Skill Claude Code
Author still-image infographics and figures for slide decks, talks, tutorials and papers with Remotion — the still-first, deck-matched workflow distilled from Stefano's talks (hpc-webinar, pilot-tutorial) and the mosaic reel. Use this whenever the task is "make a figure / infographic / diagram for a slide" in a…
Skill Claude Code
Look up current research information using the Parallel Chat API (core model). Use for finding papers, gathering research data, and verifying scientific information.
Skill Claude Code
Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting…
Skill Claude Code
Verification discipline for AI/agent-produced research results in computational science (CFD, HPC numerics, Fortran solvers), distilled from OpenAI's Oct-2026 math release (722 manuscripts, Lean + Comparator) and its Navier–Stokes claim. Use when: delegating a numerics/solver feature, a convergence study, a proof…
Hook Claude Code
One of 5 in settings.json
Runs when you submit a prompt, before the agent sees it, executing context-memory-guard.sh via bash. From szaghi/dotfiles.
Hook Claude Code
One of 5 in settings.json
Runs after a tool call finishes, executing context-memory-guard.sh via bash. From szaghi/dotfiles.
Hook Claude Code
One of 5 in settings.json
Runs when the agent finishes a response, executing context-memory-guard.sh via bash. From szaghi/dotfiles.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: