Shanon

MUST BE USED when analyzing meeting transcripts or notes. Classifies input type, attributes speakers, and verifies names against colleagues.json. Works with routing-brains and summarizing-meetings skills for complete workflow.

A framework for evaluating whether a product's success is mathematically possible based on its cost structure, acquisition assumptions, and unit economics. Use this when vetting a new job opportunity, evaluating a startup's viability, or determining if a failing product can be "iterated" to success.

A structured method for gathering high-signal, contextual feedback from a trusted network to validate ideas or navigate complex career decisions. Use this when facing a "fork in the road" career choice, prioritizing product features, or narrowing down topics for public speaking or content.

Create and maintain individual colleague communication profiles in Markdown. Use when the user wants to document a person's communication style, tone preferences, decision style, sensitivities, channels, response cadence, or examples of good vs bad communication, and store it as a per-person profile under input/org/profiles/.

Gather context through high-leverage eigenquestions when information is missing or ambiguous. ACTIVATE THIS SKILL when: (1) context is missing or unclear, (2) user asks something requiring unstated assumptions, (3) working within a brain without recent context, (4) starting new work or strategic decisions, (5) multiple valid approaches exist without clear direction, (6) user says "clarify", "help me think through", or "what should I consider". This skill asks ONE discriminating question at a time to unlock maximum downstream clarity.

Drafts concise, professional PM emails using the CRAFT method. Use when user needs to compose, draft, write, or rewrite professional email communication including follow-ups, status updates, escalations, and stakeholder messages.

Converts Markdown files to professional PDF documents using WeasyPrint. Use when user wants to convert markdown to PDF, export as PDF, or generate PDF from documents. Supports custom CSS styling, page headers/footers, and Autodesk brand themes.

Process and organize notes.md using the LNO (Leverage/Neutral/Overhead) framework for systematic task prioritization. Use when: (1) adding action items to notes.md, (2) organizing daily tasks, (3) categorizing work by ROI potential, (4) carrying forward incomplete tasks to new date sections, (5) routing brain-specific notes, (6) user requests "update notes" or "process my notes", or (7) synchronizing action items from CLAUDE.md files to daily tracking. Applies Shreyas Doshi's ROI-based prioritization framework to maintain strategic focus in daily execution.

PROACTIVELY used when user needs daily priorities or LNO classification. Generates and maintains TODO.md with Leverage/Neutral/Overhead priorities. Scans active brains and extracts actionable items dynamically.

PROACTIVELY used for routing meeting items to Brain CLAUDE.md files. Discovers Brains dynamically, matches items by confidence, handles unmatched content. Works with analyzing-meetings and summarizing-meetings skills.

Generates Slack messages in user's authentic voice: direct, concise, data-driven. Use when user needs to write, draft, compose, or rewrite Slack messages, DMs, or channel posts. Adapts style based on channel type (public vs DM) and message type.

MUST BE USED when generating meeting summaries after analysis and routing. Creates per-brain and overall summaries, updates CLAUDE.md files. Works with analyzing-meetings and routing-brains skills.

Adapt Shannon to your workflow. Use proactively when patterns emerge, or when user asks "evolve Shannon", "adapt the system", "improve Shannon", "Shannon doesn't fit my workflow", or "suggest system changes".

Diagnose Shannon system integrity. Use when something seems broken, on first run, or when user asks "check system health", "diagnose Shannon", "what's broken", "is Shannon set up correctly", or "run health check".

Download YouTube transcripts using yt-dlp. Outputs markdown with timestamps (default) or VTT. Use when extracting subtitles/captions from YouTube for analysis or reference.

Search and discover code context across GitHub Enterprise organizations using gh CLI. Use when needing to find code implementations, understand how functions are used, trace dependencies, or gather context about deployed/developed code across multiple repositories. Triggers on requests like "find where X is implemented", "how is Y used across repos", "show me the auth code", or "find context for this feature".

Guide for creating effective custom subagents in Claude Code. Use when users want to create or update specialized AI subagents with custom system prompts, tool restrictions, and specific configurations for task delegation.

Use these research-backed techniques to maximize LLM performance and secure AI agents. Apply this skill when designing system prompts for AI products, troubleshooting low-accuracy outputs, or testing model vulnerabilities against prompt injection.

Transition from a hands-on "bricklayer" to a high-level "architect" by managing a fleet of autonomous AI agents. Use this when you need to scale engineering output with a small team, handle repetitive migrations/bug fixes, or onboard engineers to complex legacy codebases.

Build functional software prototypes and MVPs without deep technical skills by using AI agents as "developers in your pocket." Use this skill when you need to validate a new product concept, build custom back-office tools (e.g., a real estate data manager), or create high-fidelity demos to unblock engineering roadmaps.

Transition from static LLM chats to autonomous agents that execute multi-step tasks. Use this when you need to automate cross-platform reports (e.g., Snowflake to Google Docs), build self-service tools for non-technical teams, or create "anticipatory" engineering workflows that draft PRs based on Slack discussions.

A step-by-step framework to safely transition AI products from prototypes to autonomous agents. Use this when reliability is a major concern, when users are skeptical of AI decision-making, or when deploying LLM-based systems into high-stakes workflows.

Shift focus from AI hype (latest models, vector DBs, agentic frameworks) to high-leverage activities that actually improve product quality. Use this when an AI feature is underperforming, when the team is stuck in a "research loop," or when planning the roadmap for a new AI application.

A systematic workflow to move AI products beyond "vibe checks" by identifying specific failure modes and building automated LLM judges. Use this when your AI outputs feel "janky," when you need a feedback signal for prompt engineering, or when monitoring production performance at scale.

Develop "quizzes" (evals) to measure model performance on specific tasks. Use these benchmarks to guide fine-tuning, determine product UX patterns, and track performance improvements over time. Use this when launching a new AI feature, switching between model versions, or optimizing for high-stakes accuracy.

Transform an established SaaS or service business into an AI-first company. Use this when growth has plateaued, your industry is facing AI disruption, or you need to shift from seat-based to outcome-based revenue models.

Transition from manual code writing to high-level architectural oversight by leveraging AI tools. Use this skill when onboarding junior developers to accelerate their growth, when planning complex feature integrations, or when auditing legacy codebases for efficiency gains.

A complete end-to-end framework for non-technical product managers to build and ship software using AI coding agents. Use this when starting a side project, building a prototype, or automating internal tools without an engineering team.

Rapidly build, prototype, and deploy full-stack software using AI "text-to-app" tools. Use this when you need to create a greenfield application, build a high-fidelity working prototype for user testing, or bypass traditional engineering bottlenecks for internal tools.

A framework for transitioning from incremental SaaS development to an AI-native product strategy. Use this skill when you need to "refound" an existing product for the AI era, accelerate shipping velocity for AI features, or upskill a product team to be more hands-on with LLM primitives.

Transition from traditional PRDs to "Evals" (evaluations) to guide AI model behavior. Use this skill when launching new AI features, debugging unpredictable model outputs, or moving from a prompted prototype to a production-ready agent.

Strategy and tactics for evolving from a generalist PM to an AI PM. Use this skill when identifying if a problem requires an AI solution, collaborating with research scientists, or using generative AI to augment your core PM deliverables.

A framework to assess and integrate AI into your product strategy by mapping core customer problems to AI capabilities. Use this when your industry is facing a major technology shift, when prioritizing an AI roadmap, or when deciding between augmenting existing features vs. building new AI-first solutions.

A framework for balancing outsized performance (Alpha) with system reliability (Beta) through strategic process design. Use it when deciding how much process to add to a team, evaluating a new hire's fit for a specific project, or standardizing product quality without stifling innovation.

A framework for measuring product velocity and output quality using standardized stage-gates (P-strat to P2) and binary quality triage. Use this when you need to identify team bottlenecks, align cross-functional teams (Analytics, Marketing, Product, Engineering, Design), or calibrate organizational standards for "what great looks like."

Strategies for getting products and content cited within LLM responses (ChatGPT, Perplexity, Claude). Use this when launching a new product, seeing referral traffic from AI agents, or trying to capture high-intent users who have moved from Google search to chat interfaces.

A three-step framework (Articulate, Ask, Accept) to overcome career stagnation and interpersonal conflict by expressing needs with integrity. Use this when you feel stuck in your career, are avoiding a difficult conversation with a stakeholder, or need to align a team on a high-stakes deadline.

Systematize customer discovery by automating the sourcing and scheduling of research calls. Use this when you are starting a new discovery phase, feel disconnected from "raw" customer material, or need a steady stream of interviews without manual sourcing.

A framework for determining when to create a new software category versus winning an existing one, and the tactical steps to define and validate that category. Use this when your product is too disruptive for current labels, when existing categories have negative associations, or when you need to expand your TAM.

A framework to evaluate the market potential and strategic direction of B2B products based on workflow frequency and organizational breadth. Use it when validating a new startup idea, evaluating a product's "ceiling," or planning a pivot to increase market share.