IgorWarzocha

Create custom /slash commands for repetitive tasks. Use proactively for command creation, prompt automation, or workflow shortcuts. Examples: - user: "Make a /test command that runs pytest" → create command in opencode.json, set prompt to run tests with bash tool - user: "Add a /review command for PRs" → design prompt to fetch diff, analyze changes, generate review comments - user: "Automate this repetitive task" → identify pattern, create slash command with parameterized prompt - user: "Make a /deploy command" → design workflow (build, test, deploy), encode in command prompt

Generate AGENTS.md for AI agent navigation. Covers build/test commands, coding conventions, task routing, and codebase structure. Use proactively during /init workflow or when creating agent-readable repository documentation. Examples: - user: "/init" → full AI navigation AGENTS.md + skill recommendations - user: "/init basic" → minimal AGENTS.md structure only - user: "Create AGENTS.md for this repo" → assess complexity, generate navigation doc - user: "Document codebase for AI agents" → structured AGENTS.md with task routing

Generate AGENTS.md for end-user assistance. Covers setup, installation, running, and troubleshooting. Use proactively when user asks for "getting started" help or during /init user workflow. Examples: - user: "/init user" → user assistance AGENTS.md with official docs - user: "Create getting started guide" → installation + setup + troubleshooting - user: "Document how to use this repo" → user-focused AGENTS.md - user: "Help users run this software" → setup, prerequisites, usage patterns

Apply official brand colors and typography to professional artifacts. Use for presentations, reports, and documents to ensure corporate visual identity. Use proactively when a "client-ready" look-and-feel is requested. Examples: - user: "Brand this report" -> apply corporate colors and fonts - user: "Apply brand guidelines to these slides" -> update colors/fonts in XML - user: "Check if this document is on-brand" -> verify against color/font standards

Apply standardized formats for internal business communications. Use for status reports, company newsletters, FAQs, and leadership updates. Use proactively when consistency in corporate communication is required. Examples: - user: "Write a 3P update for the week" -> use Progress/Plans/Problems template - user: "Draft a company-wide announcement" -> use newsletter format - user: "Create an FAQ for the new project" -> use internal FAQ guidelines

Principles and patterns for effective collaborative work (coworking). Use for aligning agents on communication etiquette, workspace hygiene, and feedback loops. Use proactively when coordinating multi-agent workflows, managing vault hygiene, or standardizing status updates. Examples: - user: "How should we work together?" -> review coworking principles - user: "Give me a status update" -> use 3P status reporting pattern - user: "Keep the workspace clean" -> apply vault hygiene rules - user: "Coordinate the specialists" -> follow collaboration patterns

Handle spreadsheet operations (Excel/CSV) with high-fidelity modeling, financial analysis, and visual verification. Use for budget models, data dashboards, and complex formula-heavy sheets. Use proactively when zero formula errors and professional standards are required. Examples: - user: "Build an LBO model" -> create Excel with banking-standard formatting - user: "Analyze this data and create a dashboard" -> use openpyxl + artifact_tool - user: "Verify formulas in this spreadsheet" -> run recalc.py to check for errors

Handle PDF manipulation, form filling, text/table extraction, and high-fidelity generation. Use for professional PDF reports, merging documents, and automated form processing. Use proactively when visual quality and verification are critical. Examples: - user: "Fill this PDF form and verify" -> populate fields and inspect images - user: "Merge these reports and add a watermark" -> use pypdf - user: "Extract this complex table to Excel" -> use pdfplumber for layout preservation

Runs this repository's GitHub issue, branch, PR, Changesets, release, and review workflow. Use when filing or implementing issues, preparing package changes, opening or updating PRs, or handling review feedback.

Designs, audits, refactors, and packages reusable agent skills. Use for creating or improving SKILL.md files, trigger descriptions, supporting references/scripts/assets, validation, consolidation, or porting skills between agents. Not for one-off prompt edits or passive documentation with no repeatable workflow.

Audits and improves codebase architecture for safe human and agent changes. Use for structural reviews or refactors involving ownership, godfiles/functions, feature boundaries, duplication, contract or state safety, traversability, feedback loops, test fit, work decomposition, or parallel-change readiness. Not for ordinary bug fixes or feature work with no architecture concern.

Writes, audits, and maintains AGENTS.md files. Use for repository agent instructions, nested scope guidance, global or personal agent context, pruning bloated rules, or separating agent-facing instructions from README documentation.

