AD tianshu-paper-card
把论文摘要或简介整理成「速读卡片」：题目占位、研究问题、方法要点、主要结论、局限、可引用句草稿。 Use when: 学生读文献、写综述、组会前速览；用户说「文献卡片」「摘要整理」「论文笔记模板」。 NOT for: 代替精读全文或学术不端式代写。
As a process D 43/100 · Unfinished process — weak spots: steps, inputs and preconditions, failures and branches
How to improve
For the model run — optional
- 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 · 0
✓ No critical or high findings
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 43/100
- 0Steps. Prose only: no discrete steps
- 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
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 80 tokens
- 100Running it twice. No mutating operations
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
- +3No numbered steps or checklist
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 124: enough signal without eating the budget
- +4Structure: 3 headings
- +3Output format is stated explicitly
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.
External checks
ClawHub: suspicious
The skill set is mostly coherent for ClawHub maintenance, but it includes high-impact moderation workflows and a review helper that grants full local sandbox-bypass authority by default.
LLM: suspicious (medium) · VirusTotal: · 29 May 2026