iris

Claude Code ecosystem expertise. Modules: CLI tool (setup, slash commands, MCP servers, hooks, plugins, CI/CD), extensibility (agents, skills, output styles creation), CLAUDE.md (project instructions, optimization). Actions: configure, troubleshoot, create, deploy, integrate, optimize Claude Code. Keywords: Claude Code, Anthropic, CLI tool, slash command, MCP server, Agent Skill, hook, plugin, CI/CD, enterprise, CLAUDE.md, agentic coding, agent, skill, output-style, SKILL.md, subagent, Task tool, project instructions, token optimization. Use when: learning Claude Code features, configuring settings, creating skills/agents/hooks, setting up MCP servers, troubleshooting issues, CI/CD integration, initializing or optimizing CLAUDE.md files.

Generates a hotfix track definition document for the jioh agent workflow system. Use when asked to create a hotfix track for a small, out-of-band task between phases. Produces a file under docs/tasks/ following the hotfix-{name}.md format and updates README.md.

Create structured implementation plans for features, refactoring, upgrades, design, architecture, or infrastructure. Generates machine-readable, deterministic plans for autonomous execution by AI agents or humans. Domains: software implementation, package upgrades, system refactoring, architecture design, infrastructure changes. Actions: create, generate, structure implementation plans. Keywords: implementation plan, technical spec, feature spec, upgrade plan, refactoring plan, architecture spec, infrastructure plan, design doc. Use when: planning new features, refactoring existing code, upgrading packages, designing architecture, documenting infrastructure changes.

Snippet newsletter Skill A — Phase 2. Interactive. Reads the latest candidates file written by /discover-oss-candidates, presents repo options to the human, writes 3 selection files (one per language), increments the issue counter. Run Saturday morning after reviewing the Friday night candidates file.

Snippet newsletter Skill A — Phase 1. Fully automated. Discovers trending OSS repos for Python, JS/TS, and C/C++, validates all repos via GitHub API, and writes a single candidates file for human review. Reads issue number from snippet/current-issue.txt. No human input required. Run on Friday nights. After reviewing the output, run /discover-oss-candidates-select to make selections.

Snippet newsletter Skill B — Phase 2. Interactive. Reads the latest snippet candidate files written by /find-snippet-candidates, presents ranked candidates to the human (all 3 languages at once), verifies selected snippet URLs via GitHub API, and appends Snippet Selections to the corresponding selection files. Run Sunday morning after reviewing the Saturday night candidate files.

Snippet newsletter Skill B — Phase 1. Fully automated. Finds the 3 latest selection files written by Skill A, spawns 6 parallel snippet-repo-explorer sub-agents (2 per language) via GitHub API, and writes 3 snippet candidate files for human review. No human input required. Run on Saturday nights. After reviewing, run /find-snippet-candidates-select to make selections.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Snippet newsletter Skill C — Phase 2. Interactive. Reads the latest review files written by /generate-snippet-draft, presents breakdowns to the human for approval, handles revision feedback, writes to drafts.json and repos.json, spawns snippet-html-generator sub-agents, and saves HTML draft files. Run Monday morning after reviewing the Sunday night review files.

Snippet newsletter Skill C — Phase 1. Fully automated. Finds the 3 latest completed selection files (with Snippet Selections), reformats snippets for mobile, researches repos, generates and self-refines breakdowns, and writes 3 review files for human approval. No human input required. Run on Sunday nights. After reviewing, run /generate-snippet-draft-select to approve and generate HTML.

Universal planning for technical and non-technical projects. Domains: software implementation, business, personal, creative, academic, events. Capabilities: feature planning, system architecture, goal setting, milestone planning, requirement breakdown, trade-off analysis, resource allocation, risk assessment. Actions: plan, architect, design, evaluate, breakdown, structure projects. Keywords: implementation plan, technical design, architecture, roadmap, project plan, strategy, goal setting, milestones, timeline, action plan, SMART goals, sprint planning, task breakdown, OKRs. Use when: planning features, designing architecture, creating roadmaps, setting goals, organizing projects, breaking down requirements.

Structured reflective problem-solving methodology. Process: decompose, analyze, hypothesize, verify, revise. Capabilities: complex problem decomposition, adaptive planning, course correction, hypothesis verification, multi-step analysis. Actions: decompose, analyze, plan, revise, verify solutions step-by-step. Keywords: sequential thinking, problem decomposition, multi-step analysis, hypothesis verification, adaptive planning, course correction, reflective thinking, step-by-step, thought sequence, dynamic adjustment, unclear scope, complex problem, structured analysis. Use when: decomposing complex problems, planning with revision capability, analyzing unclear scope, verifying hypotheses, needing course correction, solving multi-step problems.

Sets up the multi-session agent workflow coordination structure under docs/tasks/. Creates the docs/tasks/ folder, README.md (workflow rules), and UPDATES.md (handoff log). Use when starting a new round of parallel Claude Code track work.

This skill provides expert-level guidance for debugging and fixing bugs in VS Code extensions. Use when investigating runtime errors, fixing memory leaks, resolving WebView issues, debugging activation problems, fixing TypeScript type errors, or troubleshooting extension communication failures. Covers systematic debugging workflows, common bug patterns, root cause analysis, and prevention strategies.

This skill provides expert-level guidance for VS Code extension development. Use when implementing new extension features, debugging extension code, designing WebView UIs, implementing Language Server Protocol features, or optimizing extension performance. Covers activation events, contribution points, VS Code API patterns, security best practices, testing strategies, and publishing workflows.

This skill provides expert-level guidance for implementing VS Code WebView features. Use when creating WebView panels, implementing secure CSP policies, handling Extension-WebView communication, managing WebView state persistence, optimizing WebView performance, or debugging WebView rendering issues. Covers security best practices, message protocols, and VS Code-specific WebView patterns.

Generates a track definition document for the jioh agent workflow system. Use when asked to write a track doc, define a new track, or add a track to a phase. Produces a file under docs/tasks/ following the standard {phase}-track-{x}-{name}.md format.