AC paper-analyzer
Deep-dive analysis of academic papers, with optional architecture diagrams of the paper's method. Use this skill whenever the user shares a research paper, a paste of paper content, a PDF attachment, or asks to analyze, summarize, critique, or explain a paper. Also trigger when the user passes --draw-structure, asks for a "paper architecture", or wants to visualize a method/pipeline from a paper. Trigger on phrases like "analyze this paper", "read this paper", "deep dive on", "explain the method", "draw this paper's architecture", "visualize this method". Don't wait for explicit skill invocation — if paper content is present, use it.
Deep-dive analysis of academic papers, with optional architecture diagrams of the paper's method.
As a process C 61/100 · Has gaps — weak spots: inputs and preconditions, consistency, running it twice
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: 9. 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 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (paper-analyzer) differs from the folder (paper-reading)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4255 tokens
- 85Steps. 64 steps, 3 vague phrases
- 100Failures and branches. 7 branches, has a failure section
- 100Progress reporting. Reports progress
- low 14 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 641: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 64 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.