Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,883 indexed, measured the same four ways as everything else here.
Production-hardened practices for building, debugging, and optimizing LLM agents with tools, streaming UI, and multi-turn sessions. Covers dual-store transcripts, artifact ownership, phase gating, orchestration tiers, failure classification, and root-cause fixes over patches. Use when designing agent loops, fixing…
Design UIs in Pencil (.pen files) and generate production code from them. Use when working with .pen files, designing screens or components in Pencil, or generating code from Pencil designs. Triggers on tasks involving Pencil, .pen files, design-to-code workflows, or UI design with the Pencil MCP tools.
The transmission-jitter-reduction skill is implemented as a modular skill-registry rather than a fixed pipeline. The markdown contract in skills/main.md describes the 6-step harness; the Python agent framework (tjr) makes that contract a dynamically-composable, schema-validated, hook-observable system. Each step is a…
This document is the canonical reference for how skills are registered, resolved, executed, and validated in the dcthermal flexible agent & skill architecture for the small-datacenter-airflow-thermal-optimization domain.
This document serves as the authoritative registry for all skills in the dex-market-manipulation-detector harness. It documents how skills are registered, resolved, executed, and validated, including input/output JSON schemas for runtime validation and automatic documentation generation.
Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn…
A document intake and completion tool for existing or unfinished design documents. It sorts requirements, database, interface, flowchart, and glossary files into a common structure and records what is missing.
Use when the user explicitly asks to search, find, retrieve, recall, compare, review stale projects, resume prior work, or answer from an Obsidian vault. Read-only: never create, update, move, or delete notes.
Layer-first retrieval from a Crystallized Intelligence for Agents brain via CLI or MCP. Use when BRAINROOT is set, brain MCP tools are available, or the user asks to query/bootstrap/expand a domain brain without loading the full corpus.
An article-rewriting skill for generative engine optimization, meaning it structures content so AI systems can understand, evaluate, quote, and recommend it more easily.
Use when: generating complete Vue 3 page code (index.vue + data.ts + modal components + api.md + pages.ts registration) from a prototype page inventory and API contract, following the current project component and API contracts. Read SKILL.md first (rules+constraints), then read the matching TPL-.md for the template…
Scaffold, set up, and work with a brmbh WordPress theme. Use when the user wants to create a new brmbh theme, set up the WordPress development environment, install dependencies, run the doctor check, add ACF blocks or custom post types, deploy, or sync the database.
Operate the SES Sender email management platform via its API or MCP tool. Use when the user wants to send emails, check sending stats, manage contacts, view email delivery details, manage scheduled tasks, or any email marketing operations. Supports both direct API calls and the "ses" MCP tool.
UX/product workflow for design-makers and consumers of existing designs. Use for making or revising mockups, screens, layouts, flows, prototypes, tokens, typography, components, design systems, live design previews, signoff, and Figma or board handoff. Also use to consume a prototype, Figma file, screenshots, or UI…
Use when creating professional PowerPoint presentations, generating slides from content/topics, or visualizing concepts into a deck with Nano Banana 2. Supports Template Cloning and AI Minting modes.
Turns vague customer requirements into a structured, visual, estimate-ready project requirement plan. Use when the user provides a product idea, customer brief, pre-sales request, BA analysis, scope definition, feature breakdown, user flow, project phases, task breakdown, estimation worksheet, Quick Blueprint, Full…
Set up Cortex by discovering the user's existing systems and generating a personalized Workflow Registry from them. Use when the user runs /cortex-init, says "set up cortex", "adopt my tools into cortex", "build my registry", or right after installing Cortex for the first time.
Hertwill dropshipping sourcing playbook for AI agents. Encodes winner heuristics (60% gross-margin floor after EU VAT and ad spend), EU-first shipping rules (prefer EU warehouses, flag CN-only, 20-27% VAT range), per-category markup bands (not a single multiplier), a category-to-niche map with seasonal calendar (Q4…
Build an on-demand RL-Kernel roadmap, dependency, gap, document-plan, and competitor radar dashboard from live GitHub evidence. Use only when the user explicitly invokes $kernel-radar or /kernel-radar, or explicitly asks to use, run, or invoke the kernel-radar skill. Do not trigger for general RL-Kernel reviews…
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: