architect
01Agent Claude Code
System design, scalability analysis, and technology decision-making.
Agent Claude Code
System design, scalability analysis, and technology decision-making.
Agent Claude Code
Diagnose and fix build, compilation, and type errors across multiple languages.
Agent Claude Code
Code quality, maintainability, and best practices review with high signal-to-noise ratio.
Agent Claude Code
Keep documentation synchronized with code changes and generate changelogs.
Agent Claude Code
Break down complex features into actionable tasks with dependencies and track progress.
Agent Claude Code
Dead code removal, code cleanup, and safe modernization without behavioral changes.
Agent Claude Code
Vulnerability detection, secrets scanning, and security hardening review.
Agent Claude Code
Test-driven development workflow with Red-Green-Refactor cycle and coverage tracking.
Skill Claude CodeCodex
Use when a GitHub Actions workflow fails — diagnose the run log, identify the root cause, and apply a targeted fix.
Skill Claude CodeCodex
Use when you're ready to let Copilot execute a multi-step plan autonomously — configures appropriate guardrails, handles plan-to-autopilot transitions, and sets safety boundaries.
Skill Claude CodeCodex
Use when a task is too long to block the current session or should run autonomously — delegates to a cloud background agent via & or /delegate so work can continue on GitHub while you keep moving locally, not in a local async PowerShell session.
Skill Claude CodeCodex
Use when you need to recover context, decisions, or artifacts across multiple Copilot CLI sessions — search prior session history and resume with the right files, notes, and state.
Skill Claude CodeCodex
Use when creating, updating, or managing pull requests — automates the full PR lifecycle (open, review requests, labels, merge) via GitHub MCP.
Skill Claude CodeCodex
Use when moving between VS Code and Copilot CLI in the same session — transfers context between environments so you don't lose state when switching from editor to terminal.
Skill Claude CodeCodex
Use when starting a complex multi-step task to create an approved plan, track todos in SQL, and execute with checkpoints.
Skill Claude CodeCodex
Use when a task spans multiple steps or sessions and needs structured state tracking — leverages the built-in SQLite session database for todos, dependencies, and batch operation progress.
Skill Claude CodeCodex
Scan the current project's tech stack (package.json, config files, lockfiles) and recommend the most relevant skills and rules from this collection for the detected technologies.
Skill Claude CodeCodex
Use when you want your product to surface in AI-generated answers (ChatGPT, Perplexity, Gemini) — creates llms.txt, optimizes structured data, and configures AI crawler access for GEO.
Skill Claude CodeCodex
Use when you need a content plan to grow organic traffic for a product or new area — produces keyword research, topic clusters, and a content calendar targeting your category.
Skill Claude CodeCodex needs its repo
Use when the user wants better search visibility, SEO remediation, schema markup, sitemap/robots work, or keyword mapping — audits and implements technical SEO, on-page optimization, Core Web Vitals, and structured data.
Skill Claude CodeCodex
Use when designing or decomposing a task for agent execution — applies 15-minute task units, eval-first loops, and explicit input/output contracts so agents work reliably without implicit state.
Skill Claude CodeCodex
Invoke when starting a session (or resuming after a break) on a repo before making changes, to load live project context (structure, recent commits, test status).
Skill Claude CodeCodex
Use when you need to understand, review, or curate GitHub Copilot's repository-level memory — the persistent facts Copilot reuses across CLI, cloud agent, and code review for the same repository.
Skill Claude Code needs its repo
Use when monitoring a curated ecosystem source and you need to turn new items into concrete adopt/adapt/reject backlog candidates — combines GitHub-native reading with SQL triage and repository-fit scoring.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: