biruk741
@biruk741
Public Skills
stack
by biruk741
Interactively select the complete technology stack for the hackathon project. Covers package manager, frontend framework, backend framework, database, ORM, styling, testing, and deployment. Considers agent-coding compatibility, documentation quality, and team familiarity. Use when the team needs to decide on technologies, when someone asks "what should we use for X", "what's the best framework for this", or "let's pick our stack". Also use mid-project if a technology choice needs to be reconsidered.
design-system
by biruk741
Create a project-specific UI component library and design tokens. Builds on top of shadcn/ui or similar component primitives, customized to match the product's aesthetic vision. Produces reusable components that all developers import for visual consistency. Use when the team needs to establish the visual language, create reusable UI components, define colors/typography/spacing, or when someone says "make it look good", "set up the design system", "create reusable components", or "define the aesthetic".
mockup
by biruk741
Generate interactive HTML/React mockups of the hackathon project. Creates clickable prototypes that can be opened in a browser to test user flows and visual concepts. Use when the team wants to visualize the product, test user flows, iterate on features, or needs a tangible artifact to discuss. Also use when someone says "show me what this looks like", "let's prototype this", "mock this up", or "build a quick UI for this".
state-manager
by biruk741
Manages the .hackathon/ state directory. Handles reading state, validating document schemas, checking phase status, and maintaining the changelog. Automatically invoked by other hackathon-pilot skills as a utility. Also use directly when you need to check or manipulate project state, fix corrupted state files, or manually transition phases.
architect
by biruk741
Design the system architecture for the hackathon project. Produces a high-level architecture document, component map, data models, API contracts, and shared TypeScript types. Use when the team needs to plan the technical structure, define how components interact, create API contracts, or establish the shared type system. Also use when someone says "how should we structure this", "what's the architecture", or "let's plan the backend/frontend split". Critical for enabling parallel development between multiple developers.
execute
by biruk741
Execute tasks from a mini-orchestrator by spawning parallel subagents in waves. Reads an orchestrator file, identifies available tasks, routes them to the right model by complexity, enforces exclusive file ownership within waves, and tracks progress in a compaction-resilient way. Pure orchestrator — never edits source files directly. Use when /start-work generates a parallel execution plan, when someone says "execute my tasks", "run the orchestrator", "batch my work", or when a developer has multiple independent tasks to parallelize.
phase-plan
by biruk741
Create a detailed, phased execution plan with tasks assigned to specific team members by role. Handles dependency mapping between tasks, identifies parallelizable work, sets gate points where work must sync, and produces per-person task boards. Use when the team is ready to start building and needs to know who does what and in what order. Also use for re-planning mid-hackathon if priorities shift.
breakdown
by biruk741
Expand each component from the architecture into detailed specifications covering both the conceptual design and technical implementation details. Produces per-component spec files. Use when the team has an architecture and needs to drill into the details of each component, when someone asks "how exactly should we build X", "what are the edge cases for Y", or "spec out this component". Also used to plan implementation tasks at the code level.
feasibility
by biruk741
Assess whether a hackathon project idea can be built within the time constraints using agentic AI coding tools. Breaks the idea into effort chunks, scores each for complexity and risk, and recommends scope adjustments. Use when the team needs a reality check on scope, when evaluating if a feature should be included, when someone asks "can we actually build this?", or when time pressure requires cutting features. Also use for re-assessment mid-hackathon if the team is falling behind.
refine
by biruk741
Finalize and lock the hackathon project idea after brainstorming, mockups, and feasibility assessment. Produces the definitive IDEA-FINAL.md that all subsequent phases reference. Use when the team is ready to commit to the final idea, after feasibility has been assessed, or when someone says "let's lock this in", "finalize the idea", or "we're going with this".
demo-prep
by biruk741
Finalize the hackathon demo presentation. Refines the demo script, identifies the most impressive moments, creates a fallback plan, helps with pitch structure, and times the presentation. Use when preparing for the final demo, when someone says "let's prepare the demo", "practice the pitch", "what should we show", or anytime the demo script needs updating. This skill can be used throughout the hackathon, not just at the end.
ideate
by biruk741
Structured brainstorming and idea development for hackathon projects. Guides the team through problem definition, solution framing, demo visualization, and scope scoping. Use when the team needs to develop, refine, or evaluate a hackathon project idea. Also use when someone says "let's brainstorm", "what should we build", "help me think through this idea", or needs to evaluate multiple competing ideas.
scaffold
by biruk741
Initialize and scaffold the complete monorepo project structure based on the technology stack and architecture decisions. Sets up the frontend, backend, shared packages, configuration, dev scripts, and a working hello-world across the full stack. Use when the team is ready to start coding and the stack and architecture are decided. Also use when someone says "set up the project", "scaffold this", "initialize the repo", or "let's start building". This skill creates a production-quality project foundation, not just boilerplate.
