Claude
Tools

A Rust SDK for Anthropic's Claude API that won't panic on you — no unwrap/expect/panic, denied at compile time. Typed structured output and tools derived from Rust structs, streaming, thinking, caching, batches.

六爻占卜 AI Agent 技能 + Python 排盘引擎｜纳甲·六亲·暗动·墓库·三合·应期，含完整断卦方法论与验证卦例

Claude skill: turn a script into a director's shotlist for Seedance 2.0 — an editable HTML production board with copy-ready prompts (English edition)

SaaS product hero illustrations — real UI card × line-art scene × single accent color · Claude Code Skill

Marketing skills for Claude Code: SEO audits, content strategy, CRO, launches, reporting, and copy.

Claude skill to generate & deploy Tenable Security Center Vulnerability Management and Remediation Planning dashboards and reports

Claude Code project harness v3.2.0 — commands, skills, agents, deterministic safety hooks, memory system. Bilingual docs (EN/UA).

SAGA: an open agent skill that makes any entity findable in search, described accurately by AI, and safe to act on. Works in Claude, ChatGPT, Gemini and any assistant.

Claude Skill: ISO 14971:2019 medical device risk management — risk analysis, evaluation, control, FMEA tooling, post-production surveillance

Tiny VS Code for herdr: a real editor with LSP diagnostics, autocomplete, rename and go-to-definition — plus source control, search, problems, tests, a debugger, live app preview, runtime error capture, image paste and agent diff review. 12 panels, one idempotent reversible command.

Knowledge graph builder for legal docs. Extracts clauses, detects conflicts, traces compliance. Agent skill.

A skill for AI agents that curate better daily reports — scan front pages, tape every decision, learn from feedback.

月老鳌烨风格婚恋画像匹配报告 — 一个 Agent Skill。男看钱女看脸两套算法·普通人就是 4 分·上限下限双画像·浅色单文件 HTML 落盘

Cache-friendly Claude Code configuration: environment caps, read-deny rules, and Token Optimizer hook wiring. Generic settings only.

A security baseline for vibe coding with Claude Code: a CLAUDE.md that sets the rules, plus permissions, hooks and read-only subagents that enforce the parts a long session forgets.

Claude Skill for Seedance 2.5 / 2.0 prompt engineering (ByteDance, Dreamina, Jimeng, Doubao) — 6-block formula, @reference roles, staging, AI-UGC realism layer, native audio & lip-sync, debug matrix.

Luciazero — make coding agents prove their work. Verification-first discipline for Claude Code + Codex CLI: 9-rule doctrine, 13 skills, risk-routed reviewer, fail-open hooks.

Portable Claude Code setup template: 66 skills with provenance, cost-aware model routing, git safety hooks. Adapt, don't run as-is.

Routed delivery system for coding agents: 32 skills covering requirement to release, for Claude Code, Codex, and OpenCode

A Claude Code Stop hook that makes Opus 5 explain its work in plain English. Blocks the turn from ending and injects one just-in-time instruction.

Claude skill for spec-driven development: interviews you one question at a time until your unknowns run out, then harvests and verifies real open-source components. Turns an idea — or a half-planned project — into a PRD you can build from.

Build verified extensions for DeepSeek Harness with an installable agent skill.

半调纸拼贴 B-roll 生成 skill（MiniMax H3 国内直连版）：三闸门审批，口播文稿 → 拼贴组装动画 | forked from pyang5166/gbro-collage-broll

小红书起号运营 Skill：0→1万粉的定位/爆款/节奏/变现方法论，支持 Claude Code、Claude 桌面版、Codex/Cursor 及任意聊天式 AI