cowork-skills

Wraps gsd-pi (Get Shit Done coding agent CLI) with Marcus's project constraints and coding standards so gsd tasks inherit observer pattern, no em-dashes, no Co-Authored-By, and AgenticOS event integration automatically. Use when the user says "run this with gsd", "hand this off to gsd", "use gsd-pi for this", "delegate to gsd", or wants to execute a coding task using gsd-pi as the execution engine rather than Claude Code directly. Also trigger when autonomous-workflow needs to fan out a phase to gsd-pi for execution.

Meta-skill that runs the full skill lifecycle in one command: create, eval, improve, and publish. Use when the user says "forge a skill", "create and improve a skill", "run the skill loop on X", "build and publish a skill", "skill-forge", or wants to go from idea to production-ready skill without manually chaining skill-creator and skill-self-improver. Also trigger when the user wants to combine or upgrade existing skills, write eval.json for a skill, or push skills to GitHub. Wraps skill-creator + skill-self-improver into one /skill-forge command.

Recover from interrupted AI agent coding sessions by detecting the exact interruption point, reconstructing intent from pre-written step comments, completing unfinished implementations, and validating through build + supervisor review. Use this skill whenever a user mentions session recovery, interrupted work, picking up where an agent left off, completing unfinished code, finding where a session dropped, resuming development, or anything related to detecting and finishing incomplete AI-assisted coding sessions. Also trigger when users mention Claude Code agent sessions that were cut off, lost progress, or need continuation. This skill works across all languages and frameworks — C++, C#, Python, TypeScript, Rust, Java, Go, Unreal Engine, Unity, .NET, React, Node.js. Trigger aggressively — if a user says anything about resuming, continuing, recovering, or picking up work, use this skill.

Agent state-writing protocol for the AgenticOS Command Center. Any Claude sub-agent running in a multi-agent parallel session reads this skill to participate in dashboard tracking, approval gates, and reviewer spawning.

Cross-domain protocol for supervised parallel multi-agent runs against the AgenticOS Command Center. Use whenever Marcus says "spawn parallel agents", "multi-agent task", "review agent output", "approval gate", "monitor sub-agents", "supervised pipeline", "gate the next stage", "run several agents", "watch the agents", or kicks off a session with named AGENT-01, AGENT-02 roster. Defines the AgentState contract, the approval gate handshake, the reviewer-agent pattern, and the parallel etiquette every sub-agent must follow to appear in the Command Center dashboard with no extra wiring.

Workflow automation and multi-agent orchestration tools. Use when the user mentions n8n, Langflow, claude-squad, container-use, Dagger, workflow automation, pipeline orchestration, multi-agent coordination, or wants to set up automated workflows. Also trigger for 'automate this process', 'create a workflow', 'run agents in parallel', or integration of multiple tools into a pipeline.

Spec-driven, phase-based workflow orchestration that runs projects end-to-end with minimal human intervention. Use this skill whenever the user says "run this end to end", "autonomous workflow", "execute phases", "ralph loop", "orchestrate this", or shares a project spec and wants it implemented without hand-holding. Also triggers when spec.md, phases.json, or state/workflow_state.json exist in the working directory. Extends the ralph loop with phase isolation, hybrid multi-role voting, and one-way AgenticOS event broadcasting.

Reference guide for MCP (Model Context Protocol) server integrations. Use when the user asks about setting up MCP servers, configuring Context7, Tavily, Playwright MCP, Firecrawl, Task Master AI, Codebase Memory, or any MCP server integration. Also trigger for 'how to add an MCP server', 'MCP configuration', or troubleshooting MCP connections.

Analyze, benchmark, auto-select, optimize, and track local Ollama models. Includes behavior audit, multi-model benchmarking, task-based auto-selection, speed/quality optimization, and historical scoring dashboard.

