skills

Learn and refine my writing voice through conversation.

Distill a book, method, or framework into an agent skill (Claude Code or any compatible agent) that follows a structured template (numbered framework sections, application tables, usage patterns, ethical boundaries, references/ deep-dives). Grounds every claim in verifiable sources — cites pages, URLs, or quotes; web-searches when the source isn't in front of the agent; drops anything that can't be cited. Uses one saved multi-agent workflow for extraction, coherent synthesis, reference expansion, and targeted review when authorized, with a portable direct-Agent fallback. Use when the user wants to turn a book / method / framework / paper / talk / course into a skill, or says "distill this", "make a skill from this book", "turn X into a skill", "book to skill", "source to skill".

Build and audit founder demand campaigns using Daniel Priestley’s Oversubscribed method, creating more qualified demand than honest delivery capacity before releasing an offer. Use when the user mentions “create more demand,” “launch oversubscribed,” “build a waitlist,” or asks how to generate excess demand for an offer. Also trigger when planning a launch, reviewing weak demand, measuring release readiness, or deciding how and when to release limited availability.

Facilitate an Inquiry through the canonical First Principles Thinking approach.

Solution Options is the second phase after problem-firewall: generate, stress-test, and evaluate solutions from a clear Problem Frame. Use when the user has a plain desired outcome, obstacle, and root-cause condition and wants to explore solution options, evaluate tradeoffs, run a premortem, avoid binary thinking, define decision criteria, or choose what to do next. For vague, symptom-level, or solution-first problems, use problem-firewall first.

Use when the user wants help solving something but the problem is vague, symptom-level, or framed as a premature solution. Enforce a problem-solution firewall: clarify the desired outcome, obstacles, root-cause condition, and user-owned plain-language Problem Frame before moving to solution methods.

Use when the user mentions tree alignment, logic tree, binary branching, or asks to walk down a tree. Guides a vague intent through mutually exclusive, collectively exhaustive binary forks to a concrete leaf/action.

Apply Jordan Belfort's Straight Line Selling from Way of the Wolf: Three Tens, first four seconds, prospecting, sales tonality, presentation scripts, objection looping, action threshold, pain threshold, and ethical closing. Use when the user mentions Straight Line, Way of the Wolf, Jordan Belfort, Three Tens, looping, action threshold, pain threshold, sell me this pen, sales tonality, first four seconds, prospecting script, sales presentation, closing objections, or wants to move a qualified prospect toward a decision without pressure. For problem-centric B2B discovery, see gap-selling. For pressure-free qualification, see sandler-selling-system. For decision-science framing, see science-of-selling.

Apply Keenan's Gap Selling methodology to diagnose buyer problems, build current-state/future-state gaps, and move B2B sales by selling change instead of product. Distinct from generic discovery: it centers the sale on problem, impact, root cause, intrinsic motivation, and the next yes. Use when the user mentions Gap Selling, Keenan, current state, future state, problem-centric selling, PIC, Problem Identification Chart, next yes, or "I'm confused, you said". Also trigger for sales discovery, deal coaching, pipeline review, demos, objections, price resistance, prospecting emails, or qualifying B2B opportunities. For commercial insight/status quo reframes, see challenger-sale. For buyer commitments and emotional state, see science-of-selling. For indecision after intent, see jolt-effect.

Turn procrastination into regulated action with an interview-driven emotion regulation prescription.

Sandler Selling System skill for pressure-free sales using the Submarine, upfront contracts, pain, budget, decision, fulfillment, post-sell, dummying up, reversing, and Negative Reverse Selling. Use when planning sales calls, discovery, qualification, budget conversations, decision-process questions, demos, post-sell checks, or handling objections like "think it over," "send me info," price resistance, vague interest, stalls, ghosting, and buyer's remorse. Use for Sandler roleplay where the user wants to practice as seller, have the agent demonstrate as seller, simulate a skeptical prospect, switch roles, drill reverses, or get call feedback. For problem-centric B2B diagnosis, see gap-selling. For commercial insight/status quo reframes, see challenger-sale. For indecision after intent, see jolt-effect.

