AC paper-reading
Deep-reading framework for academic papers based on the Eight-Elements method (八要素法): author, institution, year, title, research purpose, method, results, and the reader's own immediate reflections. Reads a paper as a dialogue with the author and as one node in the field's evolution — extracting not just conclusions but the thinking behind them (why this question, why this method, what the authors' own analysis of the results says), then guides critical evaluation (what it solved, method strengths, weaknesses, where to go next) and positions the paper on the reader's cumulative literature map. Use when the user provides a paper (full text, PDF path, title, DOI, or link) and wants to read it deeply (精读), dissect it (拆解), make literature notes (文献笔记), judge its value, or accumulate a literature map across papers.
Deep-reading framework for academic papers based on the Eight-Elements method (八要素法): author, institution, year, title, research purpose, method, results, and…
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 52/100
- 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
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 47 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 852 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 822: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 14 headings
- +3Step-by-step instructions: 47 items
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.