AB simplified-to-traditional
Convert a Simplified-Chinese article in ai-thoughts/docs/ into its Traditional-Chinese twin, and keep the two in sync. The Simplified article is the source of truth and lives as <YYMMDD-slug>-zh-hans.md; the Traditional twin is generated to <YYMMDD-slug>-zh-hant.md with OpenCC (s2twp) plus a permanent cross-link. Use when the user asks to make, sync, or update the Traditional (繁體) version of a Chinese article — "convert to traditional", "做繁體版", "同步繁简", "zh-hant", "繁體". Never runs automatically; acts only on an explicitly named article. Future articles only — do NOT backfill existing files unless the user explicitly orders it.
Convert a Simplified-Chinese article in ai-thoughts/docs/ into its Traditional-Chinese twin, and keep the two in sync.
As a process B 70/100 · Nearly there — weak spots: result and completion, 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 11, 15): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 70/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. No external tools needed
- 100Steps. 35 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 1640 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low The response is described with custom markup (10 tags): a typed call is more reliable
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
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 633: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (2 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.