BC patent-professional-agents
📜 专利专业代理 - Patent Professional Agents 一个专业的多代理专利撰写与优化技能套件，覆盖专利申请全流程。 🎯 核心功能： • 场景一：用户想法 → 技术挖掘 → 检索分析 → 专利撰写 → 质量审核 • 场景二：用户初稿 → 问题分析 → 优化建议 → 强化权利要求 • 场景三：代理机构反馈 → 风险评估 → 优化/取消建议 🤖 9个专业代理： tech-miner (技术挖掘)、prior-art-researcher (现有技术检索)、inventiveness-evaluator (创造性评估)、patent-drafter (专利撰写)、claims-architect (权利要求架构)、patent-analyst (专利分析)、patent-auditor (专利审核)、patent-value-appraiser (价值评估)、patent-converter (文档转换) ✨ 特色： • 中英文双语支持 • 7章节标准专利模板 • 授权率预判 • 自动Word文档转换 • 持续学习能力 🔍 搜索关键词：专利, patent, 专利撰写, 专利优化, 现有技术检索, 知识产权, IP, 权利要求, 技术交底书, 创造性评估, 授权率, patent drafting, prior art search, claims, patent prosecution
As a process C 50/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
-
medium Broad scope
meta-agent-memory-dumpagents/claims-architect/SOUL.mdAgent memory / workspace files bundled with the skill (9) — likely a workspace dump with personal data or tokensagents/claims-architect/SOUL.md, agents/inventiveness-evaluator/SOUL.md, agents/patent-analyst/SOUL.md, agents/patent-auditor/SOUL.md, agents/patent-converter/SOUL.md
-
low Dangerous commands
cmd-privilegeagents/patent-converter/convert_patents.py:161Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)"args": ["--no-sandbox", "--disable-setuid-sandbox"]
detectorcode literal
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "dependencies"
Process rating: all ten parameters 50/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4772 tokens
- 100Steps. 31 steps
- 100Consistency. Name and required fields are in place
- low 12 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- -245 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 619: enough signal without eating the budget
- +4Structure: 39 headings
- +3Step-by-step instructions: 31 items
- +3Output format is stated explicitly
- +4Has examples (23 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.