Claude Skills by DexForce

Add a new simulation atomic action or motion primitive to EmbodiChain's typed planning and execution framework. Use when implementing a new skill, goal contract, action planner, symbolic effect, registration entry, documentation, and tests for AtomicActionEngine.

Add or update a reusable EmbodiChain embodiment YAML component that owns one simulation robot, its sensor suite, and an optional Task Program skill_profile. Use for configs/components/embodiments, new Task Program-compatible robots, or multi-embodiment task deployment.

Use when adding a new observation, event, reward, action, dataset, or randomization functor to an EmbodiChain environment

Use when adding a new robot to EmbodiChain — scaffolds a RobotCfg subclass (single-file or package layout) with the _build_defaults hook, build_pk_serial_chain, registration, docs page, and test stub.

Add or expose a high-level EmbodiChain Task Program Semantic Call, including registered call descriptors/lowerers, configured runtime-service decoder support, or a deliberately promoted built-in call. Use when a Task Program call is unknown or must lower to an Atomic Skill.

Use when adding a new kinematic (IK/FK) solver to EmbodiChain — implements the solver module, its Sphinx docs page, the unit test, and the benchmark entry together

Route and scaffold a new EmbodiChain task by solution type: handwritten expert trajectory, Task Program expert trajectory, simulator RL, lightweight RL, or an environment-only baseline. Use when creating a task, environment, expert demo, or RL task.

Create, compose, attach, validate, or repair an EmbodiChain Task Program. Use for program.yaml, integration.yaml, TaskProgramCfg, scene_binding, configured Task Program deployments, Semantic Call workflows, or Task Program expert demonstrations.

Use when writing tests for EmbodiChain modules, including observation functors, reward functors, solvers, sensors, environments, or any Python module

Write benchmark scripts for EmbodiChain modules following project conventions

Create single or stacked pull requests for EmbodiChain following the project's PR template and conventions, including proportional validation, dependency ordering, and proper GitHub repository labels

Use before committing or creating a PR for EmbodiChain to select proportional validation and verify affected code style, tests, headers, annotations, exports, and docstrings

Route EmbodiChain project-context and codebase-navigation requests through agent_context/MAP.yaml. Use to locate files, configs, defaults, entry points, registration paths or change sites; explain resolution chains; read, refresh or add project context. Chinese triggers include 文件在哪里、配置或默认值在哪里、 入口或注册逻辑在哪里、应该修改哪个文件、参考项目上下文、刷新项目上下文。

Use when preparing, drafting, validating, or publishing an EmbodiChain release, including GitHub release notes, version tags, and release artifacts.

Review EmbodiChain pull requests, branches, commits, patches, or working-tree diffs for correctness regressions, architecture-contract violations, compatibility risks, unsafe resource behavior, and missing tests. Use when asked to review, audit, inspect, assess, or approve an EmbodiChain change; produce prioritized, evidence-backed findings without modifying the change unless the user explicitly asks for fixes.

Generate or update EmbodiChain Sphinx API documentation for public Python exports. Use when the API docs checker or CI reports missing __all__ exports, after adding or changing public APIs, or when asked to fill, generate, or synchronize API-reference pages and their descriptions.

Claude adapter for the canonical EmbodiChain add-atomic-action skill.

Claude adapter for the canonical EmbodiChain add-embodiment-component skill.

Claude adapter for the canonical EmbodiChain add-functor skill.

Claude adapter for the canonical EmbodiChain add-robot skill.

Claude adapter for the canonical EmbodiChain add-semantic-call skill.

Claude adapter for the canonical EmbodiChain add-solver skill.

Claude adapter for routing and creating EmbodiChain task environments, handwritten/Task Program expert demonstrations, and RL tasks.

Claude adapter for the canonical EmbodiChain add-task-program skill.

Claude adapter for the canonical EmbodiChain add-test skill.

Claude adapter for the canonical EmbodiChain benchmark skill.

Claude adapter for the canonical EmbodiChain PR skill.

Claude adapter for the canonical EmbodiChain pre-commit-check skill.

Claude adapter for EmbodiChain code/config navigation and reading, refreshing or adding registered project context.

Claude adapter for the canonical EmbodiChain release skill.

Claude adapter for the canonical EmbodiChain review-pr skill.

Claude adapter for the canonical EmbodiChain update-api-docs skill.