mpuig

Design multi-service architectures with RAW workflows as components

Writing effective dry_run.py mocks for workflow testing without external dependencies

Guide for creating structured plans with numbered steps and quality gates

Understanding and passing workflow quality gates (validate, dry, pytest, ruff, typecheck)

Test-driven development loop for workflows - write tests first, then implementation

Creating reusable tools in tools/ directory that workflows can import and use

Create Agent Skills that comply with the agentskills.io specification. Use when the user asks to create a new skill, add agent capabilities, or build reusable instructions.

Create reusable RAW tools that workflows can import. Use when the user asks to create a tool, extract reusable functionality, or build a new capability for workflows.

Build a complete presentation deck from a brief. Generates storytelling plan, slide operations, renders the deck, and runs QA. Requires extracted template contracts from /slides-extract. Use when the user wants to create slides, build a deck, generate a presentation, write a strategy deck, or says things like "make me a 10-slide deck on X", "create a presentation about Y", "build slides for the board meeting".

Extract template contracts from a .pptx file. Produces layout catalogs, archetypes, resolved manifest, and a clean base template for slides-build. Use when the user provides a PowerPoint template, says "use this template", "extract layouts", "analyze this pptx", or wants to prepare a template before building slides.

End-to-end deck pipeline — extract, preflight, build, audit, critique, and polish in one pass. Use when the user wants a complete deck from scratch with a template, says "create a full deck", "build me a presentation end to end", "make a polished deck from this template", or provides both a brief and a template and expects a finished, presentation-ready result. Prefer this over chaining individual skills manually.

Run technical quality checks on an existing deck. Finds and fixes font size violations, shape overlaps, contrast issues, missing sources, and layout compliance problems. Use when the user says "check the deck for issues", "run QA", "lint the slides", "are there any formatting problems", "audit the presentation", or wants to verify visual quality before sharing.

Review an existing deck for storytelling quality, visual hierarchy, and content effectiveness. Identifies weak action titles, MECE violations, isomorphism mismatches, and density issues. Use when the user says "review my deck", "critique the presentation", "are the slides telling a good story", "check the narrative flow", "improve the slide titles", or wants feedback on content quality rather than technical formatting.

Edit an existing presentation deck. Supports text edits, layout transforms, and ops-based patches. Use when the user wants to change text on a slide, update a title, fix a typo, swap a layout, replace chart data, add or remove slides, or says things like "change slide 3 title to X", "update the numbers on the chart", "move the agenda slide".

Final pass before shipping a deck. Ensures speaker notes, metadata, sources, disclaimer, and consistent formatting are all in place. Use when the user says "polish the deck", "add speaker notes", "finalize the presentation", "make it ready to send", "check sources and footnotes", or the deck is content-complete but needs a finishing pass.

Build consulting-grade presentations from a natural-language brief using a 4-phase Pre-flight -> Storyline Review -> Build -> QA workflow on top of the agent-slides CLI.

Run one experiment cycle of the demo research loop. Reads program-demo.md for the current lane and hypothesis, applies a fix, builds all benchmarks, scores them, and records results.

Guide template ingestion end to end: learn a PPTX, inspect and edit the manifest, smoke-test template-backed layouts, then hand off to create-deck.

Modify an existing agent-slides deck in place. Inspect → smallest mutation → validate. Handles layout switches, slot edits, content changes, rebinding, and batch operations.

Run rendered visual QA on an `agent-slides` deck using LibreOffice slide screenshots, a scored checklist, and optional auto-fixes for common issues.

Review an `agent-slides` deck for storytelling quality, narrative structure, message coverage, and content density without drifting into rendered visual QA.

Run the final pre-share polish pass on an `agent-slides` deck. Checks structural completeness, source lines, formatting consistency, and content completeness, then applies only safe mechanical fixes.

This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Guides discovery of local skills and enforces minimal documentation style.

Analyze a repository to generate recommended Claude Code settings.json permissions. Use when setting up a new project, auditing existing settings, or determining which read-only bash commands to allow. Detects tech stack, build tools, and monorepo structure.

Perform code reviews following Python best practices. Use when reviewing pull requests, examining code changes, or providing feedback on code quality. Covers security, performance, testing, and design review.

Create commit messages following conventional commit conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with issue references.

Create pull requests following best practices. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows conventional commit and PR conventions.

Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fixes until all checks are green. Automates the feedback-fix-push-wait cycle.

Generate AWS architecture diagrams from infrastructure JSON. Use when user asks to "generate diagram", "create AWS diagram", "visualize infrastructure", or "draw architecture".

Discover AWS infrastructure and save to JSON. Use when user asks to "discover AWS", "explore AWS account", "scan AWS infrastructure", or "create infrastructure JSON".