autonomous-ai/openharness agent skills, page 2

A skill your agent uses when displaying text in Phaser 4. An agent skill from autonomous-ai/openharness.

autonomous-ai/openharness

A skill your agent uses when working with tilemaps in Phaser 4.

autonomous-ai/openharness

A skill your agent uses when using timers and time-based events in Phaser 4.

autonomous-ai/openharness

A skill your agent uses when animating properties over time in Phaser 4.

autonomous-ai/openharness

Write documents in Typst — papers, spec sheets, reports, letters, slides — compile them to PDF with the pinned typst binary, read its diagnostics, and keep the pane current.

autonomous-ai/openharness

A skill your agent uses when migrating a Phaser 3 project to Phaser 4, or when a user asks about breaking changes, API differences, or how to update their v3 code.

autonomous-ai/openharness

Write synthesisable Verilog-2005 for an iCE40 FPGA and take it to a bitstream — the language subset that synthesises, the testbench shape the pane draws waves from, the iCEBreaker pinout, how to…

autonomous-ai/openharness

Build or update the person's About You — a short profile of how they work, from their own messages across every agent and what their agents saved about them.

autonomous-ai/openharness

Manage the machines on a Harness account by conversation — read the fleet, link and unlink, rename, note and group, bring a new computer in, remove one.

autonomous-ai/openharness

Create and revise field-survey plans from supplied GeoJSON boundaries, exclusions, camera geometry and capture requirements.

autonomous-ai/openharness

A skill your agent uses when working with the Phaser 4 event system.

autonomous-ai/openharness

Build PlatformIO firmware and inspect real compilation, memory, artifacts and pin plans without implicitly accessing hardware.

autonomous-ai/openharness

A skill your agent uses when using Phaser 4 math and geometry utilities.

autonomous-ai/openharness

Build and verify interactive GeoJSON maps in Atlas, with local exploration, safe imports, feature inspection and export.

autonomous-ai/openharness

A skill your agent uses when using Arcade Physics in Phaser 4.

autonomous-ai/openharness

A skill your agent uses when using Matter.js physics in Phaser 4.

autonomous-ai/openharness

Build, explain and verify small quantum circuits in Quantum Studio's editable statevector simulator.

autonomous-ai/openharness

Build and verify interactive HTML experiences in Web Studio's live, sandboxed preview.

autonomous-ai/openharness

Shape a Jev Archer range (target speed, bullseye size, shots), then verify Jev plants the slow targets and leaks the fast ones.

autonomous-ai/openharness

Turn what a person wants off a website into a browse.json job, read what came back in results.csv, and sharpen the fields that came back thin.

autonomous-ai/openharness

Design an arena level for Jev FPS (the ASCII map, the demons, the pace), then measure where Jev's decision rate stops being enough.

autonomous-ai/openharness

Design and verify Jev Arenas in OpenHarness's live viewer, where Jev plays the world you build.

autonomous-ai/openharness

Design a falling-blocks challenge for Jev in blocks.json (gravity, speedup, garbage, a custom board, the piece mix, the style line), then read the verdict and report where Jev starts to break.

autonomous-ai/openharness

Curate a live Jev improvisation in OpenHarness's viewer, where Jev composes chords, bass and melody bar by bar in real time.

autonomous-ai/openharness

Stage and verify Jev-on-Jev Reversi duels in OpenHarness's viewer, where Jev plays both sides and a third Jev referees.

autonomous-ai/openharness

Fix a broken module under the live eye of Jev Guard, where Jev (TypeSafe's System One model) scores your own edits for progress, risk and trust.

autonomous-ai/openharness

Design and verify Jev's landing missions in OpenHarness's viewer, where Jev is the flight computer throttling a booster down to a soft touchdown.

autonomous-ai/openharness

Design and verify Jev's command palettes in OpenHarness's viewer, where Jev ranks launch targets live per keystroke.

autonomous-ai/openharness

Design and verify Jev's balancing rigs in OpenHarness's viewer, where Jev keeps an inverted pendulum upright and loses it at high gravity.

autonomous-ai/openharness

Design and verify Jev's paddle-defense courts in OpenHarness's viewer, where Jev keeps a rally alive and loses it as the ball accelerates.

autonomous-ai/openharness

Design and verify Jev's shop windows in OpenHarness's viewer, where Jev calls the best buy as prices stream in and spends on paper.

autonomous-ai/openharness

Design and verify Jev's slalom courses in OpenHarness's viewer, where Jev is the racer steering to thread every gate.

autonomous-ai/openharness

Design and verify Jev's paper-trading desks in OpenHarness's viewer, where Jev trades a synthetic market live.

autonomous-ai/openharness

Write a keynote-grade slide deck in Marp Markdown (deck.md) — the structure of a great talk, the copy rules, the two keynote themes and their slide classes, offline art (wallpapers, charts, device…

autonomous-ai/openharness

Use in every Trail of Bits Skills workspace inside Harness, before any audit skill — the findings.json format the report pane is built from, which Trail of Bits skill serves which audit phase, and…

autonomous-ai/openharness

Inspect Harness sessions, explain activity and resource readings, preview cleanup, and stop or open explicitly selected sessions through their owning daemons.

autonomous-ai/openharness

Shape a Jev Catcher session (fall time, glove reach, field width), then verify Jev catches the slow pop flies and drops the fast ones.

autonomous-ai/openharness

Serve an MLX or Hugging Face safetensors model already on this Mac with mlx-lm's server and join it to the person's fleet.

autonomous-ai/openharness

Reuse what Ollama already has on this computer: adopt a running Ollama server into the person's fleet, or serve an Ollama-downloaded model without Ollama.

autonomous-ai/openharness

Serve a Hugging Face model with SGLang on a Linux machine with an NVIDIA or AMD GPU, configured from the model's SGLang cookbook page — or, when it has none, from the model's own files — and join it…

autonomous-ai/openharness

Serve a Hugging Face model with vLLM on a Linux machine with an NVIDIA or AMD GPU, configured from the model's official vLLM recipe — or, when it has none, from the model's own files — and join it…

autonomous-ai/openharness

Run a decision through a panel of coding agents from different vendors — writing the motion, seating the room, the sealed-openings protocol, tagging the claim map, pressing a split, and writing a…

autonomous-ai/openharness

Details behind AGENTS.md's 'Starting a model on this computer' flow: reading fleet models, sizing a start, choosing file and engine, picking a model for an engine with none, what fleet verify…

autonomous-ai/openharness

Build and verify a Babylon.js game progressively in OpenHarness's live Game Viewer.

autonomous-ai/openharness

Create and inspect music projects in the Ableton AI Harness workspace, including its local starter and optional upstream integration.

autonomous-ai/openharness

Create and inspect science projects in the autoresearch-mlx Harness workspace, including its local starter and optional upstream integration.

autonomous-ai/openharness

Create and inspect architecture projects in the Bonsai MCP Harness workspace, including its local starter and optional upstream integration.

autonomous-ai/openharness

Create and inspect generative media projects in the Comfy MCP Harness workspace, including its local starter and optional upstream integration.

autonomous-ai/openharness