Summary

Stop appending the full available skill catalog to the skill tool definition.

Why

The skill catalog is already exposed through the system/discovery path. Duplicating it inside the tool definition makes the prompt heavier and can make skill availability appear in two places that drift in wording or filtering behavior.

Related Issue

Ports the behavior from upstream anomalyco/opencode#31269. There is no local PawWork issue for this narrow upstream-value PR.

Human Review Status

Pending

Review Focus

Please check that the registry only removes the duplicated catalog from the skill tool definition and does not change skill execution or the skill tool's base description.

Risk Notes

Harness/tool-description behavior changed for skill. No visible UI changed, so the UI check is not applicable. No docs, release notes, dependencies, credentials, deletion behavior, generated content, or local file changes are included. No platform/packaging surface was touched.

How To Verify

RED: bun test test/tool/skill.test.ts failed because the skill tool description still contained `tool-skill` from the duplicated catalog.
Focused skill tests: bun test test/tool/skill.test.ts -> 4 pass, 0 fail.
Typecheck: bun run typecheck in packages/opencode -> passed.
Diff check: git diff --check -> passed.

Screenshots or Recordings

Not applicable; no visible UI changed.

Checklist

How to use this checklist:

• Tick a box by replacing [ ] with [x]. Do not edit, add, or remove items.
• The bot-applied label items can only be honestly ticked AFTER the PR is opened and the labeler / priority-triage bots have run — return to the PR description and tick them then.
• Most items are required. The few that are conditional are explicitly marked (conditional); for those, leave unticked if they truly do not apply and explain why in Risk Notes. All other items must be ticked before requesting human review.

• Type label — this PR carries exactly one of bug, enhancement, task, documentation. Type labels are author-added; the labeler bot does NOT assign them. Add the label in the GitHub UI, then tick this.
• Routing labels — this PR carries at least one of app, ui, platform, harness, ci. The labeler bot assigns these on PR open based on changed paths. Confirm the bot's choice (or override if wrong), then tick this.
• Priority label — this PR carries exactly one of P0, P1, P2, P3. The priority-triage bot suggests one on PR open. Confirm or override, then tick this.
• Human Review Status above is set to Pending, Approved by @<reviewer>, or Not required: <reason> (default is Pending; "not required" is restricted to bot-authored low-risk PRs).
• I linked the related issue, or stated in Summary why there is no issue.
• I described the review focus and any meaningful risks.
• I replaced the example block in How To Verify with the real verification steps and the key result for each.
• I did not introduce unrelated refactors, dependencies, generated files, or file changes beyond the stated scope.
• (conditional) I manually checked visible UI or copy changes when needed, with screenshots or recordings. Leave unticked only if no visible UI or copy changed.
• (conditional) I considered macOS and Windows impact for platform, packaging, updater, signing, paths, shell, or permissions changes. Leave unticked only if no platform/packaging surface was touched.
• (conditional) I called out docs, release notes, dependencies, permissions, credentials, deletion behavior, generated content, or local file changes when relevant. Leave unticked only if none of those surfaces was touched.
• I reviewed the final diff for unrelated changes and suspicious dependency changes.
• I am targeting dev, and my PR title and commit messages use Conventional Commits in English.