ethan-li-k/astra_bench/clean-table
Claude Code and agent skill by ethan-li-k/astra_bench
- community
Checking that the SKILL.md file is still in the repository.
Clear a tabletop of arbitrary objects by composing atomic skills. Decomposed at runtime by VLM, judged step-by-step, logged for post-training.
Install
npx vskill@latest install ethan-li-k/astra_bench/clean-tableSKILL.md
The same SKILL.md was published earlier as nssmd/roborsi/clean-table.
clean_table (long_horizon)
每个 long_horizon task 自带 task 特定的 progress_judge / posttrain,且只跟此 task 相关——不是平台共享的全局 skill。 共性的判定/训练逻辑在 _lib/(progress_score / pi0_posttrain),子 skill 只是把任务特定的 prompts / 判定标准注入。规划与执行统一走 3-role 三角(LHPlanner → LHExecutor → LHReviewer)。
task 特化
| sub-skill | 它知道的 task 特定信息 | |
|---|---|---|
progress_judge/ | metadata.vlm_prompts.progress_check,每 atomic 跑前/跑后的图像对 | |
posttrain/ | metadata.posttrain.reward_recipe |
执行循环
现状
candidate_atomics 只有 1 个(beat_block_hammer)。这个 long_horizon 暂时无法真跑——它需要 ≥ 2 个 atomic 才有意义。骨架在这是为了让"加新 atomic 后立刻可串起来"成立。
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ethan-li-k/astra_bench/clean-table)