Implement or review a custom VLA policy adapter for EBench EvalClient, including observation preprocessing, action semantics, chunking, and episode resets.
$ npx skills add InternRobotics/EBench --skill ebench-integrate-policy -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install InternRobotics/EBench ebench-integrate-policy --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/InternRobotics/EBench.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ebench-integrate-policy .claude/skills/ebench-integrate-policy && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ebench-integrate-policy" agent skill from https://github.com/InternRobotics/EBench/tree/main/skills/ebench-integrate-policy into .claude/skills/ebench-integrate-policy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ebench-integrate-policy", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/InternRobotics/EBench/tree/main/skills/ebench-integrate-policyType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add InternRobotics/EBench --skill ebench-integrate-policy -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install InternRobotics/EBench ebench-integrate-policy --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/InternRobotics/EBench.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ebench-integrate-policy .agents/skills/ebench-integrate-policy && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ebench-integrate-policy" agent skill from https://github.com/InternRobotics/EBench/tree/main/skills/ebench-integrate-policy into .agents/skills/ebench-integrate-policy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ebench-integrate-policy", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add InternRobotics/EBench --skill ebench-integrate-policy -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install InternRobotics/EBench ebench-integrate-policy --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/InternRobotics/EBench.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ebench-integrate-policy .cursor/skills/ebench-integrate-policy && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ebench-integrate-policy" agent skill from https://github.com/InternRobotics/EBench/tree/main/skills/ebench-integrate-policy into .cursor/skills/ebench-integrate-policy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ebench-integrate-policy", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/InternRobotics/EBench.git --path skills/ebench-integrate-policy--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add InternRobotics/EBench --skill ebench-integrate-policy -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install InternRobotics/EBench ebench-integrate-policy --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/InternRobotics/EBench.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ebench-integrate-policy .gemini/skills/ebench-integrate-policy && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ebench-integrate-policy" agent skill from https://github.com/InternRobotics/EBench/tree/main/skills/ebench-integrate-policy into .gemini/skills/ebench-integrate-policy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ebench-integrate-policy", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install InternRobotics/EBench ebench-integrate-policyInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add InternRobotics/EBench --skill ebench-integrate-policy -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/InternRobotics/EBench.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ebench-integrate-policy .github/skills/ebench-integrate-policy && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ebench-integrate-policy" agent skill from https://github.com/InternRobotics/EBench/tree/main/skills/ebench-integrate-policy into .github/skills/ebench-integrate-policy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ebench-integrate-policy", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add InternRobotics/EBench --skill ebench-integrate-policy -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install InternRobotics/EBench ebench-integrate-policy --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/InternRobotics/EBench.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ebench-integrate-policy .opencode/skills/ebench-integrate-policy && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ebench-integrate-policy" agent skill from https://github.com/InternRobotics/EBench/tree/main/skills/ebench-integrate-policy into .opencode/skills/ebench-integrate-policy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ebench-integrate-policy", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
ebench-integrate-policyImplement or review a custom VLA policy adapter for EBench EvalClient, including observation preprocessing, action semantics, chunking, and episode resets.
Ebench Integrate Policy is an agent skill from InternRobotics/EBench. Implement or review a custom VLA policy adapter for EBench EvalClient, including observation preprocessing, action semantics, chunking, and episode resets.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Elemental Diagnosis of Generalist Mobile Manipulation Policies. The licence is MIT.
Read from SKILL.md and the folder at commit 355fe56. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Ebench Integrate Policy loads about 1.3k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 576 words of instructions outside code blocks.
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.
The automated check found no risky patterns in SKILL.md.
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.
The full file from InternRobotics/EBench at commit 355fe56, republished under its MIT licence (© InternRobotics). 576 words, ~1,285 tokens.
