AB multilingual-kb-sync
Add new language translations to customer service response templates and sync them across Feishu Wiki, GitHub, and local files. Use when: (1) adding new languages to KB templates, (2) updating multilingual customer service responses, (3) syncing template changes to Feishu Wiki knowledge base, (4) creating GitHub issues to document template updates, (5) running the full multilingual template update pipeline. Triggers on phrases like "add language", "translate template", "sync to wiki", "update customer service templates", "多语言模板", "新增语种", "同步知识库".
Add new language translations to customer service response templates and sync them across Feishu Wiki, GitHub, and local files.
As a process B 65/100 · Nearly there — weak spots: result and completion, progress reporting
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Exfiltration
net-credential-usescripts/sync-feishu-wiki.sh:90Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl -s -X POST "https://open.feishu.cn/open-apis/docx/v1/documents/${OBJ_TOKEN}/blocks/${OBJ_TOKEN}/children" \vendor-host
Files scanned: 7. 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 65/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 19 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 790 tokens
- 100Running it twice. Mutating operations check current state
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 4 example trigger phrases
- +3Description length 552: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 19 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.