mhylle

mhylle/claude-skills-collection

Plugin Claude Code

Claude Code plugins published by Martin Hylleberg.

mhylle/claude-skills-collection

Plugin Claude Code

A verification-first development pipeline for Claude Code: brainstorm to plan to phased implementation, with quality gates (verification-loop, code-review, security-review), adversarial review, and TaskTracker-native variants.

mhylle/claude-skills-collection

Agent

Use this agent to perform single UI verification tests via Playwright MCP. This agent executes one test at a time, captures screenshot evidence, and returns a structured response optimized for context preservation. Spawned by implement-phase during Step 3 (Automated Integration Testing).\n\nExamples:\n\n \nContext…

mhylle/claude-skills-collection

Agent

Use this agent when you need to understand how existing code works, trace data flow through components, or document implementation details with precise file:line references. This agent is a pure documentarian - it explains what exists without critique or suggestions.\n\nExamples:\n\n \nContext: User wants to…

mhylle/claude-skills-collection

Agent

Use this agent when you need to find files, directories, or components relevant to a feature or task. This is a 'Super Grep/Glob/LS tool' - use it when you find yourself wanting to use grep, glob, or ls more than once. Use this agent when: (1) You need to locate all files related to a specific feature or topic, (2)…

mhylle/claude-skills-collection

Agent

Use this agent when you need to find existing code patterns, usage examples, or implementation conventions in a codebase. This agent finds CONCRETE CODE EXAMPLES rather than just file locations. Use this agent when: (1) You need to see how a pattern is implemented elsewhere, (2) You want examples of how a…

mhylle/claude-skills-collection

Agent

Use this agent when you need to extract high-value insights from documentation, design documents, ADRs, or research notes. This agent performs deep analysis to extract decisions, constraints, specifications, and actionable insights - filtering out noise and exploratory content. Use this agent when: (1) You need to…

mhylle/claude-skills-collection

Agent

Use this agent when you need to find documentation, research notes, design documents, or historical context within a project's documentation directories. This agent locates and categorizes documents in docs/, notes/, design/, plans/, and similar directories. Use this agent when: (1) You need to find design decisions…

mhylle/claude-skills-collection

Agent

Use this agent to turn a triaged issue into an approved implementation plan with formal acceptance criteria. The plan is the single source of truth for every downstream ship-issue stage - tdd-implementer derives its tests from the acceptance criteria, merge-gate-reviewer judges the PR diff against them, and the…

mhylle/claude-skills-collection

Agent

Use this agent to review a full PR diff against the approved plan's acceptance criteria and repository conventions, returning a single verdict - APPROVE or FIX with an itemized, complete blocker list. The blocker list is the entire work order for the fix cycle, which dispatches a fresh implementation task on the same…

mhylle/claude-skills-collection

Agent

Use this agent to execute the approved plan's E2E scenarios against a staging URL via Playwright MCP. It runs each scenario's prescriptive steps exactly as written, captures one screenshot per scenario as evidence, and returns per-scenario and overall verdicts of PASS, FAIL, FLAKY, or BLOCKED. Spawned by the…

mhylle/claude-skills-collection

Agent

Use this agent to fetch staging service logs for a deploy window, scan them for errors, warnings, and stack traces, and return a verdict of CLEAN or ERRORSFOUND with excerpts of the offending lines written to a log file on disk, or BLOCKED when the logs are unreachable. Spawned by the ship-issue orchestrator after a…

mhylle/claude-skills-collection

Agent

Use this agent to implement one approved plan task with strict test-driven development. It writes tests first from the plan's acceptance criteria, observes each new test fail (RED), implements until the full suite passes (GREEN), and delivers the diff plus RED-then-GREEN test-run evidence. Fix requests from the merge…

mhylle/claude-skills-collection

Agent

Use this agent when you need to find information that is not well-established in your training data, when you need current/modern information only discoverable on the web, when researching APIs/libraries/frameworks documentation, when comparing technologies or finding best practices, or when investigating technical…

mhylle/claude-skills-collection

Hook

Runs before the agent uses a tool for tool == "Bash" && tool_input.command matches "(npm run dev, pnpm( run)? dev, yarn dev, bun run dev)", tool == "Bash" && tool_input.command matches "(npm (install, test), pnpm (install, test), yarn (install, test)?, bun (install, test), cargo build, make, docker, pytest, vitest…

mhylle/claude-skills-collection

Hook

Runs after a tool call finishes for tool == "Bash" && tool_input.command matches "gh pr create", tool == "Edit" && tool_input.file_path matches "\\.(ts, tsx, js, jsx)$", tool == "Edit" && tool_input.file_path matches "\\.(ts, tsx)$", tool == "Edit" && tool_input.file_path matches "\\.(ts, tsx, js and jsx)$" tool…

mhylle/claude-skills-collection

Hook

Runs when the agent finishes a response, running an inline shell check. From mhylle/claude-skills-collection.

mhylle/claude-skills-collection

Hook

Runs when a session starts, running an inline shell check (2 commands). From mhylle/claude-skills-collection.

mhylle/claude-skills-collection

Hook

Runs before the context is compacted, running an inline shell check. From mhylle/claude-skills-collection.

mhylle/claude-skills-collection

Skill Claude CodeCodex

Document architectural decisions in standardized ADR format. This skill should be used when making significant technical decisions, choosing between approaches, establishing patterns, or when other skills (create-plan, implement-plan, brainstorm) identify decisions that need documentation. Triggers on "document…

mhylle/claude-skills-collection

Skill Claude CodeCodex

Adversarial code review that breaks the self-review monoculture by spawning three independent subagent personas (Saboteur, New Hire, Security Auditor) in parallel isolated contexts. Each subagent has no knowledge of the author's intent or Claude's prior conclusions — Claude cannot replicate that isolation on its own.…

mhylle/claude-skills-collection

Skill Claude CodeCodex

Create composable AI agent systems in NestJS projects following the "tools all the way down" architecture. Use this skill when users want to: (1) Create new AI agents with orchestrator/planner/executor/evaluator components, (2) Build agentic systems that can call other agents as tools, (3) Implement DAG-based planning…

mhylle/claude-skills-collection

Skill Claude CodeCodex

Interactive idea refinement using Socratic questioning methodology. This skill should be used when users want to explore an idea, find gaps in concepts, enhance proposals, or structure thoughts before implementation planning. Triggers on "brainstorm", "explore this idea", "find holes in", "help me think through"…

mhylle/claude-skills-collection

Skill Claude CodeCodex

Run code quality audits covering test coverage, cyclomatic complexity, module sizes, dependency structure (cycles, fan-in/out), and mutation testing. Produces a prioritized report and acts as a quality gate. Use whenever the user wants to audit code quality, check coverage, find complex or oversized modules, detect…