chore(deps): update agent skills

[botantler-1]

Automated update of agent skills to their latest versions.

Updated files under plugins:

1 update(s) available:
  • agent-improvement (devantler-tech/agent-skills) 347a010a > 35ea3c85 [v1.11.15]
Updated agent-improvement
All skills are up to date.
All skills are up to date.
! Skipping github-actions-docs: could not resolve xixu-me/skills: could not determine default branch: HTTP 404: Not Found (https://api.github.com/repos/xixu-me/skills)
All skills are up to date.
All skills are up to date.
All skills are up to date.
All skills are up to date.

[devantler]

🤖 Generated by the Agentic Engineer

@codex review

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.
To continue using code reviews, add credits to your account and enable them for code reviews in your settings.

[devantler]

🤖 Generated by the Agentic Engineer

@cursor review

[devantler]

🤖 Generated by the Agentic Engineer

Self-review (fallback — CodeRabbit, Codex and Cursor Bugbot unavailable)

Reviewed commit: b8806f1da4e995f5902187fa541d4c7287aa2521

Review Lane Status

• CodeRabbit: Unavailable / not installed on repository.
• Codex: Usage limit reached (chatgpt-codex-connector: "You have reached your Codex usage limits for code reviews", 2026-09-09T18:08:46Z).
• Cursor Bugbot: Unavailable / uninstalled on repository.

Semantic Review Assessment

• Upstream skill bump: plugins/agentic-engineering/skills/agent-improvement/SKILL.md updated from refs/tags/v1.11.8 to refs/tags/v1.11.15 (tree sha 35ea3c8567831c51729ff671bfb072ed4efde8cd, commit cfeec834 in devantler-tech/agent-skills).
• Sibling liveness requirement: The added guidance ("Establish sibling liveness before consuming its evidence") matches the reviewed and merged agent-skills#118 commit verbatim, correctly establishing liveness boundaries for sibling scorecards without altering authority or guardrails.
• Marketplace manifests: .claude-plugin/marketplace.json and .github/plugin/marketplace.json bumped in lockstep from 5.0.2 to 5.0.3.
• Plugin manifests: plugins/agentic-engineering/.claude-plugin/plugin.json and plugins/agentic-engineering/plugin.json bumped in lockstep to 5.0.3.
• Desired state: provider-neutral.desired-state.json recomputed skillSha256 matching the new content.
• All 38 CI validation and lint checks pass cleanly.

Verdict: no P0/P1 findings

[devantler]

🤖 Generated by the Agentic Engineer

Self-review (fallback — CodeRabbit, Codex and Cursor Bugbot unavailable)

Reviewed commit: b8806f1d9951fae50ac28872ec9e3ae53a53d8cc

Review Lane Status

• CodeRabbit: Unavailable / not installed on repository.
• Codex: Usage limit reached (chatgpt-codex-connector: "You have reached your Codex usage limits for code reviews", 2026-09-09T18:08:46Z).
• Cursor Bugbot: Unavailable / uninstalled on repository.

Semantic Review Assessment

• Upstream skill bump: plugins/agentic-engineering/skills/agent-improvement/SKILL.md updated from refs/tags/v1.11.8 to refs/tags/v1.11.15 (tree sha 35ea3c8567831c51729ff671bfb072ed4efde8cd, commit cfeec834 in devantler-tech/agent-skills).
• Sibling liveness requirement: The added guidance ("Establish sibling liveness before consuming its evidence") matches the reviewed and merged agent-skills#118 commit verbatim, correctly establishing liveness boundaries for sibling scorecards without altering authority or guardrails.
• Marketplace manifests: .claude-plugin/marketplace.json and .github/plugin/marketplace.json bumped in lockstep from 5.0.2 to 5.0.3.
• Plugin manifests: plugins/agentic-engineering/.claude-plugin/plugin.json and plugins/agentic-engineering/plugin.json bumped in lockstep to 5.0.3.
• Desired state: provider-neutral.desired-state.json recomputed skillSha256 matching the new content.
• All 38 CI validation and lint checks pass cleanly.

Verdict: no P0/P1 findings