AC paper-reorganizer
This skill should be used when the user wants to reorganize and deepen a journal paper based on given requirements. It guides WorkBuddy through a structured six-phase workflow: (1) parsing the paper and extracting the core thesis, (2) extracting and rebuilding the outline, (3) reviewing and critiquing the outline, (4) splitting the paper by chapters, (5) iteratively deepening each chapter through multi-round argumentation with Chinese and foreign literature support, and (6) integrating and performing a final consistency check. The skill enforces strict rules: each chapter must be deepened independently with repeated argumentation, must stay connected to the overall core thesis, must not go off-topic, and must not repeat content from other chapters. Literature search covers CNKI, Web of Science, Google Scholar and other databases. Trigger phrases include "整理论文大纲", "深化论文章节", "重新归纳期刊论文", "对论文进行分章深化", "帮我整理这篇论文", "按大纲深化论文", "搜集文献".
As a process C 59/100 · 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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 59/100
- 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
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 65 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 979 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 941: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 20 headings
- +3Step-by-step instructions: 65 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.