Skill Claude CodeCodex
Ultra-compressed communication mode. Slash token usage 75% by speaking like caveman while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Skill Claude CodeCodex
This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want to document a workflow as a reusable command. Essential for creating optimized, agent-executable slash commands with proper structure and best practices.
Skill Claude CodeCodex
Best practices for working with Cursor. Use when learning how to effectively use Cursor features or optimizing your workflow.
Skill Claude CodeCodex
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Skill Claude CodeCodex
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Skill Claude CodeCodex
Logging best practices focused on wide events (canonical log lines) for powerful debugging and analytics.
Skill Claude CodeCodex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Skill Claude CodeCodex
Use this skill when writing code, implementing features, refactoring, planning architecture, designing systems, reviewing code, or debugging. This skill transforms junior-level code into senior-engineer quality software through SOLID principles, TDD, clean code practices, and professional software design.
Skill Claude CodeCodex
Use when implementing any feature or bugfix, before writing implementation code.
Skill Claude CodeCodex
Builds multi-layer features as vertical end-to-end slices instead of horizontal layers. Each slice is verified before the next begins. Use when: starting any task that spans 2+ layers (DB, API, UI, tests), building CRUD features, implementing multi-step flows, decomposing features into subtasks, or planning…
Skill Claude CodeCodex
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.
Agent Cursor
A simple hello world subagent for testing and verification. This subagent demonstrates basic subagent structure and can be invoked to verify subagents work correctly.
Command Cursor
Check the diff against main and remove AI-generated slop introduced in this branch. Targets comments, defensive code, type escapes, and style inconsistencies that a human wouldn't add.
Command Cursor
This command creates a complete workflow that uses both the hello-world rule (standards) and the hello-world skill (instructions). It demonstrates how commands orchestrate rules and skills into actionable workflows.
Command Cursor
Run the full wrap-up and ship workflow: if taskmaster or beads are in use, sync tasks (file new tasks for remaining work, update or close existing tasks); ensure all quality gates pass; run deslop; then run shipit. This command orchestrates the land-the-plane skill.
Command Cursor
Fetch origin/main, rebase the current branch onto it, resolve any conflicts using the rebase-conflict-resolution skill, then push. Use when bringing a feature or bug branch up to date with main or when the user asks to "rebase onto main," "fix conflicts," or similar.
Command Cursor
Run the full flow: ensure we're on a feature/bug branch (create one if on mainline or release), stage related changes, run pre-commit, commit with a terse semantic message, push, then create a PR (or update the PR description if one already exists). This command orchestrates the ensure-feature-branch…
Cursor rule Cursor
Guidelines for using hello world artifacts. This rule establishes standards that the hello-world skill and command follow. Demonstrates how rules provide persistent guidance that skills and commands reference.
Cursor rule Cursor
Decision framework for creating artifacts. Use when analyzing patterns to determine whether to create a rule, skill, command, or subagent, and how to organize it.
Cursor rule Cursor
When creating automations (workflows that combine multiple steps), decompose into discrete skills (the 'how') then package them into commands (the 'when' and order). Do not implement multi-step automations as a single bespoke command or skill.
Cursor rule Cursor
When git commit times out because the pre-commit or git hook is still running (e.g. full test suite), retry with an extended timeout; never use --no-verify.
Cursor rule Cursor
Rules for maintaining cross-references between artifacts and documentation. Use when creating artifacts, updating documentation, or maintaining reference integrity.
Cursor rule Cursor
When working on data modeling, fixtures, seeds, migrations, or test data, default to one canonical database path that both runtime and tests use.
Cursor rule Cursor
Rules for documentation standards and keeping documentation in sync with artifacts. Use when creating or updating documentation.