Claude
Tools

Убирает признаки ИИ из русских текстов. 40 паттернов, калибровка голоса, антиИИ-аудит.

Out-of-tree patches for the VSCode Claude Code extension — fixes for rename flip-back, fork visibility, sticky-header occlusion, parentUuid chain breaks, title resolver order, and slash-command false-positives. Reapplies cleanly across releases via structural anchors.

Claude Code skill for managing Redmine issues, time tracking, and timesheets via the Redmine MCP server. Progressive disclosure, English-only enforcement, bulk timesheet auto-fill.

Claude Code skill to generate professional voicemail greeting scripts and convert them to MP3 via Solvea's AI voice generator.

Real-time token economics and context-budget observer for agentic AI systems. A local daemon + HTTP proxy + MCP server captures every Claude API call's cost, context saturation, model breakdown, tool-use counts and burn anomalies — natively in Claude Code, Cursor, and any Anthropic SDK agent. Detects "spinning" before billing time.

Anthropic warm editorial presentation skill - HTML+PPTX dual-mode design language for Claude Code

Hierarchical codebase navigation skill for Claude Code / AI coding agents. Generates per-directory CODEMAP.md index files with structure summaries, key exports with source annotations, and large file deep analysis.

Lean signal-driven skill triage for Claude Code. Fires skills on real triggers, stays silent on noise.

Claude Code skills, hooks, and commands

Claude Code skill that scaffolds a long-running personal research project for someone with a refractory or complex chronic illness.

VS Code extension: unified GUI for AI CLI tools (Claude Code, Gemini CLI, Codex, Cursor Agent)

Local web dashboard for Claude Code (Anthropic) + Codex (OpenAI) token usage with real-time 5h/7d quotas, USD cost estimation, and per-tool/subagent/project breakdown

A Claude skill that helps founders write investor outreach that actually gets replies. Cold emails, follow-ups, due diligence prep, and more.

一个基于 Anthropic Claude 的多 Agent 代码审查与自动修复系统，核心采用 tool_use 的 Agentic Loop 架构。

站在劳动者一边的 AI 工具集 / AI tools on the side of workers. Multilingual agent skill (Claude Code · Codex · Cursor) covering workplace rhetoric, performance reviews, PIPs, salary negotiation, layoffs, and 8-jurisdiction labor law. Frameworks, not legal advice.

🛠 Claude Code skill — полный SEO-аудит магазинов на Хорошоп через API + автоматические фиксы. От Target+ Agency

Dark tech-style design system for Claude Code / Claude.ai — turns one-line requests into consistent dark-themed architecture pages, dashboards, and technical landings.

Japan regulatory MCP server — 11,601 subsidies + 6,493 laws (full-text) + 9,484 law metadata + 13,801 invoice registrants + 2,065 court decisions. 261 MCP tools. Evidence Packets (source_url + fetched_at + known_gaps). ¥3/req, 3 free/day.

Claude Code skill: adversarial cross-artifact logic & consistency audit

Model Context Protocol server for Visual Sentinel: monitor, incident, and free-tool access from Claude Desktop, Claude Code, Cline, Continue

Comprehensive testing and validation for Agent Skills. Quick, Standard, and Deep checks for structure, security, best practices, and more.

Framework and CLI tool supporting the development of LispKit programs and libraries with a GenAI-driven chat interface. For now, the framework is based on Anthropic's Claude.

A Claude Code skill that runs an end-to-end system design course — anchored to DDIA and the System Design Primer, with real-world incidents, runnable exercises, and mock interviews.

Five production-ready Claude Skill templates: one-pager writer, code reviewer, brand voice keeper, CSV cleaner, decision-doc generator. Each demonstrates a different SKILL.md pattern. Drop into Claude Code or Claude.ai. MIT licensed.