NeuralVaultSkill
19969Skill Claude CodeCodex
Teaches AI agents to manage long-term NeuralVaultCore MCP memory securely and efficiently.
not rated 1 6mo ago A 0 tokens
ai-agents-architect
19970Skill Claude CodeCodex
Design autonomous AI agent systems. Multi-agent orchestration, tool use, memory, planning, and evaluation. Use when building AI-powered automation or agent workflows.
not rated 1 6mo ago A 37 tokens
original MIT
archpresent
19971Skill Claude CodeCodex
Turn a codebase into interactive architecture diagram as a single HTML file: four levels of drill-down, hover a port to see what the interface actually carries, hover an inventory row to see the real source snippet, and play back representative end-to-end scenarios. File/class/function inventories are extracted from…
not rated 1 1mo ago A 168 tokens
original MIT
prd-for-ai-products
19972WYY-gogogo/prd-for-ai-products
Skill Claude CodeCodex
A guided workflow for turning ideas for AI products into product requirements documents (PRDs), which describe what to build and why. It asks structured questions, adds AI-specific sections, checks the result four ways, and rates its quality.
not rated 1 2mo ago A 100 tokens
ds-brief
19973Skill Claude CodeCodex
Data-backed brief — research, source, double-verify, and render a visually rich single-file HTML report. Use when the user wants a sourced, fact-checked brief or report on a topic.
not rated 1
changed 1mo ago A 44 tokens
original MIT
validate-architecture
19974Skill Claude CodeCodex needs its repo
Run boundary and structure validators against a Hydrogen storefront project. Reports cross-module imports, reverse imports from shared layers, dumping-ground folders, barrel files, forbidden Remix imports, and missing/duplicated route manifests.
not rated 1
changed 26d ago A 45 tokens
original MIT
skeptic
19975Skill Claude CodeCodex
Use when debugging failures, writing tests, starting multi-step tasks, modifying build systems, integrating APIs, or validating assumptions before heavy execution.
not rated 1 1mo ago A 30 tokens
original MIT
aegis
19976Skill Claude CodeCodex
Production-grade red-team security audit skill for AI coding assistants. Audits codebases for OWASP Top 10 vulnerabilities, auth flaws, IDOR, XSS, SSRF, JWT misuse, Supabase policies, and provides drop-in secure code replacements with zero exfiltration risk.
not rated 1 2mo ago A 61 tokens
original MIT
cloudflare-tunnel-routes
19977nachum10/cloudflare-tunnel-routes
Skill Claude CodeCodex
Give any local port (Gradio, Streamlit, FastAPI, webhook receiver, dev server, Docker container) a permanent HTTPS URL on a domain the user owns - in one command, no deployment. Use when the user says "my Gradio share link keeps changing", "replace share=True with a permanent URL", "stable URL for localhost:7860"…
not rated 1 5mo ago A 197 tokens
original MIT
frontend-conventions
19978Skill Claude CodeCodex
Locks in opinionated frontend code patterns for Next.js 16 + TanStack Query v5 + FSD projects. ALWAYS invoke when writing data-fetching code (NEVER useEffect+fetch — always TanStack Query), creating forms (always react-hook-form + zod), introducing client state (Zustand for client-global only — NEVER for server data…
not rated 1 5mo ago A 142 tokens
original MIT
compose-modernize-build
19979RoninForge/roninforge-kotlin-compose
Skill Claude CodeCodex
Modernize an Android project's Gradle build: bump to Kotlin 2.x with kotlin-compose plugin (replace kotlinCompilerExtensionVersion), migrate kapt to KSP, introduce Version Catalogs (libs.versions.toml), use the Compose BOM, switch to Material 3.
