PSkinnerTech

Guide for drafting, revising, and evaluating BrainLifts: AI-ready knowledge documents that move from purpose and scope to experts, DOK 2 knowledge trees, DOK 3 insights, and DOK 4 spiky points of view. Use when asked to create a BrainLift, improve BrainLift writing style, transform notes or research into structured AI context, or audit whether a BrainLift has clear scope, evidence, synthesis, and original POVs.

Convert a raw, messy, half-formed, or dictated (speech-to-text) project brief into a single complete, balanced, execution-ready ONE-SHOT prompt that another agent can run to build the project correctly on the first try. Use this whenever the user has a brain-dump, voice memo, STT/dictation transcript, rough spec, or loose description of something they want built and wants it turned into a polished, optimized prompt — or asks to "compile", "optimize", "perfect", "tighten up", "clean up", or "one-shot" a prompt before handing it to a build agent, even if they never say the word "prompt". Also triggers on "turn this into a prompt for Claude/Codex/Cursor/an agent", "here's my brain dump", or "I just dictated this idea". Do NOT use to actually build or execute the project, or for trivial one-step asks — only to produce the optimized prompt.

AI-agnostic research workflow for mapping product value propositions to user and customer pain points, evidence, archetypal motivations, and messaging opportunities. Use when an assistant or agent needs to create, improve, audit, or structure value props & pain points research; turn rough notes, interviews, market data, transcripts, or source material into a clear research artifact; identify evidence gaps, assumptions, and next research steps.

AI-agnostic balanced research workflow for unbiased, both-sides argument analysis. Use when an assistant or agent needs to investigate a question, compare competing claims, prepare pro/con or debate briefs, steelman opposing views, audit source quality, red-team a draft, validate a Brainlift, or produce research with explicit counterarguments, limitations, uncertainty, and evidence-grounded conclusions.

Access the user's personal context layer from an AI agent session through the local Nessie CLI. Use when the user references prior work, asks what they know about a topic, needs answers grounded in past AI conversations or notes, wants to browse available sources, asks to resume/take over prior AI sessions, or wants Codex to create, update, organize, or generate reusable Nessie contexts.

Use for working with Read.ai meeting data through the Read.ai MCP server: finding meetings by date, title, participant, owner, folder, or recency; retrieving transcripts, summaries, chapter summaries, action items, key questions, topics, metrics, participants, report URLs, and recording links; and turning meeting context into digests, follow-up tasks, engineering specs, CRM notes, daily briefs, decision logs, or workspace-wide analysis. Use when the user mentions Read.ai, Read AI, meeting reports, meeting transcripts, meeting summaries, action items, or asks to convert meeting discussions into deliverables.