toddward

Use when users want to plan family dinners, build a weekly meal plan, generate a refrigerator-ready menu PDF, organize a week's grocery shopping around dinner, or kick off a meal-prep week with recipes and a shopping list.

Convert single-file task backlogs (TASKS.md format) to AutoClaude multi-file spec structure. Use when the user wants to (1) convert existing TASKS.md or similar task backlog files to AutoClaude specs, (2) initialize a new project with AutoClaude-compatible task structure, (3) migrate task definitions from simple markdown to the multi-file spec format with requirements.json, context.json, implementation_plan.json. Triggers on phrases like "convert tasks to AutoClaude", "set up AutoClaude specs", "migrate backlog", "create spec from task".

Use when creating or developing anything, before writing code or implementation plans - refines rough ideas into fully-formed designs through structured Socratic questioning, alternative exploration, and incremental validation. Optimized for git worktree workflows and Claude CLI agent patterns.

Assist users in creating quarterly connects that act as a strategic partner to guide employees through comprehensive quarterly reflections, helping craft insightful narratives for Quarterly Connection reviews that align with company values and career development goals.

Generate beautiful, professionally designed resumes as 1-2 page PDFs. Creates clean, sophisticated layouts that balance visual appeal with readability, tailored to specific job opportunities when provided.

Generate professional slide decks using company-provided template presentations. Use this skill when the user wants to create a presentation based on their own branded PowerPoint template, company slide deck template, or organizational design standards. Triggers include requests like "create slides using our template", "make a presentation with our company format", "generate a deck from this template", or "build slides matching our brand". Also use when the user asks to create slides and has uploaded or mentioned a template .pptx file.

Multi-agent thinking frameworks for rigorous problem-solving and decision-making. Contains Dialectical (thesis-antithesis-synthesis), Six Thinking Hats (parallel perspectives), First Principles (strip to fundamentals), and Composition Patterns chaining frameworks together. Use whenever the user needs to evaluate competing approaches, make architecture decisions, challenge assumptions, modernize legacy systems, write RFP responses, run post-mortems, compare technologies, or do any multi-perspective analysis. Triggers on "think this through", "pros and cons", "tradeoffs", "should we use X or Y", "devil's advocate", "argue both sides", "from all angles", "what are we missing", "first principles", "rethink this", "why do we do it this way", "brainstorm", "go/no-go", "use dialectical", "run six hats", or any thinking framework reference.

# TODO: Write a description that tells Claude when to activate this skill

# TODO: Write a description that triggers this skill when creating runbooks that need cross-referencing

Use this skill when the user asks to create, generate, or write an incident runbook, playbook, or response procedure. Triggers on alert names, incident descriptions, or requests containing words like "runbook", "playbook", "incident response", "on-call procedure", or "troubleshooting guide". Also triggers when given a monitoring alert and asked to document the response.

# TODO: Write a description for validating runbook files against team standards

Use this skill when creating new incident runbooks to cross-reference against existing runbooks. Triggers whenever a new runbook is being generated. This skill should be used alongside the runbook-generator skill to ensure new runbooks don't duplicate existing content and include links to related procedures.

Use this skill to validate incident runbooks against team standards. Triggers when asked to review, validate, check, or audit a runbook file. Also triggered automatically by the post-write hook when a runbook file is created or modified.

Initialize a new customer engagement. Creates the engagement directory structure, gathers core engagement metadata through a structured interview, and writes the initial CONTEXT.md that all subsequent skills will build upon. Run this first — it's the foundation everything else reads from.

Collect system information by running a local discovery script. Demonstrates how a skill can execute a binary or script behind the scenes to gather data that feeds into the engagement assessment. Use when the architect runs /assess-app-portfolio, mentions "app assessment", "system info", or "collect system data".

Generate a customer-facing executive presentation from all engagement artifacts. Reads CONTEXT.md and all assessment/discovery reports to produce a polished deliverable deck. Supports output as Red Hat Quick Deck (HTML), PPTX, or both. Use when the architect runs /build-deliverable-deck, says "build the deck", "create the presentation", "executive readout", "customer deliverable", or "put together the final slides".

Conduct a structured infrastructure discovery interview for a customer engagement. Walks the architect through compute, networking, storage, identity, CI/CD, and operational tooling topics. Produces a discovery report and updates CONTEXT.md. Use when the architect runs /discover-infrastructure, says "let's do discovery", "map the infrastructure", or "what's in their environment".

Turn a git diff into a standardized Conventional Commits message — a typed subject line, an explanatory body, and a "Why" section. Use when writing or improving a commit message for a set of staged or described code changes.

Redact personally identifiable information (PII) from investigative notes or reports, replacing each sensitive value with a typed, numbered placeholder like [REDACTED-SSN-1]. Use before a document is shared, when text must be sanitized while keeping its structure intact.

Create beautiful, shareable HTML-based slide presentations styled to Red Hat brand standards. Generates single-file, self-contained HTML decks with click/keyboard navigation, story-arc-driven narrative structure, and cinematic dark-mode aesthetics. Supports embedded videos (YouTube, Vimeo, direct URLs) and linked media (memes, GIFs, images) with brand-consistent styling. Use this skill whenever the user wants to create a slide deck, presentation, quick deck, quick slides, pitch deck, talk, or briefing that should follow Red Hat branding. Also trigger when the user mentions "quick deck", "quick slides", "HTML slides", "shareable deck", "presentation for [audience]", "talk about [topic]", or asks to present technical content in Red Hat style. This skill is specifically for HTML output — if the user explicitly asks for .pptx, use the pptx skill instead, but suggest this skill as an alternative for easy sharing.

Help the user learn anything — a concept, tool, body of knowledge, or skill — by combining proven techniques (Feynman, first-principles, active recall, spaced repetition, deliberate practice) into a customized plan and generating durable artifacts (notes, flashcards, quizzes, schedules, cheatsheet PDFs). Use whenever the user wants to learn, study, master, or understand something; prep for an exam, interview, or talk; absorb material from links, PDFs, articles, transcripts, code, or pasted text; build a study roadmap; create flashcards, an Anki deck, a quiz, or a cheat sheet; identify knowledge gaps; or be quizzed on a topic. Trigger broadly on phrases like "teach me", "help me learn", "get up to speed on", "quiz me", "drill me on", "make flashcards for", "I have an exam on", "study guide for", "explain X like I'm new", "I keep forgetting" — and any time the user hands over source material with an implicit goal of internalizing it rather than just summarizing.

Generate structured agile project plans with Epics, Stories, and Tasks — each with Acceptance Criteria, Definition of Done, and intrinsic value statements. Uses thinking frameworks (First Principles, Dialectical, Six Hats) as multi-agent teams to ensure plans are grounded in real user needs rather than inherited assumptions. Use this skill whenever the user asks to create a project plan, break down a project into epics and stories, generate a backlog, plan a sprint, decompose requirements into agile artifacts, write acceptance criteria, define done, or wants to understand the value of their work items. Also trigger when users say things like "plan this project", "create stories for", "break this into tasks", "what epics do we need", "build me a backlog", "write acceptance criteria", "define done for", or "help me plan this feature". Even if the user doesn't explicitly say "agile" — if they're asking for structured work decomposition with clear deliverables, this skill applies.

Multi-agent thinking frameworks for rigorous problem-solving and decision-making. Includes Dialectical (thesis-antithesis-synthesis), Six Thinking Hats, First Principles, Collision-Zone, Cynefin (problem classification), Pre-mortem (imagine failure modes), and Iceberg (events→patterns→structures→mental models), plus composition patterns and techniques like Steel-manning, Inversion, and Chesterton's Fence. Use whenever the user needs to evaluate competing approaches, make architecture decisions, challenge assumptions, modernize legacy systems, run post-mortems, classify ambiguous problems, or do multi-perspective analysis. Triggers on "think this through", "pros and cons", "tradeoffs", "should we use X or Y", "devil's advocate", "from all angles", "what are we missing", "first principles", "why do we do it this way", "go/no-go", "pre-mortem", "what could go wrong", "root cause", "this keeps happening", "steel-man", "invert the problem", "Chesterton's Fence", or any thinking framework reference.

Generate structured agile project plans with Epics, Stories, and Tasks — each with Acceptance Criteria, Definition of Done, and intrinsic value statements. Uses thinking frameworks (First Principles, Dialectical, Six Hats) as multi-agent teams to ensure plans are grounded in real user needs rather than inherited assumptions. Use this skill whenever the user asks to create a project plan, break down a project into epics and stories, generate a backlog, plan a sprint, decompose requirements into agile artifacts, write acceptance criteria, define done, or wants to understand the value of their work items. Also trigger when users say things like "plan this project", "create stories for", "break this into tasks", "what epics do we need", "build me a backlog", "write acceptance criteria", "define done for", or "help me plan this feature". Even if the user doesn't explicitly say "agile" — if they're asking for structured work decomposition with clear deliverables, this skill applies.