.claude/skills/ebench-integrate-policy/SKILL.md (or your agent's skills folder).Resolve paths from the EBench root. Read third_party/genmanip-client/src/genmanip_client/eval_client.py and the closest adapter: baselines/X-VLA/run.py, baselines/openpi/scripts/pi_eval_client_online.py, or baselines/InternVLA-A1/inference.py. Inspect the user's policy inference API and training transforms before choosing a mapping.
Observations are keyed by string worker IDs; a worker's model observation is obs[wid]["obs"]. Existing adapters use:
video.overlook_camera_view, video.left_camera_view, video.right_camera_view;state.joints, state.gripper, state.base, and optionally state.ee_pose;instruction, and reset for episode-boundary handling.Verify image type, RGB ordering, shape, resize/padding, proprioception ordering, units, and normalization against training. Do not invent missing cameras or silently replace missing input with zeros. Keep checkpoint normalization and model transforms paired.
For the current r5a/lift2 joint-position adapters, the dispatched action orders left arm (6), left gripper (2), right arm (6), right gripper (2); base_motion has 3 components. The payload explicitly declares control_type, is_rel, and base_is_rel. Verify a different robot/control mode against its server contract rather than generalizing these dimensions.
Model outputs are not interchangeable:
base_is_rel=True.action_mode setting; inspect its conversion before selecting delta or absolute behavior.Document the chosen model-to-server channel mapping, normalization, frame/units, gripper interpretation, and relative/absolute semantics. Match the checkpoint, not whichever baseline is easiest to copy.
Use EvalClient.reset() for initial observations and step() for execution; inspect supported single-action/chunk forms in the pinned client. Keep string worker IDs consistent. Limit deployed horizon to available predictions and reset model history, cached actions, and temporal state at each episode boundary. done indicates evaluation completion, not task success; use saved result metrics for success.
Never execute the remainder of an old chunk after an episode reset. For multiple workers, keep history/chunks independent and handle worker-specific resets. If a step times out, execution may already have occurred: do not blindly resend actions. Use bounded client recovery and fresh observations, discard stale actions, and record the interruption. Close the client in finally so recordings/results are flushed.
Expose evaluation URL, run ID, token, and worker IDs as runtime settings rather than hardcoding them. For a new online run, follow the queue-and-launch sequence in ebench-evaluate: call gmp online submit --print_endpoint, wait for readiness, and parse its returned endpoint and task_id. No evaluation endpoint is required from the user before this submission.
Only after both values are available, construct the client using the returned assignment:
import os
from genmanip_client import EvalClient
client = EvalClient(
base_url=os.environ["EVAL_URL"], # online submit response: endpoint
run_id=os.environ["RUN_ID"], # online submit response: task_id
token=os.environ["TOKEN"],
worker_ids=["0"],
)Connect this client to the policy's reset/inference/step loop and close it in finally. The platform base URL is used for queue submission; EvalClient.base_url is the returned evaluation endpoint. Do not create/reset workers while the task is still queued, or resubmit an online task each time the adapter reconnects. Adapter implementation alone does not require submitting a live task; use this flow when running the requested online evaluation.
Use a representative local observation or fixture to check preprocessing, finite action values, dimensions, channel order, inverse normalization, chunk-length boundaries, and reset behavior without a simulator. Include a known-value action conversion example that would expose swapped channels or incorrect delta semantics; shape-only assertions are insufficient.
Then run a small validation rollout when a server/checkpoint is available and evaluation is in scope. Inspect actual state/action traces before scaling. Deliver the adapter, concrete launch command, mapping description, and evidence distinguishing offline contract checks from live rollout validation. Keep model-specific code in its baseline/adapter directory rather than changing unrelated upstream submodules.
© InternRobotics, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/ebench-integrate-policy of InternRobotics/EBench.
