Six skills to run a sharper B2B sales process from first call to closed deal.

Claude skill for turning flat drafts into vivid public-science prose with scale, clarity, and cosmic perspective.

A Claude Code skill that gives AI assistants instant access to the complete SCS Software Modding Wiki — Documentation mirror generated from 162 pages covering ETS2 and ATS modding.

A highly professional AI fitness trainer skill for Claude Code, providing evidence-based training advice, nutrition planning, progress tracking, motivation coaching, safety guidance, and supplement recommendations.

Documenting discoveries, experiments, and lessons learned while pushing the boundaries of AI-assisted software development

Portable agent skills for Claude Code — French e-invoicing compliance (ISCA/NF525 + 2026-2027 reform), SuperPDP API integration (Factur-X/UBL/CII/EN16931/Peppol), and a generic tiered orchestration router with skill discovery.

Your AI already knows half the answers. A portable interview skill that builds your context portfolio — by AI Mates, the Australian community building with AI.

Offline deploy-safety skills for Claude Code. Zero credentials, zero network, zero dependencies.

🔄 Claude Code skill: never lose context to /clear again. Say 'wrap up' and get a 9-section structured handoff — decisions, running state, exact pickup command.

Claude Code skills for solo content creators — gameplay clips, Reels pipeline, IG captions, thumbnail A/B testing.

PR Guard: a Claude Code skill that reviews your local git diff like a Principal Engineer — and doesn't cry wolf on gitignored secrets.

Personal Claude Code plugin marketplace — portable git workflow skills (conventional commits, docs/metadata sync, changelog releases).

Write validated, paste-ready JSON-LD schema for any page, tuned for Google rich results and AI search. Current to 2026. A Claude skill by Avik Bal.

How to organize agent skills as a coherent system — stop trigger conflicts and know when to build a new skill. The systems-engineering layer Anthropic's single-skill docs don't cover.

Point a coding agent at any API's docs → client-ready assessment, sample data, and raw data landed in your warehouse (BigQuery/Snowflake/Postgres/Azure/files). A Claude Code plugin. Raw-landing only, security-first, validated.

A Claude Code skill: spend frontier-model tokens at design time, compile them into artifacts — harnesses, rubrics, evals, skills — that cheap models run at near-zero marginal cost.

Plugin marketplace for Claude Code and Claude Cowork — fresh-eyes code review agents, workflow orchestrators, and specialized skills

Discipline & quality skills for Claude Code and Codex: blind review, retrospective, architecture (less-is-more / more-is-less), no silent errors, verify the premise, pipeline verification, bugfix TDD, ADR.

Browse your AI coding-agent session history (Claude Code, Copilot, Codex, Gemini, Cursor) — every script run, why, and whether it worked — as one self-contained, local HTML page.

Multimodal LLM coaching suite for intraday trading — 3 coordinated Claude Skills over a schema-versioned journal, validated in CI.

Rewrites your Claude Code prompts before the LLM sees them — detects code, question, or text-gen intent, strips noise, adds structure. Runs automatically via a UserPromptSubmit hook, no LLM call needed for most prompts. MIT.

Streams, batch, and storage — production data pipelines, encoded.

Build and ship native and cross-platform mobile apps with Claude.

Token intelligence for Solana AI Kit powered by Tokens.xyz API v1. Equips Claude Code with canonical token data, risk scores, OHLCV charts, and curated asset lists.

A systematic 9-pass protocol for detecting and eliminating AI-generated writing patterns — for use as a Claude Project skill (or adapted for any LLM writing workflow). Named because it strips out the artificial moisture that makes AI prose feel bloated and stiff.

Hand scoped tasks to non-Claude models and get usable results back

AI code fat trim for Claude Code & Grok — measure weight, trim, verify equivalence, and benchmark.

Citations d'entités pour le référencement IA (GEO/AEO) — skill Claude adapté au Québec

⚡ Fast /my-skills catalog plugin for Claude Code — scan all installed skills, plugins & commands in seconds, not minutes

A Claude Code skill for capturing ideas and version-controlling what you ship — in plain Markdown. No database, no dependencies.

Claude Code skill for CASTEP DFT: geometry optimization, convergence testing, phonons, NEB barriers, electronic structure — with a battle-tested troubleshooting guide (the fix_com NEB trap, SCF non-convergence, PBE+U)

Universal .claude AI Project OS — a reusable, safe, copy-into-any-project Claude Code operating system (agents, skills, commands, presets, checklists, hooks, operating-capability docs).

A collection of Claude Code skills that enforce good engineering discipline — circuit-breaker (break debugging death-spirals) and measure-twice (think before coding).

From tokens to components to documentation — the complete design system workflow.

Conselho de 5 conselheiros de IA pro Claude: lentes opostas, revisão cruzada anônima e um veredito sintetizado. Método LLM Council de Andrej Karpathy.

Everything a founder needs to raise a round — from deciding the stage to wired funds.

リポジトリに置く開発者ドキュメントを、AI が作成・更新・公開するためのオープンな規格と、依存ゼロのリファレンス実装。

Product Owner skill for Claude: 16 prompts for managing a live product — health check, churn analysis, opportunity assessment, A/B testing, growth experiments, OKR planning, roadmap review, backlog grooming, pricing review, and stakeholder updates

Never finish a task without checking if you've explored your options fully.

Claude Code skill that turns YouTube links into a searchable knowledge base: captions or local Whisper, LLM-distilled summary cards with timecoded links and screenshots, topical auto-filing, hybrid RAG search, optional git sync. MIT.

Platform-agnostic AI skill: transform any project idea into a complete technical blueprint — stack, schema, API, roadmap, and risk report.

Scenes, voice, and structure — the craft of long-form storytelling.

Turn a keyword into ranked, AI-search-ready content — end to end.

Precision-first LLM code review as a scoring game — penalize false positives, reward verified bugs.

AI agent skills for Studio LXD libraries — Claude Code, Cursor, Codex/ChatGPT and generic agents (@studiolxd/scorm, @studiolxd/xapi)

Enforce architecture standards and maintainer workflows for AI coding agents to prevent code duplication, verify changes, and control project dependencies.

Claude's office presence — control surface for the office wall monitor (and future devices)

Build a test suite that actually catches bugs — and stops flaking.

Claude skill that turns any build prompt into a running agentic loop with elicitation, verification, and a publishable iteration log

A Claude Skill that coaches AI-anxious professionals from anxiety to AI-native — a 6-rung literacy ladder fusing "Open to Work" (LinkedIn) and "Agents, Robots, and Us" (McKinsey).AI 时代职场跃迁教练 Skill:沿 6 级阶梯把 AI 焦虑变成能动性,从「怕被取代」走到「新型职场人」。熔了《Open to ▎ Work》+《Agents, Robots, and Us》两本书。

Claude Code false-positive recovery — JSONL session repair + framing guards. Claude Code & Grok marketplace.

Product growth skills for Claude: diagnose where to focus your growth with a driver-tree growth map, then design the experiments to get there (ICE shortlist + top-3 portfolio). Open SKILL.md format; installable in Claude Code / Cowork.

Reference skill for NestJS — the progressive, TypeScript-first Node.js framework.

Paste a YouTube link into Claude Code and get the full transcript — instantly, locally, no API key. A Claude Code skill that uses yt-dlp + your browser cookies to reliably beat YouTube's bot checks.

Production-grade engineering discipline for AI coding agents — 5 composable skills (plan, build, secure, operate) for Claude Code, Codex & Gemini. Never skips a step, never fakes done.

Public release distribution for dmtool — the A12 Kernel document model-authoring CLI + Claude Code/Codex plugins with first-class rules support. Not an official A12/mgm artifact.

Prompt optimizer & compiler for Claude Code — intent mining, genre-aware skeletons, multi-candidate + LLM-judge eval. Text / image / video prompts (Midjourney, Seedance, Sora, Kling). 新手友好的提示词优化套件

Claude Code skills mined from 550 of my own transcripts — explain-my-app, interview-dossier, claim-scorecard, workflow-distiller. One marketplace, install what you need.

Generate an honest AI Diligence Statement for vibe-coded apps. Perform an AI transparency self-assessment that helps you build trust with your users.

EVM-first crypto token research CLI: resolves a ticker/name/address, runs on-chain + free-API collectors, and emits provenance-tracked JSON/Markdown — CPD 2.0 risk, 6-pillar quality score, holders, liquidity, locks/unlocks. Drivable directly or via two Claude Code skills.