KaydenClark

30 mods across 1 repository, 2 stars between them.

KaydenClark/LLM_Workbench

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.

2 4d ago A 1,731 tokens original MIT

codebase-design

03

KaydenClark/LLM_Workbench

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.

2 4d ago A 57 tokens copy · 100% MIT

design-an-interface

04

KaydenClark/LLM_Workbench

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".

2 4d ago A 43 tokens copy · 95% MIT

diagnosing-bugs

05

KaydenClark/LLM_Workbench

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.

2 4d ago A 40 tokens copy · 95% MIT

domain-modeling

06

KaydenClark/LLM_Workbench

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.

2 4d ago A 43 tokens copy · 91% MIT

handoff

07

KaydenClark/LLM_Workbench

Skill Claude CodeCodex

Compact the current conversation into a handoff document for another agent to pick up.

2 4d ago A 19 tokens copy · 88% MIT

loop-me

09

KaydenClark/LLM_Workbench

Skill Claude CodeCodex

Grill me about specs for the workflows I want to build, within this workspace.

2 4d ago A 20 tokens copy · 92% MIT

research

10

KaydenClark/LLM_Workbench

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.

2 4d ago A 49 tokens copy · 100% MIT

setup-pre-commit

12

KaydenClark/LLM_Workbench

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.

2 4d ago A 62 tokens copy · 100% MIT

KaydenClark/LLM_Workbench

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.

2 4d ago A 44 tokens copy · 91% MIT

tdd

14

KaydenClark/LLM_Workbench

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.

2 4d ago A 33 tokens copy · 95% MIT

teach

15

KaydenClark/LLM_Workbench

Skill Claude CodeCodex

Teach the user a new skill or concept, within this workspace.

2 4d ago A 15 tokens copy · 95% MIT

ubiquitous-language

16

KaydenClark/LLM_Workbench

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".

2 4d ago A 70 tokens copy · 100% MIT

wayfinder

17

KaydenClark/LLM_Workbench

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.

2 4d ago A 46 tokens copy · 88% MIT

wizard

18

KaydenClark/LLM_Workbench

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.

2 4d ago A 53 tokens copy · 100% MIT

code-review

20

KaydenClark/LLM_Workbench

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.

2 4d ago A 29 tokens original MIT

genesis

21

KaydenClark/LLM_Workbench

Skill Claude CodeCodex

Create a new greenfield project from a founding prompt using the Workbench bootstrap protocol and a private remote recovery boundary.

2 4d ago A 26 tokens original MIT

grill-me

22

KaydenClark/LLM_Workbench

Skill Claude CodeCodex

A relentless interview to sharpen a plan or design.

2 4d ago A 14 tokens copy · 100% MIT

grilling

23

KaydenClark/LLM_Workbench

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.

2 4d ago A 38 tokens original MIT

implement

24

KaydenClark/LLM_Workbench

Skill Claude CodeCodex

Implement one eligible Workbench ticket through verified remote recovery.

2 4d ago A 13 tokens original MIT