Skip to content

chore(mercator): sync skills - #72

Merged
tempo-github-sts[bot] merged 1 commit into
mainfrom
automation/sync-skills/mercator
Oct 27, 2026
Merged

tempo-github-sts[bot] merged 1 commit into
mainfrom
automation/sync-skills/mercator

Conversation

@tempo-github-sts

Copy link
Copy Markdown
Contributor

Generated from skills.json by .github/workflows/sync-skills.yml. Edit the source, not these copies.

Skill Source Change
mercator-setup tempoxyz/mercator/skills/mercator-setup 598f2470 → 4d40690c

@tempo-github-sts
tempo-github-sts Bot enabled auto-merge (squash) October 27, 2026 16:35
@tempo-github-sts
tempo-github-sts Bot merged commit 56f3c28 into main Oct 27, 2026
6 checks passed
@tempo-github-sts
tempo-github-sts Bot deleted the automation/sync-skills/mercator branch October 27, 2026 16:38

@claude claude Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM. This is a mechanical skill sync plus a version bump from 0.3.2 to 0.3.3.

What was reviewed:

  • The 0.3.3 in manifest.config.ts matches every generated manifest (Claude, Codex with the same +codex.20260929120000 suffix, Cursor, generic, registry) and every golden fixture, including Gemini. No 0.3.2 references are left in the repo.
  • The skills.lock.json entry for mercator-setup changes only its commit and digest, and its path, ref and dest stay the same.
  • The new Diet Mercator text in SKILL.md only adds guidance. It is conservative about payments: finite per-purchase limit, no automatic grant of spending authority, no card fallback when Balance was requested.
Extended reasoning...

The change bumps the mercator plugin's version in its config, its generated manifests and their golden fixtures. It also re-vendors the upstream mercator-setup skill, which adds two blocks of Diet Mercator setup guidance to SKILL.md. No executable code changes. The only sensitive area is agent-facing guidance about payment authorization, and the new text tells the agent to ask the user for limits and approval rather than act on its own. No CODEOWNERS file exists, the timeline has no reviewer objections, and the bug hunt ran dry with no findings.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Development

Successfully merging this pull request may close these issues.

0 participants