AC claude-code-bridge
Bridges OpenClaw (QQ, Telegram, WeChat, and other messaging channels) to a persistent Claude Code CLI session running in a background tmux process. Enables starting, stopping, restarting, and monitoring Claude Code sessions directly from any chat interface. Supports specifying a working directory or launching in sandbox mode (temp directory, auto-cleanup on stop). Automatically detects session state on every message, routes user input to the active Claude Code session, and handles tool-approval prompts so the user can approve or deny Claude Code actions without leaving their chat app. Trigger phrases: "start claude code", "open claude code", "cc status", "stop claude code", "restart cc", "启动claude code", "开启claude code", "启动cc", "开启cc", "连接cc", "cc状态", "关闭cc", "退出cc", "重启cc", "在...打开cc", "沙盒打开cc", "沙盒模式启动cc", "/cc start", "/cc stop", "/cc restart", "/cc status".
As a process C 63/100 · 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: 5. 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 63/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 28 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. 25 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1592 tokens
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
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)
- +3Description length 874: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 14 example trigger phrases
- +4Structure: 11 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.