BF acpx-bridge-troubleshooting-guide
解决 acpx 桥接超时问题和 OpenClaw 飞书多账户配置。当遇到 acpx 连接 Gateway 超时、initialize 卡住、WebSocket 1005 错误、gateway.token 缺失、acpx 配置错误、飞书多机器人配置、ACP 协议解析失败、bindings 路由不生效等问题时使用。包括创建 token 文件、修复 acpx 配置、更新 acpx 版本、正确配置飞书多账户（使用 accounts 结构而非新建 channel）、使用 openclaw config set 命令而非 jq 直接修改 JSON 等关键步骤。
As a process F 35/100 · Will not run — References files that are not bundled: scripts/gateway-token-check.sh, references/feishu-multi-account-config.md, references/acp-protocol-troubleshooting.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.
- 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: 8. 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/gateway-token-check.sh - warning
missing-refreference to a missing file: references/feishu-multi-account-config.md - warning
missing-refreference to a missing file: references/acp-protocol-troubleshooting.md
Process rating: all ten parameters 35/100
- 0Tools and files. 3 referenced file(s) missing: scripts/gateway-token-check.sh, references/feishu-multi-account-config.md, references/acp-protocol-troubleshooting.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
- 100Steps. 31 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1241 tokens
- 100Running it twice. No mutating operations
- medium 4 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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
- -218 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 277: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.