deploy
by biruk741
Deploy the hackathon project to a hosting platform. Handles frontend deployment, backend deployment, database provisioning, environment variables, and domain setup. Use when the team is ready to make the project accessible via URL, when someone says "deploy this", "make it live", "put it online", or when preparing for the final demo. Should not be run before there's something to deploy — running on scaffold alone is only useful for verifying the deployment pipeline works.
plan
by biruk741
Plan a complex coding task with adversarial review. Explores the codebase, asks clarifying questions, drafts a plan, then iterates with Codex for adversarial review against 10 quality criteria. Falls back to Claude-only if Codex unavailable. Does NOT create files — use /parallelize after.
adversarial-review
by biruk741
Run adversarial review on a plan or document via Codex. Sends the document to Codex (gpt-5.3-codex, xhigh reasoning) in the background, shows the user what was sent, pre-validates while waiting, evaluates feedback, and iterates up to 5 rounds. Usable standalone or referenced by /plan.
optimize
by biruk741
Optimize your AI documentation and workflow configuration. Runs a documentation quality audit, then analyzes your project for productivity improvements across Claude Code, Cursor, and Codex CLI. Suggests context management, subagent delegation, rule organization, exclusion files, memory optimization, and tool-specific improvements. Use when you want to get the most out of your AI coding tools. Triggers on "optimize", "improve workflow", "optimize docs", "productivity", "optimize AI setup".
update
by biruk741
Incrementally update AI documentation. Two modes — (1) add a new concept with the right doc types for each agent, (2) propagate a concept change across all existing AI docs. Use when you need to add, change, or remove a specific convention, rule, or pattern across your documentation. Triggers on "update docs", "change rule", "add convention", "propagate change", "update documentation".
scaffold
by biruk741
Quickly scaffold a single AI documentation file. Creates a skill, rule, agent, hook, command, plugin manifest, or config file with smart defaults and proper frontmatter. Use when you need to add one specific doc type rather than a full setup. Triggers on "create skill", "add rule", "scaffold agent", "new hook", "create command".
generate
by biruk741
Generate AI documentation for your project. Analyzes project structure, asks targeted questions, suggests optimal documentation types for Claude Code, Cursor, and/or Codex, then generates everything including config files. Use when setting up AI docs for a new project, expanding coverage, or adding support for additional agents. Triggers on "generate docs", "create AI documentation", "set up CLAUDE.md", "create AGENTS.md", "add cursor rules".
audit
by biruk741
Audit existing AI documentation in your project. Scans for Claude Code, Cursor, and Codex docs, reports quality scores, missing recommended files, sync drift between agents, and stale content. Use when you want to improve your AI docs or check documentation health.
reference
by biruk741
Look up any AI documentation concept, syntax, frontmatter field, or best practice. Covers Claude Code, Cursor, and Codex CLI comprehensively. Use when you need quick answers about AI doc formats, frontmatter fields, hook events, permission patterns, or any other AI documentation concept.
sync
by biruk741
Synchronize AI documentation across Claude Code, Cursor, and Codex. Detects drift between equivalent files and brings them into alignment while respecting each tool's format requirements. Use after updating docs for one agent to propagate changes to others.
migrate
by biruk741
Migrate AI documentation between formats. Converts .cursorrules to MDC, monolithic CLAUDE.md to modular rules, creates AGENTS.md from existing docs, and more. Use when adopting a new agent tool or upgrading doc format.
parallelize
by biruk741
Decompose a converged plan into parallel execution phases. Generates PLAN.md and ORCHESTRATOR.md files with wave assignments, complexity tiers, and dependency graphs. Must be run after /plan when alignment is reached.
verify
by biruk741
Run comprehensive validation against a completed plan. Checks each phase's implementation against PLAN.md requirements, then runs project-wide tests, lint, and type checks.
execute
by biruk741
Execute phases from an orchestrator document by spawning parallel subagents. Reads the orchestrator, identifies available phases, and coordinates wave-based parallel execution. Pure orchestrator — never edits source files.
structured-logging
by biruk741
Zero-dependency structured log format with timestamps. Optimized for grep, supports high-volume apps.
hypothesis-tracker
by biruk741
Manages debugging session state and tracks hypotheses. Prevents hypothesis cycles and maintains investigation history.
react-logging
by biruk741
React/React Native logging templates using DD structured format. For hooks, state, effects, and navigation debugging.
react-patterns
by biruk741
React and React Native bug patterns and verification conditions. Covers hooks, state, effects, navigation, and async patterns.
formal-logic
by biruk741
Formal logic inference rules for constructing and validating proofs. Use when building deductive arguments or checking proof validity.