mtnyilmaz

57 mods across 1 repository, 6 stars between them.

web-performance

49

mtnyilmaz/agents

Skill Claude CodeCodex

Web performance expert for Core Web Vitals, bundle optimization, image optimization, lazy loading, caching, and Lighthouse audits. Use when optimizing page load times, improving LCP/CLS/FID scores, reducing bundle size, or diagnosing performance bottlenecks.

6 3mo ago A 54 tokens original MIT

executing-plans

50

mtnyilmaz/agents

Skill Claude CodeCodex

Use when you have a written implementation plan in .agents/plans/ and want to execute it in the current session with human checkpoints between batches. Use when subagents are unavailable or when the plan's tasks are tightly coupled and benefit from shared context.

6 3mo ago A 56 tokens original MIT

mtnyilmaz/agents

Skill Claude CodeCodex

Use when implementation is complete, tests pass, and you need to decide how to integrate the work — guides the completion of a development branch by verifying tests, presenting structured merge/PR/keep/discard options, executing the choice, and cleaning up the worktree.

6 3mo ago A 59 tokens original MIT

using-git-worktrees

52

mtnyilmaz/agents

Skill Claude CodeCodex

Use when starting feature work that needs isolation from the main workspace or before executing an implementation plan. Use to create a dedicated worktree on a new branch, run project setup, and verify a clean test baseline before any code changes.

6 3mo ago A 52 tokens original MIT

mtnyilmaz/agents

Skill Claude CodeCodex

Use when facing 2+ independent problems that can be worked on without shared state or sequential dependencies. Use for debugging multiple unrelated failures, investigating independent subsystems, or running parallel audits.

6 3mo ago A 44 tokens original MIT

mtnyilmaz/agents

Skill Claude CodeCodex

Use when executing an implementation plan whose tasks are mostly independent, in an environment that supports subagent dispatch. Use to delegate each task to a fresh subagent with two-stage review (spec compliance → code quality) so the main session preserves context for coordination.

6 3mo ago A 56 tokens original MIT

writing-plans

55

mtnyilmaz/agents

Skill Claude CodeCodex

Use when you have a spec or approved design and need to produce a detailed implementation plan before touching code. Use when work spans multiple files or takes more than 30 minutes. Use after methodology-spec-driven has produced an approved spec.

6 3mo ago A 53 tokens original MIT

agents AGENTS.md

56

mtnyilmaz/agents

Instructions file CodexOpenCode

Instructions for mtnyilmaz/agents, covering ai agent instructions, what this repo is, how to use, or pass --type explicitly and supported types (framework names, not tech-stack labels).

6 3mo ago A 1,811 tokens original MIT

agents CLAUDE.md

57

mtnyilmaz/agents

Instructions file

Instructions for mtnyilmaz/agents, covering claude instructions, what this repo is, how to work with this repo, installing rules into a target repo and layer order.

6 3mo ago A 580 tokens original MIT