Design, test, evaluate, and optimize prompts for LLMs. Use when the user wants to write better prompts, test prompt quality, benchmark prompts across models, create evaluation suites, or mentions promptfoo, prompt testing, prompt optimization, few-shot examples, chain-of-thought, or systematic prompt improvement. Also trigger for 'help me write a prompt', 'evaluate this prompt', 'why is this prompt not working', or A/B testing prompts.

Recover from interrupted AI agent coding sessions by detecting the exact interruption point, reconstructing intent from pre-written step comments, completing unfinished implementations, and validating through build + supervisor review. Use this skill whenever a user mentions session recovery, interrupted work, picking up where an agent left off, completing unfinished code, finding where a session dropped, resuming development, or anything related to detecting and finishing incomplete AI-assisted coding sessions. Also trigger when users mention Claude Code agent sessions that were cut off, lost progress, or need continuation. This skill works across all languages and frameworks — C++, C#, Python, TypeScript, Rust, Java, Go, Unreal Engine, Unity, .NET, React, Node.js. Trigger aggressively — if a user says anything about resuming, continuing, recovering, or picking up work, use this skill.

Development workflow standards covering brainstorm-first methodology, session management, build/tooling rules, testing, version control, logging, debugging, and portfolio priorities.

Enforces enterprise-grade runtime, security, dependency, and AI-assisted coding guardrails aligned with OWASP, NIST SSDF, SLSA, and SOC2-aligned SDLC practices.

Marcus Daley's universal coding standards and critical rules for access control, initialization, communication patterns, dependencies, comments, and error handling across all languages and frameworks.

Canva design generation skill with prompt engineering, format specs, and quality review for logos, presentations, posters, and social media.

Design principles for visual output — color theory, typography, layout, accessibility. Auto-loaded for any design, Canva, or document task.

any input (code, docs, papers, images) - knowledge graph - clustered communities - HTML + JSON + audit report

Create videos programmatically using Remotion (React + TypeScript). Use when the user wants to generate videos from code, create animated presentations, motion graphics, social media clips, data visualization videos, or mentions Remotion, programmatic video, or 'video from code'. Also trigger for animated explainers, promotional videos, or any task where video is the output format and code-based generation is appropriate.

Professional document formatting for Excel, Word, PowerPoint, and PDF generation via cowork-win tools. Auto-loaded for document creation tasks.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Use this skill any time a .pptx file is involved in any way -- as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file; editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions 'deck,' 'slides,' 'presentation,' or references a .pptx filename, regardless of what they plan to do with the content afterward.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Nine best practices for keeping Unreal Engine 5 Blueprint graphs clean, readable, and maintainable. Covers DRY functions, commenting, reroute nodes, node reduction, modular components, subgraphs, variable categories, alignment tools, and productivity plugins. Use when reviewing or building Blueprint-heavy projects.

Post-code-write verification gate for Unreal Engine 5 C++ projects. Scans all modified files for known silent-failure patterns specific to this codebase (wrong SLOG macro syntax, FString::FromBool, EditAnywhere, etc.) then triggers a full UE5 build and surfaces every error/warning with file+line. Run automatically after writing any .cpp/.h file in the project.

Work with Obsidian vaults, markdown-based knowledge management, and personal knowledge systems. Use when the user mentions Obsidian, vault, wikilinks, PKM, personal knowledge management, Zettelkasten, PARA method, Maps of Content, daily notes, Dataview queries, or wants to organize notes and knowledge. Also trigger for creating knowledge base structures, linking strategies, or managing markdown-based documentation systems.

Continuous AI engineering analysis system for Alexander Vault — architecture, security, dependency, and concurrency scanners with visualization dashboard.

