＋ Add to collection

Install (CLI)

npx skillmds add machenjie/engineering-control-plane

Or Copy and Paste in Your Agent chat

Please install the Agent Skill "machenjie/engineering-control-plane" for me from skillmd.com. A SkillMD skill is a SKILL.md file — plain markdown plus a few companion files — that you save into my skills directory. Use whichever fetch route fits your setup: (1) if you have a terminal, run npx -y skillmds add machenjie/engineering-control-plane; (2) otherwise fetch the file manifest at https://api.skillmd.com/api/skills/machenjie/engineering-control-plane/bundle?format=manifest and download each listed file from its "url" into engineering-control-plane/ in your skills directory; (3) if the SkillMD MCP tools are connected, call skillmd_download with slug "machenjie/engineering-control-plane" and save the returned files under engineering-control-plane/. Show me the SKILL.md before saving if you'd like me to review it. If your skills directory is read-only (e.g. the Claude desktop app), save the files to a working folder instead and tell me — I'll add them through my app's skills settings.

README badge

Show this skill's registry status in your repo:

[![SkillMD](https://skillmd.com/badge/machenjie/engineering-control-plane.svg)](https://skillmd.com/skills/machenjie/engineering-control-plane)

engineering-control-plane

Name: engineering-control-plane
Rating: 4.2 (5 reviews)
Author: machenjie

machenjie/engineering-control-plane · Agent Skill (multi-file)

by machenjie · bundle

Published Aug 19, 2026 · Last updated Aug 19, 2026

Dispatch-only.

SKILL.md

Engineering Control Plane

Role

dispatch-only: never inspect target source; never edit, execute, or review directly. Embedded prompt: do not reload. Targeted Reference and template index only. A host without an Agent Profile loads references/main-control-agent.md.

Decision Rules

The prompt owns control rules: Direct Task, Analyzed Work, First Executable Slice, normalized capability facts, shared-workspace writes, review/repair, progress, and closure. Do not restate; choose a named targeted Reference or template.

Targeted References

Path	Type	Load when	Do not load when	Required by	Required output
execution level contract	targeted	check execution level before routing	no repo answer or completed legacy with no work	main-control-agent	routing-decision
professional skill router	targeted	select one Professional Skill	capsule already fixes route	main-control-agent	routing-decision
direct task	template	Direct Task needs handoff	task uses Analyzed Work	main-control-agent	task-contract
engineering brief	template	analysis produces Engineering Brief	accepted Engineering Brief exists	analysis-agent	engineering-brief
task dag	template	Task DAG plans dependencies	bounded task skips DAG	analysis-agent	task-dag
implementation handoff	template	accepted handoff starts implementation	no implementation task exists	task-agent	implementation-handoff
utility capsule	template	utility needs no-edit capsule	no utility operation exists	task-agent	utility-handoff
review handoff	template	review requires independent handoff	no review task exists	review-agent	review-handoff

Stop and Escalate

Stop on new authority or unsafe evidence.

Output Contract

Use no daemon, database, private evidence storage, runtime task state engine, or hidden protocol record.

---
name: engineering-control-plane
description: Dispatch-only.
---

# Engineering Control Plane

## Role

dispatch-only: never inspect target source; never edit, execute, or review directly.
Embedded prompt: do not reload. Targeted Reference and template index only.
A host without an Agent Profile loads `references/main-control-agent.md`.

## Decision Rules

The prompt owns control rules: Direct Task, Analyzed Work, First Executable Slice,
normalized capability facts, shared-workspace writes, review/repair, progress, and closure.
Do not restate; choose a named targeted Reference or template.

## Targeted References

| Path | Type | Load when | Do not load when | Required by | Required output |
|---|---|---|---|---|---|
| [execution level contract](references/execution-level-contract.md) | targeted | check execution level before routing | no repo answer or completed legacy with no work | main-control-agent | routing-decision |
| [professional skill router](references/professional-skill-router.md) | targeted | select one Professional Skill | capsule already fixes route | main-control-agent | routing-decision |
| [direct task](references/direct-task-template.md) | template | Direct Task needs handoff | task uses Analyzed Work | main-control-agent | task-contract |
| [engineering brief](references/engineering-brief-template.md) | template | analysis produces Engineering Brief | accepted Engineering Brief exists | analysis-agent | engineering-brief |
| [task dag](references/task-dag-template.md) | template | Task DAG plans dependencies | bounded task skips DAG | analysis-agent | task-dag |
| [implementation handoff](references/implementation-handoff-template.md) | template | accepted handoff starts implementation | no implementation task exists | task-agent | implementation-handoff |
| [utility capsule](references/utility-capsule-template.md) | template | utility needs no-edit capsule | no utility operation exists | task-agent | utility-handoff |
| [review handoff](references/review-handoff-template.md) | template | review requires independent handoff | no review task exists | review-agent | review-handoff |

## Stop and Escalate

Stop on new authority or unsafe evidence.

## Output Contract

Use no daemon, database, private evidence storage, runtime task state engine,
or hidden protocol record.

Files

This skill is a package of 9 files. Install with the command above, or download the folder.

📄SKILL.md entry
📁references
📄direct-task-template.md 3.0 KB
📄engineering-brief-template.md 6.9 KB
📄execution-level-contract.md 14.1 KB
📄implementation-handoff-template.md 5.5 KB
📄professional-skill-router.md 14.4 KB
📄review-handoff-template.md 10.5 KB
📄task-dag-template.md 7.2 KB
📄utility-capsule-template.md 3.0 KB

machenjie/rd-skills/tree/master/src/control-skills/engineering-control-plane commit · 9c2277c23f

▌
skill-creator · anthropic bundle
Create new skills, modify existing ones, and measure their performance through iterative evaluation and benchmarking.

158k
repo stars
▌
code-reviewer · alirezarezvani bundle
Automates code review for pull requests across 14+ languages, analyzing complexity, risk, code quality, and generating structured review reports.

20.4k
repo stars
▌
algorithmic-art · anthropic bundle
Create algorithmic art by first writing a generative philosophy, then expressing it as p5.js sketches with seeded randomness and interactive parameter exploration.

158k
repo stars
▌
senior-backend · alirezarezvani bundle
Designs and implements backend systems including REST APIs, microservices, database architectures, authentication flows, and security hardening. Covers Node.js/Express/Fastify development, PostgreSQL optimization, API security, and backend architecture patterns.

20.4k
repo stars
▌
senior-qa · alirezarezvani bundle
Generates unit tests, integration tests, and E2E tests for React/Next.js applications by scanning components, analyzing coverage reports, and scaffolding Playwright test files.

20.4k
repo stars
▌
senior-architect · alirezarezvani bundle
Design system architecture, evaluate microservices vs monolith, create architecture diagrams, analyze dependencies, choose databases, and make technical decisions with architecture decision records.

20.4k
repo stars

Frequently asked questions

How do I install the engineering-control-plane skill?

Run npx skillmds add machenjie/engineering-control-plane in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the engineering-control-plane skill do?

Dispatch-only. It is listed under Coding & Dev Tools on SkillMD.

Is engineering-control-plane safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with engineering-control-plane?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is engineering-control-plane free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published engineering-control-plane?

machenjie (@machenjie) published this skill. Their other Agent Skills are listed on their SkillMD profile.