Apply David Hoffeld's Science of Selling to teach the framework, build sales artifacts, or diagnose stalled deals. Use for Sales Equation/Six Whys, Why People Buy/primary buying motivators, value statements, reciprocity value statements, Primary Buying Motivator Statements, discovery, demos, objections, closing, or Hoffeld questions. For outbound systems, see predictable-revenue; for prospecting scripts, see prospecting; for negotiation, see negotiation.

JOLT Effect sales coaching for overcoming customer indecision after purchase intent exists. Use when a deal stalls with “think about it,” “no decision,” buyer hesitation, endless research, too many options, risk anxiety, forecast slippage, or when a sales skill needs an indecision playbook. For creating status-quo urgency, see challenger-sale; for buyer commitments and emotions, see science-of-selling.

Create, diagnose, and roleplay live outreach conversations using a conversation-first method for booking calls, follow-ups, and next steps across cold calling, door-to-door, and direct outreach. Use when the user mentions “conversation-first outreach,” “cold outreach conversation,” “cold calling,” “door to door,” live outreach, follow-up, objection handling, or booking calls. Also trigger when drafting scripts, improving outreach, structuring an outbound conversation, or roleplaying prospect conversations.

Capture domain stories through collaborative interviews and generate pure domain layer code from them. Two phases: capture (interview to YAML) and generate (YAML to domain code). Use when user says "domain storytelling", "capture a domain story", "generate domain layer", "let's model the domain", or runs /domain-storytelling with capture or generate subcommands.

Four-phase engineering framework for shipping features with confidence: Find → ARCH → Automate → Specify-Test-Refine. Each phase has a required input, a guided process, and an exit gate you must pass before advancing. Integrates Responsibility-Driven Design and the 54321 layered architecture model. Supports interview mode for when the user doesn't want to provide codebase access — the agent interviews instead of exploring. Use when the user wants to plan and build a feature, says "help me ship this", "let's plan this out", "walk me through building this", or provides a ticket, PRD, design, or feature request. Also triggers on "interview mode", "no codebase access", or "faas interview".

Apply the INVEST framework to make tasks, issues, user stories, backlog items, goals, and implementation slices clear, small, and actionable. Use when the user mentions INVEST, independent, negotiable, valuable, estimable, small, testable, user stories, backlog refinement, issue quality, task slicing, acceptance criteria, or asks to improve any task before execution.

Apply Anthony Ulwick's Outcome-Driven Innovation (ODI) — the eight-step method that turns "what customers want" from guesswork into a quantitative process. Capture **Jobs, Outcomes, and Constraints** instead of customer opinions; rank them with the **Opportunity Algorithm** (`importance + max(importance − satisfaction, 0)`); and score every concept on the Customer Scorecard. Use when user mentions "outcome-driven innovation", "ODI", "Ulwick", "opportunity algorithm", "outcome statement", "desired outcomes", "underserved / overserved", "outcome-based segmentation", "customer scorecard", "jobs to be done" *for product development specifically*, "what customers want", or "Strategyn". Also trigger when planning a new product or feature, auditing why an R&D pipeline is producing duds, designing a customer interview to extract metrics (not opinions), prioritising opportunities, segmenting a market that demographics won't split, repositioning a product whose true value is hidden, or evaluating concepts before build.

Write code that minimizes time-till-understanding using Boswell & Foucher's tactics from *The Art of Readable Code*: naming, aesthetics, comments, control flow, expressions, variables, decomposition, and tests. Use when the user mentions "readable code", "time-till-understanding", "Art of Readable Code", "Boswell", "naming variables", "naming functions", "explaining variable", "summary variable", "minimize nesting", "return early", "Yoda notation", "comment density", "ambiguous name", "extract subproblem", "one task at a time", "rubber duck", "smaller scope", "write-once variable". Also trigger when reviewing a PR for line-level readability, refactoring confusing logic, deciding whether to comment, picking between two names, untangling a giant boolean expression, or shrinking variable scope. Distinct from `clean-code` (Martin: SRP/OOP/error handling) and `refactoring-ui` (visual design): this skill is *micro-level* code readability — names, lines, expressions, and the tight loop a reader runs through them.

Apply, review, and explain solution architecture using Shrivastava and Srivastav's handbook model: align business goals, NFRs, architecture views, quality pillars, operations, cost, and documentation. Use when the user mentions "design this architecture", "review my solution architecture", "make this scalable", "write a solution architecture document", or "check the NFRs". Also trigger when the user is working on a SAD, cloud architecture design, architecture trade-off review, migration, modernization, or production-readiness review.

Apply, diagnose, and teach Jeff Patton's User Story Mapping — a visual technique for building shared understanding and slicing work into outcome-focused releases. Organizes the product backlog as a two-dimensional grid (backbone + prioritized tasks) rather than a flat list, keeping the whole story visible while planning incremental delivery. Use when the user mentions user story mapping, story map, story map backlog, backbone and tasks, walking skeleton, or slice the map. Also trigger when the user wants to plan to build less, plan to learn faster, or plan to finish on time. Also trigger when the user is building a story map, slicing a release, defining MVP scope, running a product discovery workshop, or restructuring a flat backlog.

Produce a chunk-by-chunk rationale for the current session's diff and persist it to .claude/rationale/. Use after a non-trivial change, or invoked automatically by the Stop hook before the session ends. Pair with /explain to retrieve rationale by file/line later.

Coaches users to turn goals into identity-based systems and durable habits using James Clear's Atomic Habits framework: habit loop, Four Laws of Behavior Change, environment design, habit stacking, and tracking. Use when the user mentions Atomic Habits, James Clear, habits, habit design, behavior change, routines, systems over goals, identity-based habits, habit stacking, making habits obvious/attractive/easy/satisfying, breaking bad habits, or asks to turn a goal into a repeatable system.

Apply and diagnose Greg McKeown's Essentialism framework for doing less but better through Essence, Explore, Eliminate, and Execute. The skill uses the 90 Percent Rule, vital-few/trivial-many filtering, essential intent, graceful no scripts, buffers, constraints, and routines to turn overcommitment into high contribution. Use when the user mentions essentialism, less but better, disciplined pursuit of less, vital few, trivial many, overcommitted, stretched too thin, busy but not productive, help me say no, or what should I focus on. Also trigger when reviewing commitments, calendars, priorities, team strategy, project scope, meetings, routines, or personal operating systems.

Sync progress and commit the next rolling timeblock to the calendar. Run this many times per day to stay locked in. Use when the user says "go", "next block", "what's next", "lock in", or "sync my day".

Planning session that builds a complete daily note with Shaped Goals, Rolling Timeblocks, calendar awareness, and a procrastination trigger roadmap. Targets today (if before noon, incomplete note) or tomorrow (after noon). Uses deep mode by default; use `/intentional auto` for auto proposal mode. Use when the user says "intentional", "plan today", "plan tomorrow", or "set up my day".

Finds active habit cards in this Obsidian vault and surfaces the right cue/action at the right time. Use when the user runs /my-habits, asks to review habits, find active habits, archive habits, or surface habit cards by day, schedule, cue, priority, or tag.

Daily workflow router. Determines whether to run /intentional, /go, or /wrap-up based on current time, today's daily note state, and user intent. Use when the user says "now", "what should I do", "continue my day", "run my day", "I'm stuck", "help me get back on track", "what mode am I in", or gives ambiguous daily-workflow input.

Plan a "One-Month Day" the night before — a single day engineered to produce a month's worth of output by stacking flow blocks (Rían Doris / Flow Research Collective). Walks the user through Preparation end-to-end (Isolate Target → Clear Load → Build Flow Fortress → Cement Commitment → Lock Schedule), then outputs the plan as a markdown brief in the user's notes vault, as calendar events for the next day, or both. Use when the user says "plan my one-month day", "set up a flow day", "plan tomorrow as a one-month day", "schedule a deep work day", "stack flow blocks for tomorrow", "I need a monster output day", or wants to design a single high-output day around flow cycles. Distinct from `the-one-thing` (lifelong focus on one goal) and `deep-learner` (Socratic learning) — this is the night-before planning workflow specifically.

