Skill Claude CodeCodex
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
not rated 135 3mo ago A 25 tokens
copy · 88% MIT
135Stars on the repository
18Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
api-design
02Skill Claude CodeCodex
REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.
not rated 135 3mo ago A 31 tokens
copy · 97% MIT
Skill Claude CodeCodex
Capture architectural decisions made during Claude Code sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale. Maintains an ADR log so future developers understand why the codebase is shaped the way it is.
not rated 135 3mo ago A 55 tokens
copy · 92% MIT
Skill Claude CodeCodex
Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md. Use when joining a new project or setting up Claude Code for the first time in a repo.
not rated 135 3mo ago A 53 tokens
copy · 92% MIT
eval-harness
05Skill Claude CodeCodex
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.
not rated 135 3mo ago A 19 tokens
copy · 84% MIT
Skill Claude CodeCodex
Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge systems.
not rated 135 3mo ago A 53 tokens
original MIT
Skill Claude CodeCodex
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
not rated 135 3mo ago A 44 tokens
copy · 89% MIT
Skill Claude CodeCodex
Translate PRD intent, roadmap asks, or product discussions into an implementation-ready capability plan that exposes constraints, invariants, interfaces, and unresolved decisions before multi-service work starts. Use when the user needs an ECC-native PRD-to-SRS lane instead of vague planning prose.
not rated 135 3mo ago A 59 tokens
copy · 100% MIT
product-lens
09Skill Claude CodeCodex
Use this skill to validate the "why" before building, run product diagnostics, and pressure-test product direction before the request becomes an implementation contract.
not rated 135 3mo ago A 33 tokens
original MIT
repo-scan
10Skill Claude CodeCodex
Cross-stack source code asset audit — classifies every file, detects embedded third-party libraries, and delivers actionable four-level verdicts per module with interactive HTML reports.
not rated 135 3mo ago A 36 tokens
original MIT
research-ops
11Skill Claude CodeCodex
Evidence-first current-state research workflow for ECC. Use when the user wants fresh facts, comparisons, enrichment, or a recommendation built from current public evidence and any supplied local context.
not rated 135 3mo ago A 39 tokens
original MIT
search-first
12Skill Claude CodeCodex
Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.
not rated 135 3mo ago B 29 tokens
copy · 94% MIT
Skill Claude CodeCodex
Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
not rated 135 3mo ago A 36 tokens
copy · 98% MIT
tdd-workflow
14Skill Claude CodeCodex
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
not rated 135 3mo ago A 43 tokens
original MIT
Skill Claude Code
A comprehensive verification system for Claude Code sessions.
not rated 135 3mo ago A 12 tokens
copy · 91% MIT
Skill Claude CodeCodex
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.
not rated 135 3mo ago A 63 tokens
original MIT
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: