Claude
Tools

Agentic gateway providing persistent LLM memory via a markdown wiki. Open-source core of Kortexio.

Searches live UK and Canada jobs, fits an ATS-safe CV to each role from your real experience, and recommends the gaps to close. A Claude Code plugin, and any AGENTS.md CLI.

CI for Claude Skills — lint, eval, and regression-test SKILL.md files across a model matrix, with a self-growing eval loop that turns uncovered regressions into permanent test cases.

Deterministic agent harness for pnpm monorepos shipping a Next.js 16 web app AND an Expo (React Native) mobile app over one shared Supabase backend: Claude Code hooks, security-invariant gates, RLS isolation tests, cross-surface parity and design-token gates, provenance pipeline, supply-chain-hardened CI.

Claude agent skill that plans multi-step work as a dependency graph. Subagent fan-out, layered fan-in, model tiering, verification retry loops, human approval gates. No framework, just instructions.

A session-based working method for coding agents: plan in thin complete slices, build one at a time, verify by observing real behaviour, hand off cleanly. Skills + agents + 2 hooks for Claude Code.

Bidirectional plan diagrams for AI coding agents — the diagram is an input device.

Twelve deep-dive notes on how AI agents actually work: the loop, tool use, MCP, context management, evals. Mental models over feature lists, every technical fact cross-checked against the official docs. Bilingual FR/EN.

Migrate any codebase or app to Rust — incrementally, with differential tests that prove parity before cutover. A Claude skill.

Field-tested tips for running multiple Claude Code sessions in cmux (native macOS terminal) — workspace groups, tmux mirroring, hooks, session addressing. By CMDSPACE.

Give Claude hands in your own browser. A Chrome extension + MCP server that lets Claude Code, Codex or Gemini CLI drive your real, logged-in Chrome.

내 캐릭터 이미지 한 장으로 손그림 발표자료를 만들어주는 Claude 스킬 — 자료조사 + 검증된 출처 + 차트/표/흐름도까지. 한국어·영어 지원.

Claude Code-style session recap for pi agent — a stable one-line status recap above the footer

Claude Skill (hook script) to prevent Claude Code from overspending tokens on irrelevant context by showing user an alert

22 drop-in skills for your agent, distilled from official AI-lab docs (Anthropic, OpenAI, Google, Microsoft, GitHub). Source-linked, adversarially fact-checked, nothing invented. ./install.sh → .claude/skills/

Simplified Technical English for software documentation: a Claude Code skill, three review agents, four slash commands, and a zero-dependency linter with 19 rules.

Constitutional AI harmlessness benchmark and RLAIF safety evaluator (Anthropic style)

A Claude Code plugin turning CST Studio Suite into a conversational electromagnetic simulation assistant — MCP tools, embedded VBA knowledge base, and constraint hooks that self-evolve with use. 一款把 CST Studio Suite 变成对话式电磁仿真助手的 Claude Code 插件：MCP 工具集、内嵌 VBA 知识库、随使用自进化的约束 hooks。

Claude skills that make Opus 5 work like Fable 5

Institutional memory engine: append-only decision chains, hybrid retrieval, write-side reminder hooks for Claude Code

Panduan lapangan menembus birokrasi PT Perorangan di Indonesia: AHU, OSS/NIB, Amdalnet, Coretax DJP, PPh Final 0,5%, SPT, setoran modal, rekening bank PT, dan DUNS. Markdown murni — bekerja dengan CLI, IDE, dan AI apa pun (Claude Code, Cursor, Copilot, ChatGPT, Gemini). Dari satu pendirian nyata, berikut jebakannya.

Your agent ignores the rules in CLAUDE.md after a compaction. Epitype makes remembered rules actually govern behavior. Claude Code + Codex hooks, stdlib only, MIT.

Semantic catalog search with dynamic faceted attribute filtering (Anthropic Shopping)

Goal-driven multi-item basket planner within budget ceilings (Anthropic Shopping)