AC openclaw-openai-multi-account
Manage multiple OpenAI OAuth login accounts inside OpenClaw, including OpenAI Codex OAuth account snapshots, switching, real active-account detection, 5-hour and weekly quota inspection via Codex CLI cache, ACTIVE metadata repair, auto-enrollment of newly logged-in accounts, same-model auto-rotation near exhaustion, and fallback to a backup model such as Bailian when all OpenAI accounts are unavailable. Use when the user asks about multiple OpenAI OAuth accounts in OpenClaw, OpenAI/Codex account switching, the current real active account, local saved accounts, 5h or weekly remaining quota, OAuth re-login, automatic account rotation, or fallback behavior in OpenClaw.
As a process C 59/100 · Has gaps — weak spots: result and completion, 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: 4. 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 59/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 64 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2168 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
- +1No license
- +2Single-language instructions
- +3Description length 674: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 64 items
- +4Has examples (11 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.