Writes, rewrites, and reviews prose so it sounds specific, natural, and appropriate to its author and context. Use for drafting or editing product copy, docs, READMEs, emails, posts, bios, essays, UI text, and other writing; removing AI/ChatGPT, SaaS, corporate, or LinkedIn tells; preserving voice; or making prose more direct, warm, dry, blunt, clear, or human. Not for AI-detector analysis or purely mechanical proofreading with no voice work.

Controls a local Chrome-family browser through CDP. Use when a task needs rendered-page inspection or debugging, authenticated browser state, navigation, clicks, typing, or screenshots.

Runs an opinionated GitHub issue and PR workflow with gh. Use when filing or implementing issues, creating branches, pushing changes, opening or updating PRs, requesting Codex review, or handling review feedback. Repository-specific instructions override this fallback.

Designs and reviews model-facing Pi tool contracts: names, descriptions, schemas, prompt snippets/guidelines, results, errors, and truncation. Use when adding or refining tools, or improving tool selection, calls, recovery, or prompt cost.

Deprecated. Howcode now uses regular Pi SDK extensions from Pi settings/packages; do not add Howcode-only native extension snapshots or settings. Use this only as historical context when removing old dual-native-extension code.

Use when weird app/UI behavior needs live reproduction and tracing, including flicker, stale state, remounts, focus/scroll jumps, action glitches, or ordering flashes

TypeScript/JavaScript codebase hardening: maintainability, code quality, architecture cleanup, repo scoring, agent-friendly structure, godfiles, godfunctions, feature folders, DRY, type safety, traversability, feedback loops, worktrees, subagents, swarm refactors.

Runs this repo's GitHub issue and PR workflow with gh. Use when the user mentions issue numbers, PR links, or the project board, asks to pick a manageable issue, wants an issue rewritten into a proper issue, wants backlog triage or relabeling, or wants a PR opened, updated, or reviewed. Do not use for local-only git work with no GitHub issue or project flow.

Use when Igor asks to build this branch/current repo and run a disposable build version

How to add short-lived static fixtures for hard-to-reproduce UI states while tuning layout

Use when Igor says a worktree seems complete and wants a branch/worktree summary saved for later review and merging

Manage GitHub stacked pull requests with `gh stack`. Use when creating stacked diffs, splitting work into dependent PRs, pushing/submitting/syncing/rebasing a stack, checking stack status, or navigating branch layers. Do not use for ordinary single-branch PR work.

Orchestrates the creation of a full job application package. Triggers whenever the user shares a new job posting, provides a link/URL, pastes a job description or specification, or uses phrases like "apply for this job", "create application package", or "draft application". Generates CV, cover letter, and tracking files using the Candidate Profile.

Manages the application process, tracks statuses, and handles follow-up. Use after sending an application and for updates.

Automates AI briefing preparation and technology research. Use for regular updates on AI trends, tools, and models relevant to the job search.

Analyzes a job offer for fit with the Candidate's profile and recommends an application strategy. Use before considering a new job offer.

Automates collecting and analyzing job market data and trends. Use for cyclical monitoring of sectors, salaries, and skills demand.

Prepares a complete interview plan based on the Candidate Profile and company research. Use after receiving an invitation.

Conducts deep company research and creates a dossier to support applications. Use before applying, interviewing, or for cultural fit assessment.

Guided onboarding for new users. Collects reference documents, builds CANDIDATE-PROFILE.md from them, configures agents. Use for: "set up", "initialize", "get started", "configure my profile".

Use this when planning for, entering, or playing an elite or boss fight. Trigger it before pathing into hard fights, before committing combat lines in elites or bosses, when the hard fight is new or unclear and needs STS1 parallel reasoning, and after those fights when updating durable lessons.

Use this for combat turn planning and execution. Trigger it before taking combat turns, when deciding whether a turn is easy or hard, when a fight presents setup vs tempo tension, when cost changes or free-card effects appear, and whenever you need general combat heuristics that are not boss-or-elite specific.

Use this when the current screen is a merchant or when planning a shop line from map pressure, gold, deck state, relics, and potions. Trigger it before buying, before leaving a shop, and when a forced elite or boss makes the shop an immediate survival checkpoint. Shops are hard decisions, so prefer reading them with `--hard`.

Use this at the start of an act, or whenever act-level planning resets after a compaction summary or major state change. Trigger it to re-evaluate deck shape, route goals, elite readiness, and act-specific priorities.

Use this at the start of Act 1 and for Act 1 route, reward, elite, boss, and survival decisions. Trigger it on new runs, whenever Act 1 pathing changes, before Act 1 elite or boss commitments, and when documenting new Act 1 encounters.

Use this at the start of Act 2 and for Act 2 route, reward, elite, boss, and survival decisions. Trigger it when Act 2 begins, whenever Act 2 pathing changes, before Act 2 elite commitments, and when documenting new Act 2 encounters.

Use this when the current run is Ironclad. Trigger it on new runs, after automated compaction summaries, and for Ironclad card, route, shop, reward, and combat decisions.

Use this when the current screen is an event or when planning an event line from the real run state. Trigger it before choosing any event option, especially when the event offers generated cards, relics, gold-for-HP trades, removes, transforms, or branch-defining risk/value choices.

Creates OpenCode agents in project folders for opencode serve operations. Use when you need to autonomously create specialized OpenCode agents that will be used by OpenCode serve, not by Claude directly.

Creates complete OpenCode folder structures with configuration files, agents, and commands

Creates universal OpenCode orchestrator folder structure with specialized agent that can manage swarm servers via curl commands

Launch and manage OpenCode servers with simple commands, from single instances to multi-server swarms

Creates universal OpenCode orchestrator folder structure with specialized agent that can manage swarm servers via curl commands

Launch and manage OpenCode servers with simple commands, from single instances to multi-server swarms

Designs, writes, refactors, and packages agent skills. Use for new skills, SKILL.md improvements, trigger descriptions, references/scripts splits, examples, validation, or porting workflows. Not for one-off prompt tweaks, strict runbooks, or vague workflows.

Operates a Clawa home. Use when asked to create or onboard subclawas, edit Clawa config, manage pulses, maintain CLAWAS.md routing, or shape Clawa living docs.

Hardens codebases for agent-native maintainability across languages. Use when asked to audit, score, refactor, or plan cleanup for architecture, godfiles, godfunctions, feature folders, duplication, type/contract safety, traversability, feedback loops, worktrees, or subagent-friendly structure.

Runs a lightweight GitHub issue and PR workflow with gh. Use when the user asks to create or update GitHub issues, work from an issue number or PR link, create a branch, push changes, open a PR, request review, or handle PR review feedback. Repository-specific instructions override this global fallback when present.

Warms stiff internal agent docs without losing rules, paths, commands, tool names, boundaries, or facts. Use for AGENTS.md, CLAW.md, HUMAN.md, CURIOUS.md, persona cards, worker-home docs, or project instructions that feel robotic. Do not use for schemas, runbooks, API specs, or grammar-only cleanup.

Designs, writes, refactors, and packages agent skills for this workspace. Use when the user asks to create a new skill, improve an existing `SKILL.md`, tighten trigger descriptions, split heavy detail into `references/` or `scripts/`, add examples or validation, or port a workflow into a reusable skill. Do not use for one-off prompt tweaks, strict deployment runbooks, or vague workflows that are not repeatable yet.

Reproduce pi-masterplan todo selector/action UX, layout anchoring, and key behavior in another extension command.

Operate and troubleshoot OpenBrain memory through the `brain` CLI and OpenBrain HTTP API. Use when the user asks to capture thoughts, run semantic search, review recent/history, check stats/health, tune retrieval, or diagnose why memory read/write is failing.

Set up openbrain-local-convex from a cloned repository on localhost, a LAN server, or LAN client machines. Use when the user asks to install, bootstrap, deploy, repair services, validate health, or make `brain` work end-to-end without handwaving.

Refreshes the vendored Rust apply_patch source from the local Codex checkout, rebuilds the binary, and validates the package without publishing locally.

This SKILL provides detailed instructions on how to use the planning plugin tools. MUST be loaded when: Situations: - User asks to create a plan, roadmap, or break down work into steps - User mentions specs, requirements, or standards that need to be documented - User references an existing plan that needs to be read or updated - User asks to mark work as complete or done - User wants to link requirements to a plan - User references a task that matches <available_plans>

Create or update rich task/session artifacts in the local Agent Pages app. Use when the user asks for a visual proposal, options, prototype, diagram, report, review surface, or anything easier to judge/annotate than chat.