Comprehensive marketing skill covering CRO, copywriting, email sequences, growth engineering, launch strategy, and customer research. Use when the user needs help with marketing strategy, writing marketing copy, conversion rate optimization, landing page optimization, email campaigns, social media content, pricing strategy, launch plans, customer research, A/B testing, referral programs, or growth tactics. Trigger for any marketing-related task including writing ads, creating content calendars, analyzing funnels, or planning campaigns.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Launch and manage autonomous skill self-improvement loops using binary assertions and Karpathy-style eval-modify-test cycles. Use when the user says "improve skill", "self-improve", "run eval loop", "optimize skill", or invokes /skill-self-improver.

Advanced software development workflow patterns including test-driven development (TDD), systematic debugging, subagent-driven development, and structured code review. Use when the user mentions TDD, red-green-refactor, systematic debugging, code review process, development workflow, subagent development, parallel development, or wants to follow disciplined software engineering practices. Also trigger for 'write tests first', 'debug this systematically', 'review this code', or 'help me plan this implementation'.

6-step build verification pipeline that prevents unstable code from being pushed. Runs: build, launch runtime, 5-minute stability monitor, full test suite, independent reviewer agent analysis, and produces a final READY/NOT READY verdict. Use when pushing code, before releases, or when /build-gate is invoked.

PyQt6 visual test runner that displays real-time test execution with live progress bars, pass/fail indicators, console output, and per-test timing. Integrated with the self-improving feedback pipeline to provide recurring visual verification of all pipeline modules.

Generate an interactive React-based brainstorming wizard artifact for scoping MVPs, feature sets, project requirements, or client discovery. Use this skill whenever the user wants to brainstorm features, scope an MVP, lock decisions on a project, gather client requirements, define what's in or out of scope for a build, or capture structured feedback from a stakeholder. Trigger this even when the user uses casual phrasing like "let's figure out what to build", "I need to scope this", "help me think through features", "I'm confused on what we want", or "send this to my client to fill out". Two output modes are supported, an internal mode with gamification and live wizard flow for solo or team scoping sessions, and a client mode with a clean fillable form that exports to JSON or PDF for stakeholders to return. The skill adapts its theme to match the project's domain (game dev, military/government, research/editorial, or a custom theme defined per project) so each artifact feels native to its project rather than

Connects any Claude Code project to the AgenticOS Universal Hub — enables multi-project monitoring, iPhone approval, Ollama handoff, and skill auto-loading.

Integrate Spline 3D scenes into web, Electron, PyQt6, or React frontends. Covers scene spec authoring, variable-driven state sync, background embeds, icon/asset generation, WebGL fallback, and performance patterns. Evolves with each project — check the changelog at the bottom.

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

Autonomous research and experimentation skill inspired by Karpathy's autoresearch. Use when the user wants to run autonomous experiments, iterate on code/models overnight, benchmark configurations, or set up a self-improving experiment loop. Trigger when the user mentions 'autoresearch', 'autonomous experiments', 'overnight research', 'experiment loop', 'benchmark iterations', or wants an agent to try multiple approaches and keep what works.

Search engine optimization skill for technical SEO audits, content optimization, schema markup, site architecture analysis, and keyword strategy. Use when the user mentions SEO, search rankings, organic traffic, keyword research, meta tags, site crawlability, page speed, schema markup, search console data, backlinks, or wants to improve their website's search engine visibility. Also trigger for content optimization, title tag writing, meta description creation, and competitive SEO analysis.

Optimize context window usage, prevent context degradation, and implement memory systems for AI agents. Use when the user asks about context window management, token optimization, agent memory, context compression, multi-agent context coordination, or when working with long conversations that approach context limits. Also trigger when the user mentions 'context degradation', 'lost in the middle', 'context poisoning', attention mechanics, or needs to design memory/caching systems for AI applications.

Conduct thorough, multi-source research on any topic and produce detailed, cited reports. Use when the user asks for deep research, literature review, competitive analysis, technology evaluation, market research, or any task requiring comprehensive investigation across multiple sources. Trigger when the user says 'research this', 'deep dive into', 'investigate', 'analyze the landscape', 'compare options for', 'what are the best approaches to', or needs a thorough understanding before making a decision.