BF doubao-opencli
豆包（Doubao）AI 助手 OpenCLI 技能包。通过 opencli browser 桥接复用 Edge 浏览器登录态， 提供豆包对话、AI 播客生成（文字/网页链接/PDF 三种输入方式，自动裁剪广告）、 PPT 生成、图像生成（文生图）、会议摘要、批量提问、对话备份等功能。 使用场景：(1) 需要通过 CLI 或脚本自动化操作豆包时；(2) 需要批量生成播客/图片/PPT时； (3) 需要备份豆包对话记录时。前置条件：Edge 已登录 https://www.doubao.com/chat，opencli 已安装。
As a process F 33/100 · Will not run — References files that are not bundled: ../../knowledge/doubao-podcast-bug-fix.md
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: ../../knowledge/doubao-podcast-bug-fix.md
Process rating: all ten parameters 33/100
- 0Tools and files. 1 referenced file(s) missing: ../../knowledge/doubao-podcast-bug-fix.md
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 100Steps. 72 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1979 tokens
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)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -213 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 266: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 72 items
- +4Has examples (7 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.