DeerFlow Smoke Test
bytedance/deer-flow
Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.
Diagnose and repair failures in this repository's BundleSDF or SAM3D HOI object reconstruction workflow.
Install Hoi Object Reconstruction Doctor
$ npx skills add nvidia-isaac/video_to_data --skill hoi-object-reconstruction-doctor -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nvidia-isaac/video_to_data hoi-object-reconstruction-doctor --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/nvidia-isaac/video_to_data.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/hoi-object-reconstruction-doctor .claude/skills/hoi-object-reconstruction-doctor && 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 "hoi-object-reconstruction-doctor" agent skill from https://github.com/nvidia-isaac/video_to_data/tree/main/.claude/skills/hoi-object-reconstruction-doctor into .claude/skills/hoi-object-reconstruction-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hoi-object-reconstruction-doctor", 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/nvidia-isaac/video_to_data/tree/main/.claude/skills/hoi-object-reconstruction-doctorType 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 nvidia-isaac/video_to_data --skill hoi-object-reconstruction-doctor -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nvidia-isaac/video_to_data hoi-object-reconstruction-doctor --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nvidia-isaac/video_to_data.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/hoi-object-reconstruction-doctor .agents/skills/hoi-object-reconstruction-doctor && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "hoi-object-reconstruction-doctor" agent skill from https://github.com/nvidia-isaac/video_to_data/tree/main/.claude/skills/hoi-object-reconstruction-doctor into .agents/skills/hoi-object-reconstruction-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hoi-object-reconstruction-doctor", 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 nvidia-isaac/video_to_data --skill hoi-object-reconstruction-doctor -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nvidia-isaac/video_to_data hoi-object-reconstruction-doctor --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nvidia-isaac/video_to_data.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/hoi-object-reconstruction-doctor .cursor/skills/hoi-object-reconstruction-doctor && 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 "hoi-object-reconstruction-doctor" agent skill from https://github.com/nvidia-isaac/video_to_data/tree/main/.claude/skills/hoi-object-reconstruction-doctor into .cursor/skills/hoi-object-reconstruction-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hoi-object-reconstruction-doctor", 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/nvidia-isaac/video_to_data.git --path .claude/skills/hoi-object-reconstruction-doctor--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 nvidia-isaac/video_to_data --skill hoi-object-reconstruction-doctor -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nvidia-isaac/video_to_data hoi-object-reconstruction-doctor --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nvidia-isaac/video_to_data.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/hoi-object-reconstruction-doctor .gemini/skills/hoi-object-reconstruction-doctor && 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 "hoi-object-reconstruction-doctor" agent skill from https://github.com/nvidia-isaac/video_to_data/tree/main/.claude/skills/hoi-object-reconstruction-doctor into .gemini/skills/hoi-object-reconstruction-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hoi-object-reconstruction-doctor", 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 nvidia-isaac/video_to_data hoi-object-reconstruction-doctorInstalls 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 nvidia-isaac/video_to_data --skill hoi-object-reconstruction-doctor -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nvidia-isaac/video_to_data.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/hoi-object-reconstruction-doctor .github/skills/hoi-object-reconstruction-doctor && 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 "hoi-object-reconstruction-doctor" agent skill from https://github.com/nvidia-isaac/video_to_data/tree/main/.claude/skills/hoi-object-reconstruction-doctor into .github/skills/hoi-object-reconstruction-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hoi-object-reconstruction-doctor", 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 nvidia-isaac/video_to_data --skill hoi-object-reconstruction-doctor -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nvidia-isaac/video_to_data hoi-object-reconstruction-doctor --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nvidia-isaac/video_to_data.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/hoi-object-reconstruction-doctor .opencode/skills/hoi-object-reconstruction-doctor && 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 "hoi-object-reconstruction-doctor" agent skill from https://github.com/nvidia-isaac/video_to_data/tree/main/.claude/skills/hoi-object-reconstruction-doctor into .opencode/skills/hoi-object-reconstruction-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hoi-object-reconstruction-doctor", 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.
Facts
- Skill name
hoi-object-reconstruction-doctor- GitHub stars
- 861
- Token cost
- ~1k tokens
- SKILL.md length
- 453 words
- Files
- 2
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Diagnose and repair failures in this repository's BundleSDF or SAM3D HOI object reconstruction workflow.
- Works in 5 steps: Read the exact command and error from… → If no job directory is named, inspect… → Infer the mode from the command and… → …
- Setup checks fail
- SKILL.md covers Discover context automatically, Run the fast diagnostic set, Classify the first failure and Detect a stall correctly, plus 1 more section
- Calls python, docker and git
What it does
Hoi Object Reconstruction Doctor is an agent skill from nvidia-isaac/video_to_data. Diagnose and repair failures in this repository's BundleSDF or SAM3D HOI object reconstruction workflow. Use when setup checks fail, Docker or GPU access is broken, weights or images are missing, input preflight fails, CuSFM or scan-quality gates fail, a BundleSDF stage produces bad geometry, FoundationPose alignment fails, SAM3D inference or EGL rendering fails, a job stalls, or final GLB and review artifacts are missing or invalid.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Testing & QA, covering Quality gates and Containers. It works with Docker. The repository describes itself as: Nvidia Isaac Video to Data Pipeline.
When your agent uses it
- Setup checks fail
- GPU access is broken
- Images are missing
- Input preflight fails
Example prompts
- “/hoi-object-reconstruction-doctor”
Requirements
- Python 3
- Docker
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Read the exact command and error from the conversation or available log.
- If no job directory is named, inspect the newest directory under
- Infer the mode from the command and artifacts
- Infer the input from the recorded command or job metadata.
- Ask one focused question only if neither logs nor a job directory can be
What it can do on your machine
Read from SKILL.md and the folder at commit 193382a. 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
Shell commands in SKILL.md call:
pythondockergit
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use docker and git, which can reach the network depending on how they are called.
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
Hoi Object Reconstruction Doctor loads about 1k tokens when it runs. Until then it costs about 118 tokens; SKILL.md has 453 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.
Safety
Auto-check passed
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.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 453 words (~1,027 tokens).
“Inspect evidence first and ask later. Work from reconstruction/, preserve the job directory, and diagnose the first bad stage instead of rebuilding everything.”
- name
- hoi-object-reconstruction-doctor
Files
SKILL.md and 1 other file in .claude/skills/hoi-object-reconstruction-doctor of nvidia-isaac/video_to_data.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 193382a
Compare with similar skills
Hoi Object Reconstruction Doctor 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 |
|---|---|---|---|---|---|---|
| Hoi Object Reconstruction Doctor this skillnvidia-isaac/video_to_data | 861 | — | ~1k | Automated safety check: Pass | Custom licence | |
| DeerFlow Smoke Testbytedance/deer-flow | 84k | — | ~2.5k | Automated safety check: Notes | MIT | |
| Dqd Labctrsploit/ctrsploit | 154 | — | ~1.6k | Automated safety check: Pass | None | |
| Suite ConverterMargin-Lab/evals | 160 | — | ~3.7k | Automated safety check: Pass | AGPL-3.0 | |
| Benchflow Experiment Reviewbenchflow-ai/benchflow | 356 | — | ~4k | Automated safety check: Pass | Apache-2.0 | |
| Run SDK Testsrestatedev/sdk-typescript | 125 | — | ~745 | Automated safety check: Pass | MIT |
Similar skills
Dqd Lab
ctrsploit/ctrsploit
Manage ctrsploit dqd lab environments from github.com/ctrsploit/dqd.
Suite Converter
Margin-Lab/evals
Converts test suites from external eval frameworks into the Margin Eval suite format.
Benchflow Experiment Review
benchflow-ai/benchflow
Review Benchflow or SkillsBench task-run trajectories and integration-test Benchflow code changes.
Run SDK Tests
restatedev/sdk-typescript
Run the Restate SDK conformance test suite locally against this SDK's Docker image.
Crabbox Setup
AI-Builder-Club/skills
Scaffold an isolated CLOUD dev box per agent (via crabbox + Daytona) for any codebase — the parallel-safe counterpart to dev-local-setup.
