#claude-code-skills

Free, open-source memory for Claude Code. Your own database, no cloud, no subscription.

Open-source Claude Code skills that turn one product photo into a full set of e-commerce visuals — main images, A+ detail pages, multi-angle shoots, social posts, and ad creatives. For cross-border sellers on Amazon, Shopify, TikTok Shop.

Agentic loop image generation without diffusion or autoregressive image models. Coding agents draw in p5.js, using iterative refinement and adversarial visual review for high-fidelity art and method figures. Skills for Claude Code and Codex.

AI video and image ads for marketers, built in Claude Code or Cursor and priced by a live estimate first.

Awesome Claude Code And Agent Tools

Link WhatsApp to Claude (or any MCP client) in ~20 minutes: a live self-refreshing QR page that makes pairing actually work, production patches, and 12 field gotchas. On top of @sjawhar/whatsapp-mcp.

Preserves a long-lived repository's engineering context — an architecture index, an impact map, session records, and the decisions behind them — as markdown committed beside the code, so an agent reads instead of rediscovering. Repository-local, no network, Python stdlib, MIT.

Connect Claude (or any MCP client) to your own Telegram in ~15 minutes: setup prompt for Claude Code/Codex, production patches (shared daemon, extra tools, multi-account), watchdog, and every gotcha that cost us hours. On top of chigwell/telegram-mcp.

Delegate coding work from Claude Code to a local pi agent — MCP tools with mid-run steer/abort, plus per-project discipline hooks.

Keep Claude Code working across usage limits — loop runner with a web dashboard, Telegram progress notifications, and per-round model switching

A family of branded-media plugins for Claude Code — decks, images & 2D, video, and audio, coupled by CLI capabilities (never file paths) over one shared engine.

A Claude Code plugin that shows exactly where your AI coding session wasted tokens — and how to fix it. Flags waste, never quality. Runs locally.

An autonomous Claude skill that runs high-stakes decisions through a 5-advisor council with double-blind peer review and executive synthesis ;- adapted from Karpathy's LLM Council.

Save a secret: a small window opens that Claude cannot see, you paste there, it lands in 1Password. Read it back: any item in your vault loads into Claude with one fingerprint check, names only, never the values. Keys you paste in the chat are deleted before Claude reads them. Mac, Windows, Linux. MIT.

Agent Skills that take a requirement — or a production alert — to a reviewed pull request: multi-agent TDD coding, a parallel review panel with severity-graded verdicts, living OpenSpec-compatible specs, and per-language guardrails.

Evidence-gated (Implement, Check, Control, Audit) subagentic development: maker-checker-auditor separation, mechanical Claude Code enforcement, and ~40% more reach from an expensive-model subscription.

Tested guardrail hooks and repo-hygiene skills for Claude Code. Every skill ships with an eval transcript.

Structured Thinking for Claude Code 2026 – Ask, Search, Verify Before You Build

35 个即用 Claude Code skill,每个都带离线测试 + skill-doctor 自校验 · 35 tested, self-linted Claude Code skills (中文优先)

Lightweight Claude Code skills for daily AI-assisted development workflows.

Skills that give coding agents whole-project sense — requirement discovery, controlled building, and working inside a living codebase. For Claude Code, Codex, Cursor & Gemini CLI.

QECTOR Quantum Error Correction: High-performance, mathematically verified local QEC engineering environment for Claude Code and Claude Desktop.

Skill de sécurité applicative pour agents de code IA (Claude Code, Cursor, Codex) — détection, explication, correction et scoring OWASP/ASVS.

A reusable Claude Code agent team: orchestrator + subagents, cost ledger, hooks, and hire/retire/retro skills.

A Claude Code plugin marketplace: triage a GitHub Projects board, pick the next issue, plan it, build it in a worktree, review it adversarially, ship it.

Best AI Code Architect 2026: Diagram-First Agent Orchestrator with AST Editing & Atomic Commits

Claude Code plugin marketplace: the bitranox skill collection (82 skills) plus a self-improve Stop hook. Skills invoke as /bitranox:<skill>.

AI 编程技能合集——让 Claude Code 听懂中文、帮你干活。基于 mattpocock/skills 改编并补充了原创工具。

Spec-driven development workflow for Claude Code — built around an approved design doc, where each stage waits for your approval.

A Claude Skill that writes code comments explaining why, not what, and never deletes an existing comment without asking.

Meeseeks is a Claude Code plugin. One command hands a specification to an autonomous loop that designs, builds, gates, audits and ships it - unattended - until it passes an enterprise definition of done, or the budget dies.

Engineering Graph for AI coding agents. Code intelligence, persistent memory, plans and multi-project context over MCP.

Claude Code forgets a project when you move or rename its folder. Commonbook binds its memory to the repo's git identity instead — and recovers the notes you already lost.

Claude Code plugin: one engineering process, skills that take turns, and agents that keep discovery off the main context.

Universal Expert Skill Suite & Dual-Scope Memory Engine for AI Coding Agents (Cursor, Claude Code, Windsurf, Copilot, Antigravity)

👁️ /screenshot — real Chrome screenshots for your coding agent. A Claude Code plugin: 3 skills, a visual-reviewer agent and a bundled MCP camera.

Claude Code plugin: map the human's role in a PR from the session transcripts that produced it. Developer-facing self-review.

A clearer Claude Code terminal: boxed and organized you/claude conversations, colour-coded clickable tool rows, a live status band with a timer and task info, a session panel, copy buttons, cards, alerts, readable palettes, and overall transforms Claude Code.

Agent skill (Claude Code, SKILL.md) that cuts any ad, landing page or signup to one picture, 15 words and one button, so a stranger gets it in 3 seconds.

Reusable Claude Code skills for test automation workflows