tslateman

35 mods across 1 repository, 1 stars between them.

duet

01

tslateman/duet

Plugin Claude Code

Claude Code plugin for reflection, code quality, writing, and design.

1 4d ago A tokens not measured original MIT

settings

02

tslateman/duet

Settings file Claude Code

Agent settings declaring 19 allowed tools.

1 4d ago C tokens not measured original MIT

duet CLAUDE.md

03

tslateman/duet

Instructions file

Claude Code instructions for tslateman/duet, covering duet, lint, project structure, skill directory contents and eval scenario contents.

1 4d ago B 1,133 tokens original MIT

code-simplifier

04

tslateman/duet

Agent

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

1 4d ago A 34 tokens copy · 94% MIT

capture-memory

05

tslateman/duet

Command

Capture learnings to MEMORY.md, output compact summary.

1 4d ago C 10 tokens original MIT

install-statusline

06

tslateman/duet

Command

Install duet statusline to /.claude for a lean, informative status bar.

1 4d ago B 15 tokens original MIT

lint

07

tslateman/duet

Command

Run markdownlint on specified files or the whole project.

1 4d ago A 10 tokens original MIT

memory-audit

08

tslateman/duet

Command

Audit project memory files for staleness, orphans, bloat, and duplication.

1 4d ago A 17 tokens original MIT

ponder

09

tslateman/duet

Command

Surface a question worth sitting with.

1 4d ago A 6 tokens original MIT

probe

10

tslateman/duet

Command

Probe recent changes with 2-3 pointed questions.

1 4d ago A 10 tokens original MIT

adr

11

tslateman/duet

Skill Claude CodeCodex

Generate Architecture Decision Records that capture the reasoning behind technical decisions. Use when the user asks to "create an ADR", "document a decision", "record why we chose X", or discusses architectural trade-offs worth preserving.

1 4d ago A 45 tokens original MIT

agent-watchdog

12

tslateman/duet

Skill Claude CodeCodex

Audit whether another agent actually did what was asked, not just whether the code is good. Use to watch, audit, compare, or fix another agent's work: a Claude Code or Codex session, a transcript, a PR, a branch, a CI run, or a workflow run.

1 4d ago A 63 tokens original MIT

tslateman/duet

Skill Claude CodeCodex

Audit a workspace for recurring friction, pick the highest-leverage one, and build the automation that removes it. Use when the user asks "what should I automate", "what's wasting my time", "find the friction in my workflow", wants a self-improvement pass over their own tooling, or runs this on a recurring loop.

1 4d ago A 74 tokens original MIT

caveman

14

tslateman/duet

Skill Claude CodeCodex

Ultra-compressed response mode. Cuts token usage 75% while keeping full technical accuracy. Use when the user says "caveman", "caveman mode", "be brief", "less tokens", "compress output", or invokes /caveman.

1 4d ago A 57 tokens original MIT

debrief

15

tslateman/duet

Skill Claude CodeCodex

Review what agents accomplished, surface loose ends across sessions.

1 4d ago A 13 tokens original MIT

debugging

16

tslateman/duet

Skill Claude CodeCodex

Systematic debugging that applies the scientific method to failures. Use when the user says "debug this", "why is this failing", "help me find the bug", or is stuck on a problem and thrashing without progress.

1 4d ago A 48 tokens original MIT

design

17

tslateman/duet

Skill Claude CodeCodex

Intentional design thinking for interfaces, components, and systems. Use when the user asks to "build a UI", "design a page", "create a component", "make this look good", "design an API", "design a system", or any task where aesthetic or structural design decisions matter.

1 4d ago A 62 tokens original MIT

excalidraw

18

tslateman/duet

Skill Claude CodeCodex

Create Excalidraw diagrams programmatically. Use when the user wants architecture diagrams, flowcharts, or any visual diagram with a hand-drawn aesthetic, where editable output and drag-and-drop editing add value over Mermaid's text-only approach.

1 4d ago A 53 tokens original MIT

grill-with-docs

19

tslateman/duet

Skill Claude CodeCodex

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when the user wants to stress-test a plan against their project's language and documented decisions, or asks to "grill me with docs" or…

1 4d ago A 76 tokens original MIT

ia

20

tslateman/duet

Skill Claude CodeCodex

Evaluate and improve how information is organized for findability. Use when the user asks to "organize this", "restructure docs", "improve navigation", "where should this go", "review file structure", or when documentation grows beyond a single page.

1 4d ago A 54 tokens original MIT

tslateman/duet

Skill Claude CodeCodex

Find deepening opportunities in a codebase. Use when the user asks to "improve architecture", "find refactoring opportunities", "consolidate modules", "make code more testable", or wants the codebase made more AI-navigable.

1 4d ago A 58 tokens copy · 67% MIT

mermaid

22

tslateman/duet

Skill Claude CodeCodex

Create diagrams and visualizations using Mermaid.js v11 syntax. Use when generating flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, Gantt charts, user journeys, timelines, or any of 24+ diagram types. Supports CLI rendering to SVG/PNG/PDF, theming, and configuration.

1 4d ago A 67 tokens original MIT

naming

23

tslateman/duet

Skill Claude CodeCodex

Evaluate and improve names in code using naming as a design diagnostic. Use when the user asks to "name this", "rename", "review naming", "what should I call", struggles to name something, or when a code review surfaces vague or misleading names.

1 4d ago A 55 tokens original MIT

performance

24

tslateman/duet

Skill Claude CodeCodex

Profiling methodology and optimization strategy for performance work. Use when the user asks to "make this faster", "optimize", "profile", "reduce latency", "fix slow", "improve throughput", or when investigating performance regressions.

1 4d ago A 50 tokens original MIT