camera-inspection
Get a closer or different view of small, occluded or out-of-view task details by moving a camera the robot carries (a wrist camera on an empty arm, a pan-tilt…
Skill by robot-agent-exploration
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/robot-agent-exploration-camera-inspection
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/camera-inspection
What's inside
- Skill name
camera-inspection- Description
- Get a closer or different view of small, occluded or out-of-view task details by moving a camera the robot carries (a wrist camera on an empty arm, a pan-tilt head, the torso or the base). Use when the overview image cannot settle a task-relevant question, and before motions that sweep space you have not seen.
- License
- Apache-2.0
- Instructions
- 37 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Camera inspection A camera the robot carries is a movable viewpoint. Moving it closer or around reveals detail an overview image cannot; this is physical repositioning, not digital zoom. [Robot interface](../robot-interface/SKILL.md) lists this robot's cameras, what moves each one, and the tools to aim them (`<aim_camera>` where the robot has one). ## Close-up with a wrist camera - Use an arm that holds nothing. Never release a held object to get a view, and keep the other arm's grasp and the task state intact. - Choose a clear approach from the overview, move with the robot's planned or small observation-guided motions, and keep the arm and gripper clear of the support surface, task objects and the robot's own body. A successful plan does not prove clearance from objects the planner cannot see. - Inspect the fresh wrist image after each move and adjust distance and angle until the detail is clear and unoccluded by the gripper. Stop approaching once the view is useful, or when clearance is uncertain. ## Looking around When the target, a placement spot, an obstacle or a person may be beside or behind the robot, move the viewpoint instead of guessing. Before an in-place turn, a reverse or any motion that sweeps space you cannot see, look at that space yourself; ask the operator only when the views cannot settle it. Keep the arms close to the body while looking, observe at each view, and note the joint state and base pose of each view so you can relate it to the robot's frame. Turn back to the working view before manipulating. ## After moving a camera Run [object-localization](../object-localization/SKILL.md) on the new observation. Never reuse pixels, rays or camera poses from before the camera moved. Move only when the new view resolves a task-relevant uncertainty (it costs time or episode steps), and return the arm or body to a clear pose if it obstructs the next manipulation.
From robot-agent-exploration/rax, Apache-2.0.
More from robot-agent-exploration/rax
- 0.793score
object-localization
robot-agent-exploration
Locate visible object points in the robot's frame from the current observation, choosing the method the observation profile allows (depth with camera…
SkillAFreshness: A★ 184Claude Code +9 - 0.793score
autonomous-control
robot-agent-exploration
Turn what worked by hand into a step-wise Python controller, controller.py:main(ctx), that re-perceives the scene, completes the task from a fresh start and…
SkillAFreshness: A★ 184Claude Code +9 - 0.790score
experience-memory
robot-agent-exploration
Save successful action tips as soon as they work and retrieve them for later actions under matching observable conditions; distill reusable procedures into…
SkillAFreshness: A★ 184Claude Code +9 - 0.790score
multi-agent-exploration
robot-agent-exploration
Divide exploration among subagents with explicit robot or environment ownership and complementary motion or subtask goals, and combine their results.
SkillAFreshness: A★ 184Claude Code +9 - 0.790score
continual-learning
robot-agent-exploration
Read, run and grow a persistent skill library of verified, executable sub-task skills that carries what agents learn across sessions and tasks on the same…
SkillAFreshness: A★ 184Claude Code +9 - 0.788score
multi-env-exploration
robot-agent-exploration
Select and operate parallel exploration environments, keep their independent scenes apart, and share one episode budget.
SkillAFreshness: A★ 184Claude Code +9 - 0.788score
vlm-perception
robot-agent-exploration
Use the harness's vision-language model tool for image questions (identify, point at, segment, check) from direct tool calls or inside Python controllers…
SkillAFreshness: A★ 184Claude Code +9 - 0.784score
manual-robot-control
robot-agent-exploration
Solve the task by choosing robot actions directly from current observations.
SkillAFreshness: A★ 184Claude Code +9 - 0.784score
transfer-handoff
robot-agent-exploration
Write handoff/README.md, describing how to plan the motion for each subtask and object manipulation of this task, for a later session (or a later copy of you)…
SkillAFreshness: A★ 184Claude Code +9 - 0.784score
in-context-action-learning
robot-agent-exploration
Infer task goals and a useful strategy from visual demonstrations (an image sequence of a human or robot completing the task, or a terminal-state image), and…
SkillAFreshness: A★ 184Claude Code +9 - 0.784score
live-stream
robot-agent-exploration
The continuous, read-only recording of the robot's cameras and state over the recent past.
SkillAFreshness: A★ 184Claude Code +9 - 0.652score
robot-interface
robot-agent-exploration
Placeholder for the robot's own interface skill, which every universal skill links to for tools, frames, limits and safety.
SkillAFreshness: A★ 184Claude Code +9
Signals
- Stars
- 184
- Forks
- 12
- Open issues
- 0
- Last commit (this folder)
- Oct 14, 2026 (13 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/robot-agent-exploration/rax
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from robot-agent-exploration
- 0.793score
object-localization
robot-agent-exploration
Locate visible object points in the robot's frame from the current observation, choosing the method the observation profile allows (depth with camera…
SkillAFreshness: A★ 184Claude Code +9 - 0.793score
autonomous-control
robot-agent-exploration
Turn what worked by hand into a step-wise Python controller, controller.py:main(ctx), that re-perceives the scene, completes the task from a fresh start and…
SkillAFreshness: A★ 184Claude Code +9 - 0.790score
experience-memory
robot-agent-exploration
Save successful action tips as soon as they work and retrieve them for later actions under matching observable conditions; distill reusable procedures into…
SkillAFreshness: A★ 184Claude Code +9 - 0.790score
multi-agent-exploration
robot-agent-exploration
Divide exploration among subagents with explicit robot or environment ownership and complementary motion or subtask goals, and combine their results.
SkillAFreshness: A★ 184Claude Code +9 - 0.790score
continual-learning
robot-agent-exploration
Read, run and grow a persistent skill library of verified, executable sub-task skills that carries what agents learn across sessions and tasks on the same…
SkillAFreshness: A★ 184Claude Code +9 - 0.788score
multi-env-exploration
robot-agent-exploration
Select and operate parallel exploration environments, keep their independent scenes apart, and share one episode budget.
SkillAFreshness: A★ 184Claude Code +9
Cite this page
camera-inspection skill. Agent Mart. https://agentmart.dev/skills/robot-agent-exploration-camera-inspection (last updated 2026-10-24)