Instructions file CodexOpenCode
Instructions for KaydenClark/LLM_Workbench, covering llm workbench - agent operating system, authority order, read scope, edit scope and work selection and lifecycle.
Instructions file CodexOpenCode
Instructions for KaydenClark/LLM_Workbench, covering llm workbench - agent operating system, authority order, read scope, edit scope and work selection and lifecycle.
Instructions file
Instructions for KaydenClark/LLM_Workbench, covering llm workbench - claude instructions and claude-specific notes.
Skill Claude CodeCodex
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Skill Claude CodeCodex
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Skill Claude CodeCodex
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
Skill Claude CodeCodex
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
Skill Claude CodeCodex
Compact the current conversation into a handoff document for another agent to pick up.
Skill Claude CodeCodex
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
Skill Claude CodeCodex
Grill me about specs for the workflows I want to build, within this workspace.
Skill Claude CodeCodex
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
Skill Claude CodeCodex
Use when you need to resolve an in-progress git merge/rebase conflict.
Skill Claude CodeCodex
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
Skill Claude CodeCodex
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
Skill Claude CodeCodex
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Skill Claude CodeCodex
Teach the user a new skill or concept, within this workspace.
Skill Claude CodeCodex
Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUSLANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".
Skill Claude CodeCodex
Plan a huge chunk of work — more than one agent session can hold — as a shared map of investigation tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
Skill Claude CodeCodex
Generate an interactive bash wizard that walks a human through a manual procedure — third-party setup, a one-off migration, an A→B state transition — opening URLs, capturing values, confirming each step, and writing .env files and GitHub Actions secrets.
Skill Claude CodeCodex
Route a situation to the smallest appropriate Workbench skill or flow.
Skill Claude CodeCodex
Review a fixed diff against repository controls and its assigned Workbench spec when a branch, change, or implementation slice needs independent review.
Skill Claude CodeCodex
Create a new greenfield project from a founding prompt using the Workbench bootstrap protocol and a private remote recovery boundary.
Skill Claude CodeCodex
A relentless interview to sharpen a plan or design.
Skill Claude CodeCodex
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Skill Claude CodeCodex
Implement one eligible Workbench ticket through verified remote recovery.