agent-contracts-contracts-ci
Make contract-driven agents safe to change with strict validation, architecture docs, and contract diffs in CI.
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。
菜单
Make contract-driven agents safe to change with strict validation, architecture docs, and contract diffs in CI.
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。
基于 SOC 职业分类
| name | agent-contracts-contracts-ci |
| description | Make contract-driven agents safe to change with strict validation, architecture docs, and contract diffs in CI. |
| metadata | {"short-description":"Contracts in CI"} |
Use this skill when you want a stable workflow for changing agents safely (team + CI).
strict=True)visualize)diff)pytestagent-contracts validate --strict --module <your.nodes>agent-contracts visualize --module <your.nodes> --output ARCHITECTURE.mdagent-contracts diff between two versions/modulesdiff PracticallyPick one pattern:
myapp/agents/v1.py and myapp/agents/v2.py as sources for --from-module/--to-moduleagent-contracts diff in two checkouts (CI jobs) and compare outputsdocs/cli.mddocs/roadmap.mddocs/skills/official/agent-contracts-contracts-ci/references/checklist.mdBuild a production-minded AI agent using agent-contracts (contracts, slices, validation, graph, runtime, CLI tooling).
Build an API-oriented agent using AgentRuntime/StreamingRuntime with predictable request/response slices and session support.
Build question/answer style agents using InteractiveNode, explicit routing, and workflow slices.
Tune routing with TriggerCondition priorities, LLM hints, context_builder, and traceable decisions.
Implement tool-using or retrieval-style nodes with services, dependency injection, and safe LLM context building.