Intrinsic Core Solution Building

What it does

When your agent uses it

• Game Development work in your project

Example prompts

• “/intrinsic-core-solution-building”

Requirements

• Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Direct SDK imports and connection parameter exclusivity: Import SBL libraries directly in Python (from intrinsic.solutions import…
2. 2Resource iteration and membership: Inspect handles via solution.resources. or bracket indexing solution.resources[name], and iterate using…
3. 3Explicit bt.Task wrapping in conditional branches: Wrap action calls explicitly in bt.Task(action=skill) when supplying child nodes to…
4. 4Belief and simulation world synchronization: Pass start_from_world_state=worlds.EditWorldId.BELIEF to executive.run() after modifying…
5. 5Execution blocking and return value handling: Pass the behavior tree to solution.executive.run(tree) or call…

What it can do on your machine

Read from SKILL.md and the folder at commit 0221644. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Intrinsic Core Solution Building loads about 2.7k tokens when it runs, and up to ~19k if it reads all its reference files. Until then it costs about 136 tokens; SKILL.md has 645 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~136

When it runs · the whole SKILL.md, loaded when a task matches

~2.7k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~19k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from intrinsic-ai/intrinsic-core at commit 0221644, republished under its Apache-2.0 licence (© intrinsic-ai). 645 words, ~2,664 tokens.

name

intrinsic-core-solution-building

description

Intrinsic Solution Building Library (SBL) Python SDK guide for connecting to workcells, composing Behavior Trees, querying/mutating ObjectWorld frames, binding equipment resources, and orchestrating execution. Triggers: connect to solutions, compose behavior trees, mutate world frames, bind equipment resources, execute trees. Subsystems: SBL, Executive, ObjectWorld, Resources, BehaviorTree. Dependencies: localhost:17080, intrinsic.solutions. Anti-keywords: inctl service add, raw C++ authoring, BUILD rules.

from intrinsic.math.python import data_types
from intrinsic.solutions import behavior_tree as bt, deployments, worlds


def connect_and_run(address: str = "localhost:17080") -> None:
  # 1. Connect directly to active solution over local Envoy ingress
  solution = deployments.connect(address=address)
  solution.update_skills()

  # 2. Mutate belief world using explicit keyword arguments on Pose3
  world = solution.world
  waypoint = data_types.Pose3(
      rotation=data_types.Rotation3.identity(),
      translation=[0.45, 0.0, 0.30],
  )
  world.update_transform(
      node_a=world.root,
      node_b=world.waypoint_frame,
      a_t_b=waypoint,
      node_to_update=world.waypoint_frame,
  )

  # 3. Construct Behavior Tree with explicit bt.Task wrapping in conditional nodes
  move_home = solution.skills.ai.intrinsic.move_robot(
      arm_part=solution.resources.robot,
      target_joint_configuration=world.robot.joint_configurations.home,
  )
  tree = bt.BehaviorTree(
      name="Home workflow",
      root=bt.Sequence(children=[bt.Task(action=move_home, name="Move home")]),
  )

  # 4. Execute tree while syncing simulation ("sim_world") from belief ("world")
  solution.executive.run(
      tree,
      start_from_world_state=worlds.EditWorldId.BELIEF,
  )

[Issue detected during SBL Python workflow]
  │
  ├─► [Symptom: ValueError: Org is not supported when connecting via grpc_channel or address]
  │     └─► Cause: Conflicting connection parameters supplied to deployments.connect().
  │     └─► Action: Omit org when connecting via address="localhost:17080" or grpc_channel.
  │
  ├─► [Symptom: KeyError: 'Resource 0 not registered' or TypeError: object has no len()]
  │     └─► Cause: Direct iteration or len() invoked on solution.resources.
  │     └─► Action: Iterate via [solution.resources[k] for k in dir(solution.resources)].
  │
  ├─► [Symptom: FailedPrecondition: solution does not have an origin nor does it track a branch]
  │     └─► Cause: Attempting solution.behavior_trees[...] dictionary assignment on branchless workcell.
  │     └─► Action: Pass BehaviorTree directly to solution.executive.run(tree) or executive.load(tree).
  │
  ├─► [Symptom: TypeError: expected BehaviorTree.Node got BehaviorCall]
  │     └─► Cause: Raw skill passed to bt.Fallback.Try or bt.Selector.Branch without task wrapping.
  │     └─► Action: Wrap action explicitly via bt.Fallback.Try(node=bt.Task(action=skill)).
  │
  ├─► [Symptom: Gazebo simulation ignores solution.world edits or reports missing obstacles]
  │     └─► Cause: Simulation world ("sim_world") not synchronized from belief world ("world").
  │     └─► Action: Pass start_from_world_state=worlds.EditWorldId.BELIEF to executive.run().
  │
  ├─► [Symptom: CEL evaluation error: params.<field> refers to variables that do not exist]
  │     └─► Cause: Saved BehaviorTree executed without parameter debug payload.
  │     └─► Action: Pass parameters=saved_bt.user_data_protos.get("PARAMETER_DEBUG_VALUES").
  │
  └─► [Symptom: UNIMPLEMENTED / maximum recursion depth of 100 reached on CreateOperation]
        └─► Cause: Resubmitting BehaviorTree containing output-only runtime execution metadata.
        └─► Action: Strip RunMetadata, called_tree_state, and node state fields before resubmitting.

© intrinsic-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in .agents/skills/intrinsic-core-solution-building of intrinsic-ai/intrinsic-core.

• SKILL.md
• references/behavior-trees-and-cel.md
• references/resources-and-execution.md
• references/world-and-motion.md

Open the folder on GitHubat commit 0221644