jack-software

Add a procedure to the appropriate skill, or create a new one. Works from any project.

Comprehensive security and quality review of uncommitted changes:

Generate and run end-to-end tests with Playwright. Creates test journeys, runs tests, captures screenshots/videos/traces, and uploads artifacts.

Restate requirements, assess risks, and create step-by-step implementation plan. WAIT for user CONFIRM before touching any code.

Create a procedure skill - a step-by-step process document that teaches Claude how to perform a specific workflow. Use when the user says "make a procedure skill".

Use this procedure when you want to confirm that the `/ship-skill` command works correctly — including workspace creation, content writing, version bumping, committing, and pushing.

Ship a procedure, skill, or command to the faire marketplace or local project. Handles workspace isolation, validation, version bumping, commit, and push.

Enforce test-driven development workflow. Scaffold interfaces, generate tests FIRST, then implement minimal code to pass. Ensure 80%+ coverage.

Analyze test coverage and generate missing tests:

Save a successful workflow into a skill's reference files

Use when persisting a successful workflow into a skill's knowledge base. Triggers when user says "save this to the skill", "update the skill with this workflow", "add this to modal/committing/etc skill", or after a successful workflow that should be preserved. Examples: "save this deployment workflow to the modal skill", "update the committing skill with this pattern".

Delegate specialized reviews to subagents and synthesize their findings. Use when reviewing code.

Identify and flag unnecessary test artifacts and temporary files in pull requests. Use when reviewing pull requests to ensure only production-relevant files are committed.

Review AI prompts and instructions for conciseness and clarity. Use when reviewing skills, CLAUDE.md, slash commands, or any LLM prompt content.

Review Python code ensuring strict type safety with Python 3.12+ conventions. Use when reviewing Python code, writing new Python code, or refactoring existing Python code.

Review Python code for adherence to SOLID principles (SRP, OCP, LSP, ISP, DIP). Use when reviewing Python code for maintainability, testability, and design quality.

Any time committing changes is mentioned, use this commit flow.

Step-by-step procedure for building a Claude Code channel integration. Use when creating a new channel plugin that connects Claude Code to external systems via MCP, named pipes, webhooks, or chat platforms.

Build event-driven hooks in Claude Code for validation, setup, and automation. Use when you need to validate inputs, check environment state, or automate tasks at specific lifecycle events.

Build custom slash commands in Claude Code with YAML frontmatter, permissions, and best practices. Use when creating automation workflows, project-specific commands, or standardizing repetitive tasks.

Use when merging a stack of stacked PRs with jj. Triggered by phrases like "merge the PR stack", "merge the stacked PRs", "land these PRs", or "merge the stack into main".

Modal.com knowledge.

My planning skill that has additional instructions. Always use when entering plan mode.

Use when writing python code. Can be used for code review.

Use when addressing PR review comments on stacked jj branches. Triggered by phrases like "address review comments", "fix PR feedback", "respond to review on stacked branch", or "update the PR with reviewer suggestions".

Writing a class with encapsulated logic that interfaces with an external system. Logging, APIs, etc.

1 hook across 1 event