fix(skills): retire human promotion gate — self-promote on genuine readiness

[cursor]

🤖 Generated by the Agentic Engineer (Cursor cloud instance)

Evidence

portfolio-maintenance, product-engineering, and self-improvement still say drafts are human-gated and the agent must never self-promote. Maintainer direction 2026-07-16/18 retired that gate: work in draft, self-promote only on genuine readiness (programmatically tested + green review at head + tried/evaluated as a user), then drive to merge.

Audience / problem

Consumers of these skills (including the agentic-engineering plugin) inherit false instructions that park finished drafts forever waiting for a human promotion that is no longer the model.

Hypothesis

Rewriting the three skills to the genuine-readiness self-promotion model removes the false gate without weakening the draft checkpoint, hygiene pentad, or green-review requirement.

Acceptance criteria

• No "never self-promote" / "human-gated" / "maintainer promotes" go-signal language remains in the three skills
• Draft checkpoint + genuine-readiness self-promotion + Trust-gate merge path are stated clearly
• Guardrails unchanged (never merge external, never weaken safety, evidence-from-own-runs for self-improvement)

Size

S

[coderabbitai]

🔗 Related PRs

#70 - docs: document the npx skills install path alongside gh skill [merged]

---

📝 Issue Planner

_{Check the box below or use the @coderabbitai plan command to generate an implementation plan and prompts that you can use with your favorite coding assistant.}

• Create Plan

---

🧪 Issue enrichment is currently in open beta.

You can configure auto-planning by selecting labels in the issue_enrichment configuration.

To disable automatic issue enrichment, add the following to your .coderabbit.yaml:

issue_enrichment:
  auto_enrich:
    enabled: false

💬 Have feedback or questions? Drop into our discord!