메뉴
Generate Claude Agent SDK Python code scaffolding from a validated MECE decomposition. Use when user says "export to Agent SDK", "generate agent code", "create SDK scaffolding", or wants to turn a decomposition tree into runnable Python code.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Opt the current project into down-tier model delegation by installing a standalone .claude/rules/model-delegation.md rule, optionally with pre-shaped .claude/agents/ definitions (fast-executor, task-coder) and an optional agent-state feedback layer. The rule tells Claude to route well-specified data and coding tasks to a cheaper model in a subagent, keeping judgment-heavy work in the main loop. Use when the user says "set up model routing", "set up model delegation", "use cheaper models for subagents", "delegate to a lower-power model", or wants to remove or update that rule.
Pre-share scan for leaked secrets and privacy-sensitive content. Wraps simonw/scan-for-secrets for literal matching (with JSON/URL/HTML/backslash/unicode escape variants) and composes a ripgrep regex pass for shape-based leaks (other users' home paths, emails, IPv4, MAC, JWTs, API keys). Use when user says "scan for secrets", "check for leaked credentials", "pre-share scan", "redact home paths", "PII scan", "strip my username from transcripts", "scan logs before publishing", "check before sharing", "audit before commit", "find leaked API keys", "scan agent transcript".
Convert JavaScript and TypeScript projects to use bun instead of npm/yarn/pnpm. Use when user asks to "migrate from npm to bun", "convert to bun", "switch package managers", "replace npm", or "use bun instead". Includes conversion tables and lock file migration. Core conventions auto-loaded via SessionStart hook; invoke /dev-conventions:bun-tooling for full reference.
Audit project dependencies for known vulnerabilities using uv audit (Python) and bun audit (JS/TS). Use when user says "audit dependencies", "check for vulnerabilities", "security audit", "check deps", "are my packages safe", "CVE check", "dependency security", "vulnerability scan". Invoke with /dev-conventions:dep-audit.
Documentation conventions: last-updated dates, lowercase filenames, internal/ subfolder for non-shared docs, session logs, and documenting the "why". Use when creating or updating documentation, READMEs, or design docs. Invoke with /dev-conventions:doc-conventions. Triggers on "write docs", "update README", "document this", "add a design doc", "session log".
Detailed Python/uv conversion reference. Core conventions auto-loaded via SessionStart hook; invoke /dev-conventions:python-tooling for full conversion tables. Use when you need the complete uv command mapping, version pinning strategy, or lock file workflow.
| name | export |
| description | Generate Claude Agent SDK Python code scaffolding from a validated MECE decomposition. Use when user says "export to Agent SDK", "generate agent code", "create SDK scaffolding", or wants to turn a decomposition tree into runnable Python code. |
| metadata | {"author":"Fred Bliss","version":"0.4.1","last_verified":"2026-04-02"} |
Generate Claude Agent SDK Python code from a validated MECE decomposition tree.
/export <decomposition JSON or file path>
Examples:
/export after a /decompose session (exports the last output)/export output.json/export then paste decomposition JSONThe decomposition must pass validation first (overall score >= 0.70). If not validated, I'll run /validate first and show any issues.
Using the mapping rules from references/agent_sdk_mapping.md:
Agent definition per agent atom"""
Agent SDK scaffolding for: [Decomposition Scope]
Dimension: [temporal/functional/etc.]
"""
import asyncio
from agents import Agent, Runner, function_tool
# Node 1.1.1: Step Name
step_name_agent = Agent(
name="step-name",
model="claude-sonnet-4-6",
instructions="""...""",
tools=[...],
)
# Orchestration
async def execute_phase_1(input_data: str) -> str:
"""Phase 1 (sequential orchestration)"""
result = input_data
result = await execute_step_1(result)
result = await execute_step_2(result)
return result
async def main(input_data: str) -> str:
return await execute_root(input_data)
if __name__ == "__main__":
result = asyncio.run(main("initial input"))
print(result)
The mece-export-sdk MCP tool renders a preview panel with the generated code and a copy button.
main() entry point that executes the full tree/decompose or /interview