菜单
Trigger-driven automation definitions and runner management. Use when creating, running, or managing skill-based automation pipelines.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
DEEP multi-step research harness. Decomposes queries into sub-questions, executes parallel web searches via Pieces MCP, iteratively refines with gap detection, and synthesizes cited reports. Architecture inspired by GPT Researcher (27.6k stars), Vane/Perplexica (35.2k stars), and Gemini Deep Research. Use when user asks for deep research, investigation, analysis, comparison, or any task requiring exhaustive web research.
DEFAULT THINKING MODE — not a feature, but how the agent operates. Every task gets innovation-overdrive thinking: research, ground, reflect on contradictions, propose, then build. This is the agent's identity, not a command. Integrates MiMo-Code's 6-phase memory consolidation.
Chain execution manager: validates dependencies, enforces order, tracks violations. Use to verify that all required skill chains were executed and to get the correct execution order.
API design patterns, REST conventions, and endpoint standards. Use when creating or modifying API endpoints. Covers routing, request/response patterns, error handling, and versioning.
Architectural design, system patterns, and dependency management. Use when designing new modules, refactoring existing systems, or making architectural decisions. Covers layering, coupling, cohesion, and design patterns.
DEFAULT THINKING MODE — not a feature, but how the agent operates. Every task gets innovation-overdrive thinking: research, ground, reflect on contradictions, propose, then build. This is the agent's identity, not a command. Integrates MiMo-Code's 6-phase memory consolidation.
基于 SOC 职业分类
| name | automation |
| description | Trigger-driven automation definitions and runner management. Use when creating, running, or managing skill-based automation pipelines. |
| chains_with | ["quality","automated-learning"] |
Automations connect triggers (events, schedules, file changes) to skill pipelines (our 25 skills) to produce actions (PRs, comments, Slack messages, reports).
Each automation is a YAML file in automations/definitions/ that declares:
| Type | How to Fire | Example |
|---|---|---|
github | PR opened/pushed | automate.py run pr-security-review |
cron | Scheduled via system crontab | automate.py cron-install |
file_watch | File changes on disk | automate.py watch . |
cli | Manual invocation | automate.py run generate-docs |
# List all available automations
python .opencode/scripts/automate.py list
# Run an automation once
python .opencode/scripts/automate.py run pr-security-review
# Run all automations
python .opencode/scripts/automate.py run-all
# Watch directory for file changes (daemon)
python .opencode/scripts/automate.py watch .
# Install cron jobs from automation schedules
python .opencode/scripts/automate.py cron-install
# View run history
python .opencode/scripts/automate.py status
automations/definitions/python .opencode/scripts/automate.py run <name>Pipelines compose skills sequentially. Each step can be:
"security"{skill: "security", config: {severity: "high"}}{skill: "security", when: "severity == critical"}| Template | Trigger | Pipeline | Action |
|---|---|---|---|
| PR Security Review | GitHub PR | exhaustive-crosscheck → security → code-hardener | PR comment + Slack alert |
| Nightly Audit | Cron | quality → security → performance | File report + log |
| Add Test Coverage | GitHub PR | testing → quality → python | PR comment |
| Find Critical Bugs | Cron | exhaustive-crosscheck → debugging → code-hardener | Draft PR + log |
| Generate Docs | CLI | documentation → communication | Git commit |
| Weekly Summary | Cron | communication → data-science | File report |