AB docx-trackdiff
Compare two versions of a .docx document and produce a single Word file in tracked-changes (revision / tracking) mode, as if a human had edited the old file into the new one with Track Changes turned on. Use whenever the user has two versions of a DOCX (e.g., successive drafts of a paper, report, or contract — often AI-generated or AI-assisted revisions) and wants to see the differences as native Word revisions (insertions/deletions) that can be accepted/rejected in Word. Triggers: "对比两个版本的 docx", "tracked changes", "tracking mode", "修订模式对比", "compare two Word documents", "diff two drafts", "生成修订对比文件". Do NOT use for: creating new documents from scratch (use docx skill), single-file editing with revisions (use docx WIR engine), or PDF-only comparisons.
Compare two versions of a .docx document and produce a single Word file in tracked-changes (revision / tracking) mode, as if a human had edited the old file…
As a process B 76/100 · Nearly there — weak spots: inputs and preconditions, 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 76/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 11 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 760 tokens
- 100Progress reporting. Reports progress
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
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 762: enough signal without eating the budget
- +4Structure: 4 headings
- +3Step-by-step instructions: 11 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 100.