Code Generation skills

Dwsy/agent

Skill Claude CodeCodex

A skill for creating, editing, and benchmarking Pi skills stored in SKILL.md files. Benchmarking means testing a skill against examples to measure and improve its behavior.

DarrenBenson/sdlc-studio

Skill Claude Code

The antidote to vibe coding: a full software engineering team at your fingertips. Create or reverse-engineer PRDs, TRDs, personas, epics, and user stories with acceptance criteria, then plan, implement, test, and verify code against them - plus an autonomous Goal-Driven sprint loop that drives a prioritised batch to a…

ursazoo/lanhu-to-code

Skill Claude CodeCodex

Lanhu to Code workflow for Claude Code. Convert Lanhu design URLs into Vue/React frontend code with component reuse, design token mapping, TODO-safe business logic, and optional code review.

EpisodeYu/HarnessSmith

Skill Claude CodeCodex

Read complex or JavaScript-rendered web pages cleanly. When a plain URL fetch returns an empty shell, garbled HTML, or "enable JavaScript", re-fetch the page through Jina Reader (https://r.jina.ai/) to get rendered, LLM-ready Markdown. Keyless, no setup. Use whenever a fetched page looks broken or you need the real…

zuoyebang/aiweave

Skill Claude Code needs its repo

A documentation audit tool that compares project documents with the code and checks several linked records, such as routes, database models, and service methods. It also scans selected rules and configuration areas for omissions or unsafe patterns.

sabir-gbs/the-polyglot-protocol

Skill Claude CodeCodex

Use when generating, reviewing, refactoring, or planning code in polyglot repositories and you need senior-engineer guidance for language choice, architecture, testing, security, performance, dependencies, concurrency, CPU/GPU use, release safety, and LLM coding guardrails.

CodeForUsers/odoo-dev-superskill

Skill Claude CodeCodex

Expert guide for creating, reviewing, refactoring, and migrating Odoo modules in versions 16.0, 17.0, 18.0, 19.0, and 20.0, strictly following OCA Guidelines and Odoo 20 official house rules. Use it when the user mentions: creating an Odoo module, inheriting models or views, writing security (ACL/ir.rule), migrating…

ofux/lauren

Skill Claude CodeCodex

Use this skill when the user wants to plan a piece of implementation work and add it to the lauren queue (the lauren todo / backlog). Typical phrasings include "add this to lauren", "add this to the lauren todo", "lauren this", "let's make a lauren plan for X", or "plan this with lauren". The plan is then executed…

instantcms-dev/instantcms-mcp

Skill Claude CodeCodex

Build or modify InstantCMS themes, template overrides, layout schemes, widget positions, and frontend/backend templates.

goadesign/goa-ai

Skill Claude CodeCodex

Use when designing or reviewing the tools an LLM agent will call — choosing tool boundaries, argument and result shapes, retrieval/search/get decompositions, MCP or goa-ai toolset surfaces — or when an agent misuses existing tools (wrong tool picked, IDs carried between calls, wrong dates computed, confident answers…

husniadil/fastmcp-builder

Skill Claude CodeCodex

Build production-ready MCP servers using FastMCP framework with proven patterns for tools, resources, prompts, OAuth authentication, and comprehensive testing. Use this when creating FastMCP-based MCP servers with features like Google OAuth, multiple resource types, testing with FastMCP Client, or complex tool…

pradeepmouli/skillit

Skill Claude CodeCodex

Documentation conventions for generating high-quality AI agent skills from TypeScript source. Use when preparing a library for skill generation, auditing JSDoc quality, fixing audit warnings, writing @useWhen/@avoidWhen/@never tags, or asking about documentation conventions for skills. Use this even if the user just…

Kimyongari/harness-factory

Skill Claude CodeCodex

Use when asked to review code. Triggers - "look at this PR", "review this diff", "safe to merge?", change inspection. Input is a diff/branch/PR; output is a severity-ranked list of findings at file:line. If the job is to change code, use development.

medalsoftchina/workcopilot

Skill Claude Code

A project-workflow station that coordinates agents and skills from project setup through delivery, including requirements, design, task planning, scaffolding, and engineering workflows.

FreePeak/devagent

Skill Claude CodeCodex

Dispatch implementation tickets through the DevAgent pipeline (worktree isolation, test gates, PR delivery) from any agent session.

agent-frontier/wgm

Skill Claude CodeCodex

Autonomous build skill that turns a rough request into working software through a relentless requirements interview (grill), a persistent plan, and a Ralph-style build loop (analyze → implement → validate → review → record). Use when the user runs /wgm, or asks to build, implement, prototype, or ship a feature or app…

Aukexecutivedepartment5152/PaperOrchestra

Skill Claude CodeCodex

Pre-pipeline aggregator that scans AI agent cache directories (.claude, .cursor, .antigravity, .openclaw) or any user-specified directory for experimentation logs, extracts insights and numeric results, and formats them as PaperOrchestra-ready inputs (idea.md + experimentallog.md). TRIGGER when the user says…

planetabhi/figma-skills

Skill Claude Code

Build or edit Figma designs and components using the ( ) design system. Load alongside figma-use whenever a task targets / / products — reusing the published Variables, UI Kit, and Icons libraries (semantic tokens, text styles, effect/elevation styles, components) instead of hardcoding colors, spacing, type, or…

velimir-jankovic/apply-technical-concepts

Skill Codex

Extract technical concepts from one or more accessible videos or local video files and apply them to real repositories by auditing existing code or implementing and adapting new behavior. Use when asked to review a system against conference talks, tutorials, lectures, screen recordings, gameplay demonstrations, or…

kangwa/penny

Skill Claude Code

Plan a repository task for execution by a small local coding model, then hand the plan to the local executor over MCP. Inspect the codebase, decompose the work into self-contained sequential prompts, define deterministic eval gates, validate the manifest, and submit it for execution. Never implement the task.