industrial-design-robot-brief

Use when the task is to find recent humanoid-robot papers and turn them into Chinese briefs for industrial designers, prioritizing design impact, user experi...

Security Scan

The skill's instructions, scope, and contents are internally consistent with its stated purpose (producing daily Chinese briefs for industrial designers), with no code or install steps — the main caveat is it expects to update a Feishu document but does not declare how Feishu access is provided.

Purpose & Capability

Name, description, and provided references (sources, template, translator, formatter, quality checks) all align: the skill is purely a content-collection/translation/formatting helper for humanoid-robot papers. It does not request unrelated binaries, credentials, or installs.

Instruction Scope

Runtime instructions are specific and constrained: collect recent humanoid papers (arXiv, HF feeds, etc.), apply defined selection/scoring, translate and format into a Feishu document, and run quality checks. The only open item is the step to 'append the result to the same Feishu document' — the SKILL.md assumes a mechanism to write to Feishu but gives no details. Otherwise instructions avoid accessing unrelated system files or secrets and include anti-hallucination checks.

Install Mechanism

No install spec and no code files — instruction-only. This minimizes surface area; nothing is downloaded or written by the skill itself.

Credentials

The skill declares no required environment variables or credentials, which is reasonable for an instruction-only skill. However, it expects to edit a Feishu document; that requires Feishu access (API token/account) in practice. The skill doesn't declare or request Feishu credentials — this may be intentional (relying on the host agent's existing connectors) but is a minor mismatch worth verifying before enabling document-editing behavior.

Persistence & Privilege

always is false, the skill is user-invocable and not force-included. It does not request permanent presence, system-wide config changes, or access to other skills' credentials.

Scan Findings in Context

[no-findings] expected: Regex scanner had no findings; expected because this is an instruction-only skill with no code files for static analysis.

Assessment

This skill appears to do what it says: gather recent humanoid-robot papers, score them for design relevance, translate into concise Chinese briefs, and format them into a Feishu doc. Before installing or enabling it to edit your documents, confirm how the agent will get permission to modify the Feishu document (platform connector, OAuth, or you will paste links). Also: rely on the quality-checks included (they emphasize verifying arXiv IDs, authors, and numeric claims) — ask the agent to show all source links and verification steps before trusting factual details, since the skill delegates web/API access to the hosting agent environment.

Use this skill when the user wants humanoid-robot papers translated into Chinese and rewritten as briefs that industrial designers and product teams can quickly understand.

Goal

Produce a daily brief from recent humanoid-robot papers.

Default behavior:

• collect papers from yesterday in the user's local timezone
• select the top 5 papers
• prioritize industrial design, UX / trust, and product-definition impact
• write in Chinese
• append the result to the same Feishu document
• place the newest day directly below the pinned header

Workflow

1. Read sources to collect and rank candidates.
2. Use the design-impact scoring rules there to choose the final 5.
3. Read translator before writing any paper brief.
4. Read template and follow the exact section order.
5. Read formatter before updating the Feishu document.
6. Run the checks in quality-check before finalizing.

Output Standard

Every paper must help the reader answer:

• Why does this matter for the robot's external shape?
• Why does this matter for internal layout or packaging?
• Why does this matter for user trust, safety, or interaction?
• What kind of product or scenario does this suggest?

If a paper cannot clearly answer at least 2 of those 4 questions, it should usually not be in the final 5.

Defaults

• date_range: yesterday
• count: 5
• language: Chinese
• audience: industrial designers, UX designers, product teams
• doc_name: 🤖 Robot Paper Daily Brief

Hard Rules

• Do not fabricate arXiv IDs, DOI, author names, institutions, or metrics.
• Mark uncertainty explicitly with 待核实, 未找到, or 论文未公开该数据.
• Separate 论文事实 from 设计判断 when making product or design inferences.
• Keep the daily update useful for someone with about 15 minutes to read.