AC paper-kb
Research paper knowledge base for storing and querying academic papers. Activate when: 1. User shares an arxiv link or PDF file AND expresses intent to save/store it — keywords: "入库"、"存到知识库"、"加到知识库"、"帮我存"、"收藏"、"记录一下"、"保存起来"、"加进去"、"科研知识库" 2. User says something like "帮我加到我的科研知识库" after receiving paper info 3. User queries their personal knowledge base — keywords: "知识库里有没有"、"帮我查一下存过的"、"有没有我之前存的"、"查一下知识库" Do NOT activate when user only wants to summarize, discuss, or analyze a paper without any storage or query intent.
Research paper knowledge base for storing and querying academic papers.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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: 13. 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 51/100
- 0Result and completion. Does not say what the result is
- 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. 1 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 13 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1831 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -33 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 527: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (14 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.