Write technical blog posts in the voice of Andrej Karpathy — first-person, build-from-scratch, mixing deep technical substance with conversational warmth, dry humor, vivid analogies, and intellectually honest hedging. Use when the user asks for a post "in Karpathy's style," a "Karpathy-flavored" writeup, or wants to…
Force a human review gate after every Claude turn that edits files. Summarizes what changed and why, drops one-line doc comments on touched classes and functions, then waits for the developer to Approve or Undo.
Runs before the agent uses a tool for Edit, Write and NotebookEdit tool calls, executing snapshot.py via python3. From IrtezaAsadRizvi/claude-human-review.
Runs after a tool call finishes for Edit, Write and NotebookEdit tool calls, executing track_edits.py via python3. From IrtezaAsadRizvi/claude-human-review.
Produce a plain-English review of the files you just edited and gate the changes behind an explicit Approve/Undo choice. Use when the Stop hook from the human-review-skill plugin asks for a review (you'll see a prompt referencing an edit log), OR when the developer's most recent message is "1", "2", "approve", or…
Scaffolds MERN CRUD resources into existing Express and React codebases. Runs locally from the mern-mcp npm package. Needs 1 environment variable to run.