planning-with-files
Optional persistent file-based planning for multi-phase or long-running work that benefits from recovery across sessions or…
Bevy workflows for ECS, migrations, first-party UI/input/rendering/assets/shaders, plugin selection, scenes, scheduling, hot reloading, streamed-world expansion, world authoring, diagnostics, validation, and BRP/MCP control. Use when building, debugging, profiling, testing,
$ npx -y skills add khaneliman/khanelinix --skill bevy-toolkit --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/bevy-toolkitContext preview
The summary Claude sees to decide when to auto-load this skill.
Bevy workflows for ECS, migrations, first-party UI/input/rendering/assets/shaders, plugin selection, scenes, scheduling, hot reloading, streamed-world expansion, world authoring, diagnostics, validation, and BRP/MCP control. Use when building, debugging, profiling, testing,
name: bevy-toolkit description: Bevy workflows for ECS, migrations, first-party UI/input/rendering/assets/shaders, plugin selection, scenes, scheduling, hot reloading, streamed-world expansion, world authoring, diagnostics, validation, and BRP/MCP control. Use when building, debugging, profiling, testing, editing, migrating, or automating native Bevy apps. metadata: disable-model-selection: "true"
Route Bevy work by engine concern and live-runtime need. Keep general Rust, Cargo, unsafe, and allocator decisions in `rust-toolkit`.
1. Read contributor instructions, `Cargo.toml`, `Cargo.lock`, enabled Bevy features, development-only plugins, and repository-native launch/check scripts. 2. Confirm locked Bevy version before using API examples or migration advice. 3. For live work, inspect existing process and BRP status before launching another game. Prefer MCP lifecycle tools; use `scripts/brp-control.py` for deterministic direct-BRP calls and repository automation. 4. Use `brp_type_guide` before constructing or mutating reflected component or resource values. 5. Pick one primary route below. Load another reference only when work crosses its boundary.
1. **ECS and plugin architecture**: components/resources, query data shape, plugin ownership, relationships, scenes, and headless composition. Read [architecture.md](references/architecture.md). 2. **states and scheduling**: lifecycle setup/teardown, state-scoped entities, system sets, deferred commands, events/messages, and observers. Read [lifecycle-and-scheduling.md](references/lifecycle-and-scheduling.md). 3. **MCP and BRP**: app setup, target discovery, launch/status/logs, type introspection, queries, mutations, watches, input, screenshots, and cleanup. Read [mcp-and-brp.md](references/mcp-and-brp.md). 4. **runtime automation**: direct JSON-RPC script, deterministic control loops, window/headless handling, capture freshness, and process ownership. Read [runtime-control.md](references/runtime-control.md). 5. **performance and validation**: schedule/system profiling, archetype churn, GPU/frame diagnostics, minimal-app tests, visual proof, and build iteration. Read [performance-and-validation.md](references/performance-and-validation.md). 6. **ecosystem selection**: third-party crate compatibility, architecture fit, target/backend support, maintenance risk, and bounded integration spikes. Read [ecosystem-selection.md](references/ecosystem-selection.md). 7. **world authoring and iteration**: feedback-loop selection, source-of-truth ownership, transactional reload, editor/DCC bridges, and persisted edits. Read [authoring-pipelines.md](references/authoring-pipelines.md). 8. **Bevy migrations**: locked-version intake, chained release guides, dependency/plugin compatibility, scene/assets/reflection/BRP checkpoints, rollback boundaries, and target matrices. Read [migration.md](references/migration.md). 9. **first-party feature construction**: UI layout/focus/accessibility/text, input mapping/controllers, cameras/windows, main/render-world boundaries, assets/shaders, and headless versus visual proof. Read [feature-construction.md](references/feature-construction.md). 10. **hot reload and streamed worlds**: asset watching, scene/world reload semantics, chunk lifecycle, model/view persistence, stale async work, code hotpatching, and reload stress tests. Read [hot-reload-and-streaming.md](references/hot-reload-and-streaming.md).
explicitly need remote control. Bind local probes to loopback by default.
path, read back, capture evidence, and restore temporary changes.
command persists them to source-owned data.
gameplay correctness. Inspect resulting state and pixels.
size the compositor surface before trusting coordinates or screenshots.
and non-Bevy performance work.
skill.
Run packages directly with: Or install from the packages output. For example:
Optional persistent file-based planning for multi-phase or long-running work that benefits from recovery across sessions or…
Audit coding-agent sessions and mine cross-harness history for recurring corrections, skill-routing gaps, and harness faults. Use…
Design and audit agent instructions, skills, plugins, subagents, prompts, hooks, and provider configuration. Use for AI-tool…
Sketch interfaces, state, and module structure before code. Use for explicit design-led implementation or as a caller-owned…
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena,…
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by…