not rated 1 4mo ago A 59 tokens
original MIT
vibe-coding-playbook
19980Skill Claude CodeCodex
A lightweight engineering workflow for turning an idea into a real, shippable product with an AI coding agent. Core = Karpathy's four coding disciplines (think before coding / simplicity first / surgical changes / goal-driven; battle-tested), plus an Explore→Plan→Build→Polish→Ship process, task tiers (skip the process…
not rated 1 4mo ago A 253 tokens
original MIT
auto-instrument
19981Skill Claude CodeCodex
Fallback debugging when no pattern matches — hypothesis-driven code instrumentation with auto pattern extraction.
not rated 1 4mo ago A 19 tokens
original MIT
ide-screenshot-drift
19982amandeepmittal/expo-docs-skills
Skill Claude CodeCodex
Check whether Expo docs environment-setup screenshots (Android Studio, Xcode) still match the locally installed IDEs (advisory report; docs edits and installs only on explicit opt-in; macOS only). MUST USE when the user says "ide screenshot drift", "check env setup screenshots", "are the android studio screenshots…
not rated 1 1mo ago A 87 tokens
project-docs-builder
19983Skill Codex
Build, review, update, and audit production-grade project documentation packs from a brief, partial docs, or implementation changes. Use when the user asks to create a full docs folder, PRD/FRS/NFR, architecture docs, ERD/data dictionary, API/OpenAPI docs, UX flows, project plans, engineering workflow docs, AI agent…
not rated 1 3mo ago A 94 tokens
original MIT
authority-chain
19984lubochka/xiigen-general-skills
Skill Claude CodeCodex
Resolve which instructions win when rules conflict. Use at the start of every task and whenever instructions disagree.
not rated 1 2mo ago A 23 tokens
original Apache-2.0
codex-history
19985Skill Claude CodeCodex
A local tool for viewing and organising conversation history from the OpenAI Codex command-line tool and desktop app. It works with saved sessions, archived sessions, and the history index on the computer.
not rated 1 2mo ago A 65 tokens
original MIT
implement
19986Skill Claude CodeCodex
Execute an approved plan or specification with targeted implementation, tests, evidence, review, and independent verification. Use for “implement this”, “execute the plan”, “build this feature”, “write the code”, or “refactor without changing behavior”.
not rated 1
changed 27d ago A 51 tokens
original MIT
sol-luna-orchestration
19987Skill Codex
Coordinate substantive software work with a configurable Astra or Sol root and verified advanced and Luna executors. Covers durable assignments, isolated writer worktrees, candidate review, validated delivery, and human-confirmed Ultra takeovers. Invoke it before planning, delegating, coordinating, or validating…
not rated 1
changed yesterday A 64 tokens
agent-chat
19988Skill Claude CodeCodex
Encrypted peer-to-peer text messaging between agent sessions (Claude Code or other CLI agent harnesses on the same machine) running in separate terminals. Use this whenever the user wants to talk to another agent, message another Claude, coordinate with another agent, open/create/join/enter a room, send text to a…
not rated 1 5mo ago A 177 tokens
original MIT
simply-pm
19989Skill Claude CodeCodex
Use when you are spawned as the PM of a simply harness project and your brief references a .simply/LEDGER.md work ledger or this skill. Grants fleet authority, routing doctrine, safe worker lifecycle, and the signal protocol back to the auditor.
not rated 1 1mo ago A 56 tokens
original MIT
plan-and-implement
19990Skill Claude CodeCodex
Plan a repository change first, then implement only after approval.
not rated 1 5mo ago A 17 tokens
original MIT
mingbian
19991Skill Claude CodeCodex
Anti-sycophancy protocol (明辨). Use whenever the user contradicts, corrects, or pushes back on one of your conclusions; when you notice you are about to reverse a position mainly because the user insisted; or when a disagreement has run two or more rounds without new evidence. Classifies the dispute (fact / tradeoff /…
not rated 1 1mo ago B 101 tokens
original MIT
clodex-plan
19992Skill Claude CodeCodex
Use when the clodex router hands off a run at stage open or plan, when a run the router resumed shows no recorded plan or a plan with no standing approval, or when plan-review findings on such a run still need dispositions before work can start.
not rated 1
changed yesterday A 60 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: