Skip to content
Back to skills

Engineering Governance

ASecurity

Apply human decision gates, milestone review, physical-node routing and bounded worker repairs in an authorized multi-agent engineering project. Use for costly jobs, cross-host handoffs, disputed scope or independent result verification; avoid imposing the full profile on routine single-agent fixes.

  • 6 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 11, 2026
ai-agentsrustgonode

Security analysis

A100/100

Pro scans all 7 files and shows the line behind each finding

Scanned November 11, 2026

npx -y skills add TianMingKanae/engineering-multi-ai-skills --skill engineering-governance --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Engineering Governance?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Engineering Governance
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tianmingkanae-engineering-governance/badge)](https://www.skillsdirectory.com/skills/tianmingkanae-engineering-governance)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: engineering-governance
description: Apply human decision gates, milestone review, physical-node routing and bounded worker repairs in an authorized multi-agent engineering project. Use for costly jobs, cross-host handoffs, disputed scope or independent result verification; avoid imposing the full profile on routine single-agent fixes.
---

Apply the project's adopted governance profile within the user's authorization and host instructions. H is the human principal and highest project decision authority, never a model or simulated role. Human decisions override agent consensus and project procedure; they do not manufacture evidence or bypass host constraints.

Read the reference relevant to the task rather than loading the whole suite:
- Scope deadlock, budget stop or decision override: [human-gate.md](references/human-gate.md).
- Expensive runs, idle token cost or review scheduling: [milestone-mode.md](references/milestone-mode.md).
- Missing hardware, entitlement, network capability or cross-host migration: [node-affinity.md](references/node-affinity.md).
- Code ownership, worker self-fixes or blind verification: [role-boundaries.md](references/role-boundaries.md).
- Administrative stalls, scoped autonomy or merged roles: [lean execution](references/lean-execution.md).
- Watcher recovery, quota waits or unproven delivery: [operational health](references/operational-health.md).

Use H/O/F/W/P/C/V/A for the governed profile. I is a compatibility alias for F in the basic walkthrough, not an extra writer. Preserve existing project roles unless the project adopts this profile. A skill does not start agents, enable watchers or expand permissions.

Before declaring a governance improvement, show the observable evidence. Token-reduction percentages require matched workload measurements; a new protocol or successful launch is not a verified outcome.

The role/write limits are starter defaults. A project's explicitly adopted lean profile may assign bounded implementation or operational repairs to another role, with clear file ownership, invariants and task-level limits. Do not require a new acknowledgment for already-authorized ordinary work. Retain prospective scope/resource decisions and independent outcome checking. For expensive staged work, execution-integrity supplies exact-byte packets and durable attempt reservations; a preparation packet is never execution permission.

For cross-provider/physical-node execution, the optional distributed-orchestration skill supplies capability-based assignment and safe tail planning. For source evidence, literature-provenance supplies registry citation checks and exact offline quote location. These are complementary tools, not permission to acquire restricted sources or trust one provider's outputs. Registered runs must freeze executable criteria/tests before data and preserve failed verdicts; toolkit preregistration utilities require a protected anchor and serialized ledger authority.

Files in this skill

  • SKILL.md2.9 KB
  • references/human-gate.md3 KB
  • references/lean-execution.md4.3 KB
  • references/milestone-mode.md3.9 KB
  • references/node-affinity.md3.9 KB
  • references/operational-health.md2.7 KB
  • references/role-boundaries.md5.8 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.