Open the folder on GitHubat commit 355fe56
Ebench Integrate Policy next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ebench Integrate Policy this skillInternRobotics/EBench | 145 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Implementing Policy As Code With Open Policy Agentmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~2.6k | Automated safety check: Notes | Apache-2.0 | |
| Implementing Usb Device Control Policymukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Implementing GCP Organization Policy Constraintsmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Implementing Container Network Policies With Calicomukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~680 | Automated safety check: Pass | Apache-2.0 | |
| Implementing File Integrity Monitoring With Aidemukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~642 | Automated safety check: Notes | Apache-2.0 |
mukul975/Anthropic-Cybersecurity-Skills
Implements policy-as-code enforcement with Open Policy Agent (OPA) and Gatekeeper for Kubernetes and CI/CD pipelines, covering writing Rego policies, deploying OPA Gatekeeper as a Kubernetes…
mukul975/Anthropic-Cybersecurity-Skills
Implements USB device control policies to restrict unauthorized removable media access on endpoints, preventing data exfiltration and malware introduction via USB devices.
mukul975/Anthropic-Cybersecurity-Skills
Implements GCP Organization Policy constraints via gcloud and Terraform, such as restricting external IPs, resource locations, default service accounts, and service account keys, plus dry-run…
mukul975/Anthropic-Cybersecurity-Skills
Uses Calico's own policy CRDs beyond the upstream Kubernetes API - GlobalNetworkPolicy, HostEndpoint, NetworkSet, policy tiers, and DNS-based egress rules - applied and audited with calicoctl.
mukul975/Anthropic-Cybersecurity-Skills
Configures AIDE (Advanced Intrusion Detection Environment) for file integrity monitoring on Linux, covering baseline database creation, scheduled integrity checks via cron, change detection, and…
mukul975/Anthropic-Cybersecurity-Skills
Configures Windows Group Policy Objects to block ransomware execution and lateral spread, covering AppLocker rules, Software Restriction Policies, Controlled Folder Access, attack surface reduction…
InternRobotics/EBench
Generate and interpret EBench evaluation reports, compare runs and baselines, and diagnose capability or generalization gaps with explicit data coverage and aggregation semantics.
InternRobotics/EBench
Run and monitor an EBench policy evaluation against a local GenManip server or the online service, including baseline launch commands, worker allocation, and reproducible run records.
InternRobotics/EBench
Prepare or check an EBench evaluation environment for OpenPI, X-VLA, InternVLA-A1, or a custom policy.
InternRobotics/EBench
Diagnose EBench evaluation failures, stalled workers, transport errors, invalid actions, and unexpectedly low scores using logs and episode artifacts.
Implement or review a custom VLA policy adapter for EBench EvalClient, including observation preprocessing, action semantics, chunking, and episode resets. Ebench Integrate Policy is an agent skill from InternRobotics/EBench. Implement or review a custom VLA policy adapter for EBench EvalClient, including observation preprocessing, action semantics, chunking, and episode resets.
Run `npx skills add InternRobotics/EBench --skill ebench-integrate-policy -a claude-code`. Or copy the skill folder (skills/ebench-integrate-policy in InternRobotics/EBench) into .claude/skills/ebench-integrate-policy in your project. Claude Code loads it when a task matches its description.
Run `npx skills add InternRobotics/EBench --skill ebench-integrate-policy -a codex`. Or copy the skill folder (skills/ebench-integrate-policy in InternRobotics/EBench) into .agents/skills/ebench-integrate-policy in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add InternRobotics/EBench --skill ebench-integrate-policy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ebench-integrate-policy, .gemini/skills/ebench-integrate-policy, .github/skills/ebench-integrate-policy and .opencode/skills/ebench-integrate-policy in your project.
SKILL.md names no scripts, command-line tools or credentials: Ebench Integrate Policy is instructions for the agent only. Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Ebench Integrate Policy is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Ebench Integrate Policy: Implementing Policy As Code With Open Policy Agent (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Implementing Usb Device Control Policy (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Implementing GCP Organization Policy Constraints (mukul975/Anthropic-Cybersecurity-Skills, 34k stars) and Implementing Container Network Policies With Calico (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
InternRobotics (a GitHub organization) maintains it in InternRobotics/EBench, which has 145 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 24, 2026.
Source: InternRobotics/EBench on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