More from nvidia-isaac/video_to_data
All 13 skills in this repoHoi Object Reconstruction Setup
nvidia-isaac/video_to_data
Prepare this repository's HOI object reconstruction environment for BundleSDF or SAM3D.
Run Mv Hoi Reconstruction
nvidia-isaac/video_to_data
Run and validate the repository-local multi-view camera calibration and human-object reconstruction pipelines.
Ego Reconstruction Setup
nvidia-isaac/video_to_data
Prepare the repository-local egocentric reconstruction pipeline for Codex-driven work.
Groot Finetune
nvidia-isaac/video_to_data
Run and extend embodiment-aware GR00T N1.7 post-training workflows from successful robot-policy collection through semantic recording, LeRobot conversion, statistics, fine-tuning, open-loop…
Run Ego Reconstruction Video
nvidia-isaac/video_to_data
Run the egocentric reconstruction pipeline on an input video.
Hoi Object Reconstruction Run
nvidia-isaac/video_to_data
Launch, monitor, resume, and verify this repository's BundleSDF or SAM3D HOI object reconstruction pipeline.
Related
Works with
Categories
Questions about Hoi Object Reconstruction Doctor
What does Hoi Object Reconstruction Doctor do?
Diagnose and repair failures in this repository's BundleSDF or SAM3D HOI object reconstruction workflow. Hoi Object Reconstruction Doctor is an agent skill from nvidia-isaac/video_to_data. Diagnose and repair failures in this repository's BundleSDF or SAM3D HOI object reconstruction workflow.
When should I use Hoi Object Reconstruction Doctor?
Hoi Object Reconstruction Doctor fits situations like: setup checks fail; GPU access is broken; images are missing; input preflight fails.
How do I install Hoi Object Reconstruction Doctor in Claude Code?
Run `npx skills add nvidia-isaac/video_to_data --skill hoi-object-reconstruction-doctor -a claude-code`. Or copy the skill folder (.claude/skills/hoi-object-reconstruction-doctor in nvidia-isaac/video_to_data) into .claude/skills/hoi-object-reconstruction-doctor in your project. Claude Code loads it when a task matches its description.
How do I install Hoi Object Reconstruction Doctor in Codex?
Run `npx skills add nvidia-isaac/video_to_data --skill hoi-object-reconstruction-doctor -a codex`. Or copy the skill folder (.claude/skills/hoi-object-reconstruction-doctor in nvidia-isaac/video_to_data) into .agents/skills/hoi-object-reconstruction-doctor in your project. Codex loads it when a task matches its description.
Can I use Hoi Object Reconstruction Doctor in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nvidia-isaac/video_to_data --skill hoi-object-reconstruction-doctor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hoi-object-reconstruction-doctor, .gemini/skills/hoi-object-reconstruction-doctor, .github/skills/hoi-object-reconstruction-doctor and .opencode/skills/hoi-object-reconstruction-doctor in your project.
What does Hoi Object Reconstruction Doctor need to run?
Going by SKILL.md and its folder, Hoi Object Reconstruction Doctor needs the command-line tools its instructions call (python, docker and git). Our summary lists: Python 3; Docker.
Does Hoi Object Reconstruction Doctor access the network?
SKILL.md contains no URLs. Its commands use docker and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Hoi Object Reconstruction Doctor safe to install?
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.
What licence does Hoi Object Reconstruction Doctor use?
Hoi Object Reconstruction Doctor has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Hoi Object Reconstruction Doctor use?
About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Hoi Object Reconstruction Doctor?
Skills that share tags, products or a category with Hoi Object Reconstruction Doctor: DeerFlow Smoke Test (bytedance/deer-flow, 84k stars), Dqd Lab (ctrsploit/ctrsploit, 154 stars), Suite Converter (Margin-Lab/evals, 160 stars) and Benchflow Experiment Review (benchflow-ai/benchflow, 356 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Hoi Object Reconstruction Doctor?
nvidia-isaac (a GitHub organization) maintains it in nvidia-isaac/video_to_data, which has 861 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 8, 2026.
Source: nvidia-isaac/video_to_data on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.