azure), serverless, observability, bash/shell scripts (getopts, strict mode, traps), systemd, or infrastructure tooling. Also covers Helm, GitHub Actions, GitLab CI, Lambda, Cloud Run, ECS, EKS, GKE, nginx, DNS, SSL, Prometheus, Grafana, OpenTelemetry, FinOps, GitOps, ArgoCD, service mesh, Istio, BATS testing, ShellCheck, cron, awk, sed, curl, parallel execution, signal handling, process management.

2026-03-112

name	research-tools
description	Use when researching topics, finding YouTube videos, analyzing sources with NotebookLM, or doing requirements gathering interviews. Triggers on research, find videos, YouTube search, analyze sources, NotebookLM, research pipeline, deep interview, interview me, requirements gathering, Socratic, yt-dlp, transcript, audio overview, infographic, mind map, study guide, FAQ, briefing doc, find and analyze, research for me, analyze these videos, competitive research.
metadata	{"version":"1.0.0"}

Research Tools

Route research, analysis, and requirements-gathering tasks to the correct workflow.

Task Router

Task	Reference	Key Actions
Analyze sources with NotebookLM, generate deliverables	references/notebooklm-workflow.md	Create notebook, add sources, ask questions, generate audio/infographic/FAQ
Search YouTube for videos, fetch transcripts	references/youtube-search.md	yt-dlp search, structured results table, VTT transcript extraction
End-to-end research: YouTube -> NotebookLM -> Obsidian	references/research-pipeline.md	Chain all 3 tools, save structured notes to vault
Socratic requirements gathering, spec crystallization	references/interview-technique.md	Ambiguity scoring, challenge agents, spec document generation

Quick Decision

"Analyze these sources" -> NotebookLM workflow
"Find videos about X" -> YouTube search
"Research X for me" / "find and analyze" -> Full pipeline
"Interview me" / "I have a vague idea" -> Deep interview
URL provided directly -> Skip search, go to NotebookLM or transcript

MCP Tools Required

Use ToolSearch at task start to load:

mcp__notebooklm__* — NotebookLM notebook management and questions
mcp__obsidian__* — Obsidian vault note creation (for pipeline saves)

Shared Principles

Always return full YouTube URLs so they can be passed to NotebookLM as sources
NotebookLM handles its own transcription — do not pre-fetch transcripts when passing to NotebookLM
Visual deliverables (infographic, mind map) can take 5-15 minutes — set expectations
Deep interview: one question at a time, target weakest clarity dimension, never batch
Research pipeline default: 10 videos, analysis only (escalate to deliverable if requested)

Layer 3 Skills

notebooklm-research — NotebookLM MCP workflow for source analysis and deliverable generation
youtube-research — YouTube video search and transcript extraction via yt-dlp
research-pipeline — Full YouTube -> NotebookLM -> Obsidian orchestration
deep-interview — Socratic requirements gathering with mathematical ambiguity scoring