CD llm-endpoint-switching
把脚本里的 LLM 从一个 OpenAI 兼容端点/模型换到另一个时的排查手册。 重点覆盖三类必踩的坑：**Cloudflare 拦 urllib 默认 UA 导致 403 「error code: 1010」**（会被误判成 key 无效，换真 key 也照样403）、 **切到免 key 端点时空串是真值陷阱**（`configure()` 用 `if api_key:` 会让旧付费 key 沿用 → 必 401），以及**先 --ping 预检再跑批量**的做法。 当用户说「换成 XX 模型」「加个模型」「这个 API 报 403 / 400 / 404」 「AI 调用失败」「key 明明是对的却说无效」「怎么切模型」 「换成免 key 的模型」「切过去之后 401」时使用。
把脚本里的 LLM 从一个 OpenAI 兼容端点/模型换到另一个时的排查手册。 重点覆盖三类必踩的坑：Cloudflare 拦 urllib 默认 UA 导致 403 「error code: 1010」（会被误判成 key 无效，换真 key 也照样403）、 切到免 key…
As a process D 41/100 · Unfinished process — References files that are not bundled: scripts/test_ai_verify.py
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: 2. 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: scripts/test_ai_verify.py - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 41/100
- 0Tools and files. 1 referenced file(s) missing: scripts/test_ai_verify.py
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 100Steps. 11 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1746 tokens
- 100Running it twice. No mutating operations
- low 10 top-level sections: this looks like several domains in one skill
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
- -226 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 345: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 11 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.