Narrow focus to extraordinary results using Gary Keller's Focusing Question, Goal Setting to the Now, and Time Blocking. Use when the user mentions "the ONE Thing", "focusing question", "time blocking", "domino effect", "go small", "lead domino", "goal setting to the now", "80/20", "Pareto", "Three Commitments", "Four Thieves", "E to P", or "counterbalance". Also trigger when cutting a bloated to-do list, picking a team's top priority or OKR, designing a daily schedule around deep work, deciding what to say no to, diagnosing overwhelm or work-life-balance problems, planning a product roadmap around a single bet, or when effort is not producing results. Covers the ONE Thing principle, the Six Lies of success, the Focusing Question, Goal Setting to the Now, Time Blocking, the Three Commitments, and the Four Thieves. For habit formation mechanics, see drive-motivation. For product positioning around a single bet, see obviously-awesome. For persuading a team to adopt one priority, see made-to-stick.

Helps users break acute task procrastination through a short, action-first coaching loop: clarify the task, identify the dominant blocker, reduce resistance, and commit to a tiny immediate start. Use when the user says they are procrastinating, avoiding a task, stuck, unmotivated, dopamine-fried, distracted, dreading something, cannot start, or wants help starting a specific task right now.

End-of-day closure — summarizes the day, catches missing logs, reflects, and hands off to /intentional for tomorrow. Use when the user says "wrap up", "end of day", "day review", "reflect on today", or "close out the day".

Design and deliver training programs using Pastore's ADDIE framework: Analysis, Design, Development, Implementation, Evaluation. Use when the user mentions "ADDIE", "instructional design", "design a training", "build a course", "eLearning design", "needs analysis", "front-end analysis", "task analysis", "learning objectives", "ABCD objectives", "instructional congruency", "storyboard a course", "Kirkpatrick evaluation", "train the trainer", "rapid ID", or "is training the right solution". Also trigger when diagnosing failed training, writing objectives, designing aligned assessments, choosing instructional strategies, applying Mayer's multimedia principles, or evaluating training ROI.

Align the user's mental model with reality before they act, by surfacing implicit beliefs via prediction-check, verifying against ground truth, and why-tracing wrong beliefs to their root assumption. Three modes: codebase (verify against code), learning (verify against authoritative source), planning (verify present-reality assumptions, flag future-bets explicitly). Use when the user is about to make a codebase change, learn a new topic, or commit to a plan, and wants to surface wrong beliefs first. Also trigger on "check my mental model", "what am I getting wrong about X", "stress-test my understanding before I do X", "where is my model off", or "align my model". Asks for confidence before revealing truth — high-confidence-wrong beliefs (the dangerous ones) get the deepest correction. For surfacing gaps via attempted explanation, see feynman. For stress-testing decisions in a plan, see grill-me. For encoding new material into a retention map, see bear-hunter-system.

Guide the user through the Bear Hunter System (BHS) to encode complex material with 80-95% retention via a structured mind map. Use when the user wants to learn a topic, study complex material, build a GRINDE map, use BHS, wants to AIM/SHOOT/SKIN a subject, or needs to encode information quickly. Also trigger for "bear hunter", "GRINDE map", "layers of learning", or "backbone and concepts".

Teaches any material by extracting understanding through disciplined Socratic questioning — not by explaining. Use when user wants to deeply learn, study, or internalize a concept, book, article, framework, or any material they provide. Triggers include "help me learn", "teach me", "I want to understand", "quiz me", "deep dive", or when user pastes dense material they want to master.

Deep-understand any concept by explaining it simply until all gaps are exposed and filled. Use when the user wants to truly understand something — mentions "understand", "learn", "explain", "feynman", "teach", or "test my understanding" about any concept, topic, or idea.

Runs interactive tutoring sessions using Stanislas Dehaene’s four pillars of learning: attention, active engagement, error feedback/correction, and consolidation. Use when the user wants to learn, study, review, practice, be quizzed, or be taught from source material.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.