policy-act
Use when an approved task needs an ACT checkpoint to propose bounded, versioned action chunks from current observations.
Skill by Chenxi-Li24
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/chenxi-li24-policy-act
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/policy-act
What's inside
- Skill name
policy-act- Description
- Use when an approved task needs an ACT checkpoint to propose bounded, versioned action chunks from current observations.
- License
- MIT
- Instructions
- 25 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: "policy-act" does not match folder "act"
Files (2)
- SKILL.md
- manifest.yaml
SKILL.md (first lines)
# ACT Policy ## Purpose Load a declared ACT checkpoint and produce finite action chunks for a specific task, plan revision and observation revision. ## Contract Input references `frameRef`, `robotStateRef`, targetRef, checkpoint hash and requested horizon. Output records checkpoint identity, action units, timing, confidence and validity envelope. Task Engine and Robot Service validate every chunk before execution. A new chunk cannot extend the user's authorized action range implicitly. ## Safety Reject missing or mismatched checkpoints, stale observations, discontinuous first actions, out-of-range joints, excessive speed and unavailable supervision. Cancel clears queued chunks. Interruption requires a new plan and authorization. ## Dependencies Requires Robot, Vision, Supervisor, Startouch, XVisio and verified `policy.act` checkpoint assets. ## Current Status Only prior contract/loader prototypes exist in migration sources. The formal worker and checkpoint are absent, so Registry must report unavailable.
From Chenxi-Li24/UIEAclub_ThirdHand_VLA, MIT.
More from Chenxi-Li24/UIEAclub_ThirdHand_VLA
- 0.565score
vision-supervise-execution
Chenxi-Li24
Use when an approved physical task needs independent visual checks for target visibility, alignment, grasp progress, or placement success.
SkillBFreshness: B★ 4Claude Code +9 - 0.565score
policy-diffusion-policy
Chenxi-Li24
Use when an approved task needs a diffusion-policy model to propose bounded action candidates from current observations.
SkillBFreshness: B★ 4Claude Code +9 - 0.565score
policy-vla
Chenxi-Li24
Use when an approved task needs a VLA model to propose versioned action candidates from current visual and language context.
SkillBFreshness: B★ 4Claude Code +9 - 0.565score
vision-describe-scene
Chenxi-Li24
Use when a task needs a structured, read-only summary of the current RGB-D scene before selecting an object or planning an action.
SkillBFreshness: B★ 4Claude Code +9 - 0.565score
vision-inspect-scene
Chenxi-Li24
Use when the ThirdHand controller needs a fresh, read-only natural-language observation from the existing XVisio RGB stream.
SkillBFreshness: B★ 4Claude Code +9 - 0.564score
vision-detect-objects
Chenxi-Li24
Use when a task needs object classes, labels, confidence, and stable target references from the current RGB-D scene.
SkillBFreshness: B★ 4Claude Code +9 - 0.564score
manipulation-pick-and-place
Chenxi-Li24
Use when the user requests a supervised pick of a stable target and placement at an approved destination.
SkillBFreshness: B★ 4Claude Code +9 - 0.304score
detect-bottles
Chenxi-Li24
No description from the publisher yet.
SkillBFreshness: B★ 4Claude Code +9 - 0.304score
select-target
Chenxi-Li24
No description from the publisher yet.
SkillBFreshness: B★ 4Claude Code +9 - 0.304score
gripper-control
Chenxi-Li24
No description from the publisher yet.
SkillBFreshness: B★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Sep 10, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Chenxi-Li24
- 0.565score
vision-describe-scene
Chenxi-Li24
Use when a task needs a structured, read-only summary of the current RGB-D scene before selecting an object or planning an action.
SkillBFreshness: B★ 4Claude Code +9 - 0.565score
policy-diffusion-policy
Chenxi-Li24
Use when an approved task needs a diffusion-policy model to propose bounded action candidates from current observations.
SkillBFreshness: B★ 4Claude Code +9 - 0.565score
policy-vla
Chenxi-Li24
Use when an approved task needs a VLA model to propose versioned action candidates from current visual and language context.
SkillBFreshness: B★ 4Claude Code +9 - 0.565score
vision-inspect-scene
Chenxi-Li24
Use when the ThirdHand controller needs a fresh, read-only natural-language observation from the existing XVisio RGB stream.
SkillBFreshness: B★ 4Claude Code +9 - 0.565score
vision-supervise-execution
Chenxi-Li24
Use when an approved physical task needs independent visual checks for target visibility, alignment, grasp progress, or placement success.
SkillBFreshness: B★ 4Claude Code +9 - 0.564score
manipulation-pick-and-place
Chenxi-Li24
Use when the user requests a supervised pick of a stable target and placement at an approved destination.
SkillBFreshness: B★ 4Claude Code +9
Cite this page
policy-act skill. Agent Mart. https://agentmart.dev/skills/chenxi-li24-policy-act (last updated 2026-10-24)