Skills and MCP tagged “engineering”

agent-harness Alireza Rezvani skill Turns a goal into tasks with machine-run checks, then keeps the loop open until each task is verified or explicitly waived. Use it for work that needs a verifiable close. Claude Code 68installs claude-coach claude-skills skill This skill teaches Claude workflows and improves prompt habits through targeted tips. Use it when you want guided practice inside Claude Code. Claude Code 50installs behuman Alireza Rezvani skill Strikes robotic habits and filler out of AI responses in personal chats. Adds an internal reflection loop so drafts sound like a real person. Claude Code 49installs agent-memory Alireza Rezvani skill Replaces bloated CLAUDE.md files with a four-tier memory store. The agent promotes facts across sessions only when they recur over multiple days. Claude Code 42installs memory-engineering Alireza Rezvani skill This skill designs and audits agent memory, prices the write path, and enforces forgetting rules. Use it when a CLAUDE.md or memory store keeps growing. Claude Code 29installs book-to-skill Alireza Rezvani skill Turns books and documentation folders into structured agent knowledge with chapter files, a glossary, patterns, and decision rules. Use it when you want an agent to apply ideas from your source files while working. Claude Code 29installs collab-proof dong7812 skill Separates Claude's actual contributions from developer actions in a coding session. Helps log architecture decisions and bug root causes directly into the repository. Claude Code 25installs skillopt-sleep Alireza Rezvani skill Runs an offline sleep cycle for your agent: reviews past sessions, replays recurring tasks, and updates CLAUDE.md or SKILL.md after validation. Claude Code 12installs deep-learning-book Alireza Rezvani skill Study companion and reference for the Goodfellow Deep Learning textbook. Indexes 20 chapters, adds a 2016-to-2026 delta layer, and diagnoses neural network training issues. Claude Code 12installs ar-resume Alireza Rezvani skill Resumes a paused autoresearch experiment in Claude Code by checking out its git branch, loading previous metric logs, and preparing the next run. Claude Code 11installs spinning-up-deep-rl Alireza Rezvani skill A deep RL knowledge base for Claude Code, covering algorithms, policy gradients, and silent bugs. Use it when building or checking RL experiments. Claude Code 8installs human-gate Alireza Rezvani skill Blocks an agent loop until a named person reviews the artifact and signs off on open issues. Claude Code 8installs minimalist Alireza Rezvani skill Stops Claude Code from over-engineering and installing unnecessary packages. It enforces a strict ladder to prioritize standard libraries and existing code. Claude Code 7installs