ericmjl

Guide for authoring Agent Skills with strong YAML `description` triggers, progressive disclosure, and bundled resources. Use when creating or updating a skill, running init_skill.py or package_skill.py, or improving a bland skill description so agents load the skill on the right user tasks.

Build an awesome marimo notebook that brings a research paper or dataset to life — for competitions, tutorials, demos, or blog companions. Use when asked to "make an awesome marimo notebook," "build a notebook for this paper," "create a competition submission," or pair-program an interactive research explainer on molab. Covers: what makes a notebook engaging (intuition game, real experiment, novel extension, design system), paper selection, narrative arc and proportions, custom anywidget patterns, wigglystuff CellTour, effective GPU usage, memory-efficient training (fused STE, gradient checkpointing), parallel review subagents, and a pre-publication polish checklist. CRITICAL: mo is auto-injected (import in ONE cell); every top-level name must be unique across ALL cells; custom anywidget needs model.save_changes(); use mo.output.replace() for live charts; guard all torch.cuda calls for CPU-only machines.

Create VS Code-style typewriter animation videos with mechanical keyboard sounds. Supports 4 typing speeds, ghost text autocomplete, strikethrough corrections, emoji picker, file tab switching, syntax highlighting (6 languages), Chinese IME (pinyin + direct mode), inline images, image stacks, animated checkboxes, Excalidraw hand-drawn diagrams, 8 visual themes, 4 sound packs, and A-roll narration sync. Built on Remotion (React-based video rendering). Use when the user wants to create code typing videos, explainer B-roll, or typewriter-style animations.

Create animated videos using Remotion from topics, product URLs, Google reviews, talking-head videos, CSV data, or channel/brand URLs. Supports 6 video types: educational explainers, product launch demos, testimonial/social proof, avatar video overlays, data visualization dashboards, and lower third overlays. Each follows a 2-step workflow: research/scrape/analyze then design and animate with spring animations, SVG diagrams, and count-up effects. Requires the Remotion best practices skill (install with `npx skills add remotion-dev/skills`). Use when the user asks to create a Remotion video, explainer video, educational video, product demo video, testimonial video, video with animated overlays, data visualization video, animated dashboard, lower third, transparent overlay, short-form vertical video for mobile, or multi-product video from a website.

Improve coherence in drafts through a four-pass sub-agent workflow: resolve argument conflicts, smooth section transitions, smooth paragraph transitions, and run a final coherence audit. Use when a user says things like 'make this coherent', 'tighten the flow', 'this feels choppy', 'can you smooth transitions', or asks to revise prose in Markdown, notes, essays, blog posts, emails, or docs so ideas connect cleanly without adding new points.

Break long-lived pull request branches into a mergeable stack of small PRs with clear dependency order and story flow. Use when a branch has grown too large, when the user asks to split a PR into stacked PRs, or when each PR must be reviewable in about 5 minutes while preserving logical narrative across the stack.

Use GitHub CLI (gh) for common operations like creating PRs, viewing GitHub Actions logs, managing issues, reviewing PRs, and more. When merging PRs via gh, prefer rebase merge over squash or merge commits unless repo policy or the user explicitly requests otherwise.

Use Slack CLI (`slack`) for app lifecycle and workspace operations including login/logout, create/init, run/deploy, manifest validation, trigger management, app install/uninstall, environment management, and diagnostics. Use when users ask to run or troubleshoot commands like `slack create`, `slack run`, `slack deploy`, `slack trigger`, `slack manifest`, `slack auth`, `slack activity`, `slack datastore`, `slack env`, or request help-first progressive discovery with `slack help` and `slack SUBCOMMAND --help`, plus version/documentation alignment and stale-skill refresh.

Guide for design-driven development with prescribed folder structure. New features use full workflow (HLD → LLD → EARS). Bug fixes skip doc creation but verify intent coherence.

Work inside a running marimo notebook's kernel — execute code, create cells, and build a notebook as an artifact. Use when the user wants to start a marimo notebook or work in an active marimo session.

Generate anywidget components for marimo notebooks.

Convert a Jupyter notebook (.ipynb) to a marimo notebook (.py).

Write a marimo notebook in a Python file in the right format.

Check if a marimo notebook is compatible with WebAssembly (WASM) and report any issues.

Work inside a running marimo notebook's kernel — execute code, create cells, and build a notebook as an artifact. Use when the user wants to start a marimo notebook or work in an active marimo session.

Guide for design-driven development with prescribed folder structure. New features use full workflow (HLD → LLD → EARS). Bug fixes skip doc creation but verify intent coherence.

Break unstaged or mixed changes into small, atomic, logical git commits with Conventional Commit messages. Use when the user asks to commit, stage, or split changes — e.g. 'help me commit', 'commit my changes', 'break these into logical commits', 'what should I commit first', 'stage my changes', 'commit atomically', or 'make atomic commits'. Uses git diff, git add -p, and Conventional Commits (feat:/fix:/refactor:/chore:/docs:/test:/style:/perf:/build:/ci).

Autonomous review agent that examines past conversations and extracts learning opportunities. Records observations, updates memory, creates and patches skills. Loaded by the autolearn plugin during background review cycles. Do NOT load this skill during normal conversation; it is for the autolearn-reviewer agent only.

Always-on lightweight observer. After EVERY user message, silently check: (1) did the user correct me or express a preference? (2) did the user express frustration about repetition? (3) is this a rule I've seen before in a different project? If ANY are true, run `uv run improve.py observe "<rule>" --project <name> [--domain <domain>]` to record it. Do NOT load the full skill for observation — this description is sufficient. Load the full SKILL.md body only when: checking escalation thresholds, writing to AGENTS.md, or running /improve. Manages ~/.agent-improvement/rules.yaml via improve.py CLI.

Periodic skill lifecycle management. Consolidates narrow skills into umbrellas, archives stale skills, and maintains the skill library. Intended to be run as a scheduled job via opencode-scheduler. Load this skill when running the curator.

Ensure Canvas-Chat changes update all coupled components together. Use after implementing new features, auth flows, UI controls, storage changes, or plugin wiring to verify related modules and tests are updated in sync.

Generate social media posts and blog content from local blog posts, and schedule posts to Buffer via the buffer MCP server. Use when asked to create LinkedIn posts, BlueSky posts, Substack posts, summaries, tags, or DALL-E banner images for blog posts, or to schedule/share a blog post to social media through Buffer. The banner is automatically saved as logo.webp in the blog post directory. Works with blog post slugs from content/blog/. Triggers: "generate a linkedin post", "create a bluesky post", "substack post for", "summarize this blog", "get tags for blog", "create a banner for", "schedule a post", "share my blog post", "add to buffer".

Work inside a running marimo notebook's kernel — execute code, create cells, and build a notebook as an artifact. Use when the user wants to start a marimo notebook or work in an active marimo session.

Work inside a running marimo notebook's kernel — execute code, create cells, and build a notebook as an artifact. Use when the user wants to start a marimo notebook or work in an active marimo session.

Improve coherence in drafts by diagnosing broken flow, rewriting transitions, aligning paragraph purpose, and preserving author voice. Use when a user says things like 'make this coherent', 'tighten the flow', 'this feels choppy', 'can you smooth transitions', or asks to revise prose in Markdown, notes, essays, blog posts, emails, or docs so ideas connect cleanly from sentence to sentence and section to section.