agent-prompting
Write effective prompts for Task tool sub-agents, slash commands, and system prompts. Covers Claude 4.x prompting patterns, context engineering, output format specification, and parallel delegation. Use when spawning sub-agents, creating slash commands, or writing system prompts.
AI Documentation Standards
Write AI-readable documentation using context engineering principles, nested AGENTS.md hierarchy (CLAUDE.md is a thin shim), .claude/rules/ with path-scoping, structured formats, and the litmus test. Use when writing documentation, updating docs, or optimizing existing docs.
brainstorm
Use when starting any non-trivial feature, design, or behavior change - before writing code or creating tasks. Guides collaborative design exploration through focused questioning to produce a validated spec.
MCP Integration
Set up and use MCP (Model Context Protocol) servers to extend Claude Code capabilities including PRISM semantic memory, filesystem access, and database integration. Use when setting up MCP servers, debugging MCP connections, or understanding MCP tool usage.
plasma6-panel-config
Configure KDE Plasma 6 panels, widgets, digital clock fonts, and Panel Colorizer styling. Use when modifying panel appearance, copying panel configs between monitors, fixing widget fonts, or troubleshooting Panel Colorizer not applying styles.
Python Style Standards
Python coding standards including line length (80 chars), naming conventions (snake_case, PascalCase), type hints, docstrings, exception handling, and logging patterns. Run python-code-quality script for automated checks (ruff + pyright + security). Use when writing new Python code or reviewing code quality.
ralph-loop
Use when setting up autonomous agent execution loops for a project. Takes a completed design doc and produces IMPLEMENTATION.md, PROMPT files per loop, progress trackers, cross-validation, and ralph.sh runner. Use after brainstorming/design is done, before coding starts.
receiving-code-review
Use when receiving code review feedback - before implementing suggestions, especially if feedback seems unclear or technically questionable. Requires technical verification and honest evaluation, not performative agreement.
review-initiative
Use after /breakdown-work or manual initiative creation, before running tasks. Use when initiative has 5+ tasks, multiple dependencies, or references a design document.
spec-formats
Templates for brainstorm artifacts and manifest.json. Load when using /spec.
systematic-debugging
Use when debugging any failure, bug, or unexpected behavior - especially before attempting any fix. Enforces root cause investigation before implementation to prevent fix-thrashing and symptom-masking.
test-driven-development
Use when implementing any feature, bug fix, or behavior change - before writing implementation code. Enforces strict RED-GREEN-REFACTOR cycle where tests are written and seen failing before any production code exists.
verification-before-completion
Use before claiming any task is complete, any test passes, any build succeeds, or any fix works. Prevents false completion claims by requiring fresh verification evidence before every success statement.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work correctly. Applies TDD methodology to process documentation - test with pressure scenarios, write the skill, verify compliance.