Skill Claude CodeCodex
Authors new skills for the agent-skills repo with consistent format — tight SKILL.md, frontmatter, references for depth, and a pre-merge checklist. Use when adding a new skill to github.com/Solonnikov/agent-skills, standardizing an existing skill, or auditing a skill's structure.
Skill Claude CodeCodex
Turns one piece of content into multiple surfaces — blog post → Twitter/X thread → LinkedIn post → newsletter issue — matching each platform's conventions. Use when a user has shipped a long-form piece and wants to extract shorter variants for other channels, or is planning a content launch across multiple platforms.
Skill Claude CodeCodex
Designs decentralized apps from brief to production — user + trust-boundary mapping, contract architecture, client layer, indexing strategy, off-chain components, deployment pipeline, and ops. Use when starting a new dApp and needing a coherent plan before code, auditing an existing dApp for architectural gaps, or…
Skill Claude CodeCodex
Drafts emails in the right tone and length for the situation — cold outreach, follow-up, introduction, apology, thank-you, difficult conversation. Use when a user needs to write an email they're stuck on, rewrite an email that sounds off, or draft a template they'll reuse for similar situations.
Skill Claude CodeCodex
Scaffolds a Solidity smart contract project — Foundry-first with Hardhat alternative, OpenZeppelin-based token patterns (ERC-20/721/1155), testing, and deployment. Use when starting a new Solidity project, standardizing an existing one, adding a new contract to an existing repo, or migrating from Hardhat to Foundry…
Skill Claude CodeCodex
Ready-to-use git recipes for the operations people actually run every day — undoing mistakes, safe rebasing, resolving conflicts, rescuing lost work, and PR-friendly history cleanup. Use when a user asks how to undo a git operation, clean up a branch before merging, recover from a bad push, or make a branch PR-ready.
Skill Claude CodeCodex
Verifies a deployed Solidity contract on Etherscan (or any Etherscan-compatible explorer) via Hardhat's hardhat-verify plugin, with a manual Etherscan V2 API fallback for cases where the plugin fails. Use when a contract deploy needs verification, when automated verify fails with ABI/constructor/linking errors, or…
Skill Claude CodeCodex
Produces meeting notes that capture decisions and action items — not transcription. Attendees, agenda, decisions, action items with owners and deadlines. Use when a user needs notes from a meeting that's about to happen, is happening, or just ended, or wants a template for recurring meetings.
Skill Claude CodeCodex
Scaffolds a complete NgRx feature module (actions, reducer, effects, selectors, facade, models, tests) using modern Angular patterns. Use when adding a new feature slice to an Angular + NgRx app, standardizing existing ad-hoc state code, or bootstrapping state for a new library in an Nx monorepo.
Skill Claude CodeCodex
Structures prompts for LLM applications — role usage, delimiters, chain-of-thought, few-shot examples, structured output, prompt caching, and when to stop tuning and reach for RAG or fine-tuning instead. Use when building an LLM feature, rewriting a flaky prompt, moving from a prototype to production, or reviewing…
Skill Claude CodeCodex
Copy-ready regex patterns for the 20 strings people actually match every day — emails, URLs, UUIDs, semver, IPs, dates, line-level patterns — plus the building blocks, language-specific pitfalls, and debugging workflow. Use when a user asks for a regex for a common string format, needs to extract or validate…
Skill Claude CodeCodex
Integrates @reown/appkit multi-chain wallet connections (EVM via wagmi, Solana, Bitcoin) into a web app — initialization, network configuration, connection state, and transaction flows. Use when adding wallet connect support to a new app, extending an existing app to a new chain family, or standardizing wallet state…
Skill Claude CodeCodex
Produces research briefs that answer a question — sources, synthesis, gaps, recommendation — rather than summaries that describe a topic. Use when a user needs to research a decision, investigate a market or tool, understand an unfamiliar domain quickly, or present findings to a stakeholder who wants an answer, not a…
Skill Claude CodeCodex
Tailors a résumé to a specific job description — parses the JD for priorities, reorders and rewrites bullets to match, quantifies achievements, and passes ATS filters. Use when a user is applying to a specific role and wants their résumé to match the JD, or when their bullets are weak ("responsible for...") and need…
Skill Claude CodeCodex
Scaffolds a Solana on-chain program with Anchor — workspace setup, PDA patterns, dual SOL/SPL token support, constraint-driven validation, on-chain randomness via SlotHashes, testing with the TypeScript Anchor client, and mainnet deployment. Use when starting a new Solana program, adding a new instruction to an…
Skill Claude CodeCodex
Implements Stripe subscription flows end-to-end — checkout, webhook-driven state sync, cancellation, tier downgrades, and testing. Use when adding paid subscriptions to a new app, migrating from another billing system, or hardening an existing subscription flow that has drifted out of sync with Stripe.
Skill Claude CodeCodex
Audits and implements the technical SEO basics any modern web app should ship with — metadata, structured data, crawlability, Core Web Vitals, and international targeting. Use when launching a new site, auditing an existing one, or reviewing a PR that touches routing, rendering, or head tags.
Skill Claude CodeCodex
Reads, writes, and watches EVM smart contracts using wagmi v2 with typed ABIs — simulate/write/receipt pattern, event subscription, and chain-aware error handling. Use when integrating a contract into a frontend, adding a new write flow, extending read calls, or hardening an existing contract interaction against…
Skill Claude CodeCodex
Tightens prose — removes fluff, varies sentence length, prefers concrete verbs, matches a target voice. Use when a user wants to edit or rewrite a draft (email, post, README, memo), when copy reads "AI-generated" and needs to sound human, or when matching a specific writer's voice.
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: