Skip to main content
skill CX Codex

state-verification — Claude Code skill: checks object states

The state-verification Claude Code skill checks object states and relationships using distinguishing evidence. It activates when a next step depends on whether an object is held, placed, or correctly oriented.

MIT ★ 488 updated 2026-11-15

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Open-RUA/uni-robot-agent --skill state-verification -a claude-code
Open on GitHub

What state-verification does

The skill helps an agent determine whether a gripper retains an object, whether the object rests on its intended support, and whether a required effect occurred. It focuses each check on one unresolved question and classifies the result as confirmed, contradicted, or unresolved. A reached hand pose alone does not prove that an object was placed.

Use existing images and observation records first; request another view only if it can separate the remaining possibilities. view_env_state(step=...) selects a recorded observation index, not a physics step. A collision, slip, or changed support can invalidate related findings. The current environment’s robot description and published manual are needed for units, coordinate frames, and capability limits.

What it helps with

  • check whether a gripper still holds the intended object
  • confirm that an object remains on its target support
  • distinguish entry into an opening from overlapping silhouettes
  • verify a required orientation and account for each object
  • recheck relationships affected by a collision

Example prompts for the agent

  • Check whether the gripper still holds the object before moving it.
  • Determine whether the object stayed on its support after release.
  • Check whether the arrangement is complete and list relationships that remain unresolved.

How to install state-verification

1Skills CLI (Vercel)

npx skills add Open-RUA/uni-robot-agent --skill state-verification -a claude-code

2Manually: put the files in place

~/.claude/skills/state-verification/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/state-verification/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about state-verification

How do I install state-verification in Claude Code?

Run npx skills add Open-RUA/uni-robot-agent --skill state-verification -a claude-code. The skill file is at ~/.claude/skills/state-verification/SKILL.md.

What does state-verification do?

It guides an agent through checking object relationships from observable evidence, such as whether a gripper retains an object or whether it stays on a support after release. Results are treated as confirmed, contradicted, or unresolved.

What does the step argument in view_env_state mean?

It selects a recorded observation index, not a physics simulation step. Reading the latest record again neither advances physics nor waits for an in-flight action.

Source text

SKILL.md · MIT
---
name: state-verification
description: Verify object states and relationships from distinguishing evidence. Use when the next action depends on an unresolved state or when assessing completion across occlusion and multiple objects.
---

# Verify the relation that changes the next decision

## Select one unresolved question

Identify the unresolved relation that matters for the next dependent action:
attachment, support, containment, orientation, identity or a required effect.
Derive requirements from the instruction; add no preferred pose, count or order.
Choose an observation whose possible outcomes would change the next decision.
Use existing images and feedback first. Select a new view only when it can
distinguish the remaining outcomes; no written proof is required per call.

Keep three outcomes: confirmed, contradicted and unresolved. A tool return or
absence of visible failure does not by itself confirm an object relationship.

| Question | Distinguishing evidence | Insufficient alone |
|---|---|---|
| Is the intended object controlled? | A safe test motion preserves its relation to the hand, with consistent identity and source-view change. | Closed fingers, opening residual, or a centered wrist image. |
| Is it supported after placement? | After release and clear withdrawal, it remains on the intended support. | The hand reached the placement pose. |
| Is it contained or engaged? | Visible opening, edge and depth relationships support entry rather than bridging or leaning. | Overlapping silhouettes. |
| Is its required orientation correct? | Identifiable ends, faces or axes distinguish the requested orientation. | Correct center position or an ambiguous long axis. |
| Are all required objects accounted for? | Each identity has an observed destination or a still-valid chain of confirmed transfers and placements. | Attempt counts or one final merged silhouette. |

A verification lift is appropriate when lifting is intended and observed
clearance permits it. For constrained or fragile objects, choose a compatible
test; do not impose a lift on every operation. Inspect the resulting object
motion rather than treating the test command as evidence. For an uncertain
contact effect, use `general/gripper/contact-effect/SKILL.md`.

## Compare the right records and views

Choose the camera that exposes the deciding feature rather than requesting all
views by default. For attachment, compare the original support and the hand;
for engagement, expose the remaining gap or entering feature. A second view
is useful when it resolves identity, occlusion or competing explanations.

view_env_state(step=...) selects a recorded observation index, not a native
physics step. Use returned record_index and step to identify the before/after
states. Re-reading the latest record advances no physics and does not wait for
an in-flight action. Resolve that action before checking its final effect.
When a physical process needs time, use a short hold for a specific observable
purpose, obtain its completed result, and inspect the attached image.

Track the same object across records and account for camera movement. An object
centered in a moving wrist image may still rest on its original support; image
displacement alone cannot separate object motion from camera motion.

After a verification lift, compare the same object against its original support
and the hand. If the hand rises but the object stays at its source and becomes
smaller in the wrist view, the grasp did not retain it. A centered image is not
counter-evidence: the camera moved with the hand. When the views cannot resolve
height or attachment, use a distinguishing view or a calibrated measurement of
the same visible feature before dependent transport. Do not measure again when
existing observations already establish the relation. If lifting is inappropriate,
choose a compatible probe. For a press, inspect target displacement and release
rather than counting reached hand poses; use the contact-effect skill for event counts.

## Preserve a small evidence chain

Retain only the identity, required relation, its status and the observation or
transition supporting it. Update affected entries; do not narrate a full ledger
after every call. A brief record such as "A released onto B; support observed"
can preserve evidence that will later be occluded. Include the observation's
step or time when needed to distinguish it from an older view. For nested or
stacked objects, retain each established support relation; a final merged outline
cannot retroactively confirm an unverified entry or repair a disturbed base.

A confirmed relation can remain valid after occlusion. Later placements need
not expose every earlier object again if identities and transfers were tracked
and subsequent actions give no reason to suspect disturbance. An unverified
relation does not become confirmed merely because the object disappeared.

A collision, slip, changed support or ambiguous identity can invalidate affected
relations and those depending on them. A relation depending on a displaced base
needs review even if its own object was not directly touched. Recheck those
relations rather than restarting the whole arrangement. During occluded actions
that could change a relation, preserve uncertainty until useful evidence returns.

## End the check with a decision

- Confirmed: continue the dependent action without duplicate views.
- Contradicted: correct the observed mismatch and update the affected relation.
- Unresolved: choose one useful view or safe probe that separates the alternatives
  before committing to a dependent action. Prefer the least disruptive check.

If the same view adds no information, change the view, probe or hypothesis.
If available tools cannot distinguish the alternatives, keep the relation
unresolved and pursue a different feasible observation, approach or independent
subgoal when order permits. Longer explanations do not strengthen the evidence.

For completion, combine current observations with earlier evidence that remains
valid. Check required relationships and their dependencies, not whether all
planned actions were attempted. Report remaining uncertainty faithfully; follow
the system prompt's stopping conditions. Uncertainty does not authorize success
or an early finish, and does not justify repeating an uninformative check.

When exposed, read `state.arms[arm].metadata.gripper_opening_m` for actual
signed pad gap and `gripper_target_opening_m` for the effective drive target.
Unavailable measurements remain unknown; a residual gap alone does not establish
attachment.
Read the current environment's robot description and published manual for
units, frames and capability limits.

© Open-RUA · MIT · Open-RUA/uni-robot-agent

Similar skills

SKILL.md skills catalog →

From the same set41

The whole set →
supported-contact The supported-contact Claude Code skill plans object contact and the assisting hand’s motion. It activates when a held load needs a receiver adjusted or restrained at the same time. CX Codex +1 ★ 488repo stars pose-targeting The pose-targeting Claude Code skill builds robot motion targets from a position and orientation. It activates for tool changes, reorientation, and aligning a feature on a held object. CX Codex +1 ★ 488repo stars contact-effect The contact-effect Claude Code skill checks contact by observing how the target responds and guides adjustments. It activates for new or uncertain contact, or after a change to grip, tool geometry, or support. CX Codex +1 ★ 488repo stars placement-and-engagement The placement-and-engagement Claude Code skill plans and checks object placement, support, containment, and mechanical engagement from visible features. It applies when receiver stability or relative geometry shapes the requested result. CX Codex +1 ★ 488repo stars grasp-geometry This Claude Code skill selects grasp geometry based on exposed material, finger access, and the object's next use. It covers thin, hollow, crowded, or partly blocked objects. CX Codex +1 ★ 488repo stars motion-recovery The motion-recovery Claude Code skill helps diagnose robot motion failures and choose a changed route. The agent consults it before a difficult reorientation or after motion stalls. CX Codex +1 ★ 488repo stars tool-selection The tool-selection Claude Code skill picks observation and geometry tools to find the fact needed for the next action. It activates during localization planning, measurement reuse, or recovery from an uninformative perception query. CX Codex +1 ★ 488repo stars evidence-driven-gripper The evidence-driven-gripper Claude Code skill chooses contact actions from current observations and gripper capabilities. It checks object control before transport and revises the plan after a failed grasp. CX Codex +1 ★ 488repo stars

Project sponsors

Companies that keep this analytics open