Evalkit
claudeEvaluate and compare skills and models with static reviews and worktree-isolated coding-task harnesses. Host-adaptive across Claude Code and GitHub Copilot CLI.
7 skills · 1 agent
Compare instructions, MCP servers, skills, and plugins across the Claude Code, Codex, and Copilot CLI agents installed on one machine, with fixes only on request.
Plugin agent-parity from marketplace tashtit in tashtit/marketplace. Commands read from the repo's manifest — yesterday.
agent-parityCompare the configuration of the AI coding agents installed on this machine — Claude Code, OpenAI Codex CLI, and GitHub Copilot CLI — across shared instructions (CLAUDE.md, AGENTS.md, copilot-instructions.md), MCP servers, personal skills, and installed plugins, and report per-dimension gaps with a
parity-instructionsCompare the agent-parity managed instructions block across the installed AI coding agents — global ~/.claude/CLAUDE.md, ~/.codex/AGENTS.md, and ~/.copilot/copilot-instructions.md, plus CLAUDE.md and AGENTS.md at a repository root — and report each file as in sync, out of date, or not applied against
parity-mcpCompare MCP server definitions across the AI coding agents installed on this machine — ~/.claude.json (user and per-project entries) for Claude Code, the [mcp_servers.*] tables in ~/.codex/config.toml, and ~/.copilot/mcp-config.json, with repository .mcp.json listed — and report each server as prese
parity-pluginsCompare installed plugins, their versions and enablement, and registered plugin marketplaces across Claude Code, Codex CLI, and Copilot CLI from their config homes, and report each plugin per agent as installed, differs, disabled, missing, or excluded. Use when asked which agent is missing a plugin
parity-skillsCompare personal skill directories across the AI coding agents installed on this machine — ~/.claude/skills, ~/.codex/skills, ~/.copilot/skills, the shared ~/.agents/skills, and .claude/skills, .agents/skills, or .github/skills at a repository root — by directory name and file fingerprint, and repor
Evaluate and compare skills and models with static reviews and worktree-isolated coding-task harnesses. Host-adaptive across Claude Code and GitHub Copilot CLI.
7 skills · 1 agent
Evaluate repository maturity for Dockerfiles, npm projects, repository hygiene, and CI workflows, with fixes only on request.
5 skills
Mock system design interviews against cited pattern references, plus an extractor for named articles and saved HTML. Enable after an implementation is built.
3 skills
Audit-first GitHub repository governance with a safe path to apply merge policy and rulesets.
3 skills
Standards for asynchronous REST APIs and versioned deprecation.
1 skill
Standards for C4 system context and container architecture diagrams.
1 skill
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
8 skills · 1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.