johnhenry

Author data-visualization and math-visualization scenes in ecmanim — the D3-parity foundation (scales, shape generators, hierarchy layouts, force simulation, sankey/chord, contours/hexbin/topojson, dataJoin for enter/update/exit), chart mobjects (PieChart…

Author, render, and iterate on ecmanim animations (a TypeScript port of manim that renders the same Scene code in Node and the browser). This skill should be used when the user wants to create or edit a Manim-style programmatic animation with ecmanim, render…

Interchange and fidelity workflows for ecmanim — playing back real animated Lottie/Bodymovin files (`loadLottie` → `LottieMobject`, scrub-safe keyframes/masks/mattes/precomps), exporting/importing static Lottie shape JSON (`loadLottieShapes`), exporting…

Author physics visualizations in ecmanim — analytic electromagnetic fields (point charges, current loops), traveling/standing waves, paraxial thin-lens optics, rigid-body simulation (pendulum, gravity/floor drops, pluggable planck.js/@dimforge/rapier2d…

Build slide-style/presentation ecmanim scenes — automatic shared-element transforms between two mobject states (TransformMatchingAuto, identity-keyed not position-keyed, plus Scene.autoAnimateToNextSection() and the GSAP-style FLIP helper), presenter/slide…

Covers the `ecmanim` command-line tool — the render/plan/cfg/init/plugins/checkhealth subcommands, render flags (-q quality presets, -f output formats, -o output path, -t transparent, -a write_all, -n from_upto, --save_sections), the manim.config file, the…

Sequence and time ecmanim animations with the GSAP-style Timeline position grammar, drive properties with pure expression functions (wiggle/remap/ramp/compose), distribute per-element delays with stagger helpers (cycle/staggerRange/staggerGrid +…

Practical field guide for authoring ecmanim scenes — layout math that prevents clipped/off-center output, a verification discipline that catches problems before they reach the user, working layout helpers (frame geometry, measured text width, Axes centering),…

Stage N3. Deep structural analysis of skill against real usage. Verifies gaps, prunes cruft, measures baseline health. Produces structural audit that feeds REM. Front-loaded in early cycles.

Run autonomous deep sleep cycle. Loops until all skills are below 0.2 pressure or 4 cycles complete. Does not pause for input — NEVER STOP mode. Use for overnight consolidation.

Dream about a skill to find edge cases and improvements. Use when the user says 'dream about [skill]' or 'improve [skill] through dreaming'. Generates surreal scenarios and tests patches via eval loop.

Stage N1. Stochastic scanning of past conversations to gather raw memory fragments. Broad, unfocused, deliberately noisy. The only stage that touches conversation history directly.

Quick light sleep cycle on a specific skill — N1 drift scan + N2 spindle triage only, no deep analysis or dreaming. Use when user says 'nap on [skill]'.

Run a sleep cycle to consolidate and improve skills. Use when the user says 'sleep', 'run a sleep cycle', or 'consolidate skills'. Checks pressure levels and dispatches the N1→N2→N3→REM pipeline.

Show sleep pressure gauges for all tracked skills. Use when the user asks about skill health, sleep pressure, or says 'sleep status'.

Defer sleep. Accumulates debt — like hitting the snooze button. Pressure doesn't go away, it just gets masked. Use when user says 'snooze', 'not now', or 'later'.

Use this skill whenever working with `objectify` — a CLI for persistent, versioned JSON objects backed by SQLite, designed for LLM agent use. Trigger this skill when the user asks to create, read, update, inspect, fork, or rewind objectify objects; write or…

Use this skill when the user asks you to coordinate work across multiple agent users (e.g., "have alice summarize the logs and bob analyze the result"), set up new agents, debug an agent that isn't responding, fan out a question to many agents at once, or…

A package manager for AI knowledge. Meta-skill for on-demand skill discovery and installation — search curated local repositories or the global skills.sh registry. Self-teaching capability that finds, evaluates, and installs relevant skills when the agent…

This skill should be used when analyzing a link to an AI tool and adding it to the awesome-ai-tools readme with proper categorization