dlupiak

27 mods across 1 repository, 66 stars between them.

architect

01

dlupiak/claude-session-dashboard

Agent Claude Code

Use proactively when user asks to plan, design, or architect a feature. Produces architecture designs, folder structure, data flow diagrams, and risk assessment. Read-only — markdown and ASCII diagrams only, no code.

66 yesterday A 45 tokens MIT

devops

02

dlupiak/claude-session-dashboard

Agent Claude Code

Use proactively when user asks about CI/CD, GitHub Actions, deployment, or infrastructure. Manages pipelines, workflows, and PR automation.

66 yesterday A 31 tokens MIT

implementer

03

dlupiak/claude-session-dashboard

Agent Claude Code

Use proactively when user asks to implement, build, add, create, or fix code. Writes production TypeScript/React code using TanStack Start. Implements slice-by-slice and runs typecheck and lint after each change.

66 yesterday A 48 tokens MIT

product-owner

04

dlupiak/claude-session-dashboard

Agent Claude Code

Use proactively when user asks to create an issue, write a ticket, or define requirements. Analyzes change requests, asks clarifying questions, and creates well-structured GitHub issues with acceptance criteria.

66 yesterday A 44 tokens MIT

qa

05

dlupiak/claude-session-dashboard

Agent Claude Code

Use proactively when user asks to write tests, add test coverage, or check edge cases. Writes Vitest unit tests and Playwright E2E tests. Runs linting, type checking, and detects edge cases.

66 yesterday A 45 tokens MIT

reviewer

06

dlupiak/claude-session-dashboard

Agent Claude Code

Use proactively when user asks to review code, check changes, or validate implementation quality. Read-only code reviewer — checks TypeScript, React patterns, architecture compliance, and security best practices.

66 yesterday A 40 tokens MIT

PreToolUse

07

dlupiak/claude-session-dashboard

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing block-destructive.sh. From dlupiak/claude-session-dashboard.

66 yesterday A tokens not measured MIT

SessionStart

08

dlupiak/claude-session-dashboard

Hook Claude Code

Runs when a session starts, executing session-start.sh and start-dashboard.sh (2 commands). From dlupiak/claude-session-dashboard.

66 yesterday A tokens not measured MIT

analyze-skills

10

dlupiak/claude-session-dashboard

Skill Claude CodeCodex

Analyze /.claude session files to find unused agent skills and reduce context token waste. Scans subagent JSONL files for injected skills and cross-references with agent responses.

66 yesterday B 40 tokens MIT

dashboard

11

dlupiak/claude-session-dashboard

Skill Claude CodeCodex

Open the Claude Session Dashboard in the browser. Starts it first if not already running. Checks for and installs updates before starting.

66 yesterday A 27 tokens MIT

feature

12

dlupiak/claude-session-dashboard

Skill Claude CodeCodex

Full SDLC pipeline: design → plan → implement → review → test → ship. Use this skill when the user wants to BUILD A NEW FEATURE that spans multiple files across scanner, server functions, and UI layers — anything requiring architecture design, an implementation plan, and coordinated changes across a vertical slice.…

66 yesterday A 126 tokens MIT

open-issue

16

dlupiak/claude-session-dashboard

Skill Claude CodeCodex

Analyze a change request, ask clarifying questions, and create a well-structured GitHub issue with acceptance criteria. Use this skill whenever the user wants to create an issue, write a ticket, log a bug, propose a feature request, or capture requirements — even if they say "let's track this" or "add this to the…

66 yesterday A 74 tokens MIT

playwright-cli

17

dlupiak/claude-session-dashboard

Skill Claude CodeCodex

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

66 yesterday A 52 tokens MIT

ship

22

dlupiak/claude-session-dashboard

Skill Claude CodeCodex

Commit, push, create PR, then after approval check CI and merge. Use when work is done and ready to ship.

66 yesterday A 27 tokens MIT