skills/coding-agent-orchestrator/skills/coding-agent/SKILL.md
Implementation/review workflow for approved plans. Route ACP-first, then CLI fallback. Use after explicit APPROVE.
npx skillsauth add aaaaqwq/agi-super-skills coding-agentInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Only execute this skill after explicit approval in the current conversation context:
APPROVEApproval must correspond to the latest pending plan in-context.
If no matching approved plan exists, stop and request:
Run /plan first, then reply APPROVE.
command -v codex && codex --versioncommand -v timeoutcommand -v ghcommand -v claude || test -x ~/.claude/local/clauderg, git status, git diff, docs).scripts/plan-review or scripts/plan-review-live.codex review --base ... (or safe-review.sh wrapper).For harness-style implementation/review requests, ACP routing is mode-specific:
acpx) with CLI fallback.codex review --base first, then ACP fallback.CODING_AGENT_ACP_ENABLE=0.CODING_AGENT_ACPX_CMD.CODING_AGENT_ACP_AGENT (default: codex).CODING_AGENT_VERBOSE controls execution progress verbosity. Default is off.
off (default): concise progress updates.on: include structured progress updates with Now, Why, and Next.Accepted truthy values (case-insensitive): 1, true, on, yes, verbose.
Accepted falsy values: unset, 0, false, off, no.
When verbose mode is on:
Now/Why/Next format.Verbosity must not block execution. After explaining intent, proceed immediately unless waiting on a required user decision or an explicit approval gate. Status updates are not a wait state: if the next step is executable, run it in the same turn.
For wrapper/CLI runs expected to exceed 30 seconds:
RUN_EVENT start.RUN_EVENT heartbeat every 20 seconds while running.RUN_EVENT interrupted immediately on signal/timeout/interruption.RUN_EVENT failed on non-interruption errors.RUN_EVENT done on success.Open only the references needed for the current task:
references/WORKFLOW.mdreferences/STANDARDS.mdreferences/tooling.mdreferences/codex-cli.mdreferences/claude-code.mdreferences/reviews.mdtesting
AI驱动的智能浏览器自动化工具。使用LLM理解页面并自动执行任务,比传统Playwright更智能、更省token。适用于复杂交互、动态页面、需要智能决策的浏览器操作。Chrome浏览器优先。
tools
网页登录态管理。使用 fast-browser-use (fbu) 管理各平台登录状态,定期检查可用性,新平台授权时自动保存 profile。
development
Monitor and report on API provider quotas, balances, and usage. Query official providers (Moonshot, DeepSeek, xAI, Google AI Studio) and relay/proxy providers (Xingjiabiapi, Aixn, WoW) via their billing APIs. Also checks subscription services (Brave Search, OpenRouter). Generates quota reports. Triggers on "查额度", "API余额", "quota check", "billing report", "api balance", "供应商额度", "中转站余额", "费用报告", "check balance", "how much credit".
development
# A股基金监控 Skill A股基金净值监控,支持实时估值和盘后净值,自动判断交易日/节假日。 ## 用法 ### 快速监控(命令行) ```bash # 默认配置,输出到控制台 bash ~/clawd/skills/a-fund-monitor/scripts/monitor.sh # 推送到群(使用--push参数) bash ~/clawd/skills/a-fund-monitor/scripts/monitor.sh --push # 监控指定基金 bash ~/clawd/skills/a-fund-monitor/scripts/monitor.sh --codes "000979 002943" ``` ### Agent调用 ``` 执行A股基金监控任务。 1. 读取配置文件: ~/clawd/skills/a-fund-monitor/config.json 2. 获取实时净值数据 3. 非交易日自动切换为简短报告 配置文件格式: { "funds": [ {"code": "000979", "name": "景顺长城沪港深精选股票