feat: support inline skills in agent YAML config#2946
Merged
Conversation
rumpl
approved these changes
Jun 1, 2026
|
❌ PR Review Failed — The review agent encountered an error and could not complete the review. View logs. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds support for defining "inline skills" directly in the agent YAML
skills:field, enabling users to express skills without maintaining separate files or requiring external sources. Inline skills are defined as YAML mappings mixed with existing string sources and name filters, and support the YAML-expressible subset of the skill definition format.An inline skill specifies a name, description, and instructions (all required), plus optional fields for context (only "fork" allowed), model, and allowed_tools. They cannot bundle files or use command expansion. Inline skills are always exposed to the agent, work in sandbox mode since they travel inside the agent YAML, and enable skills independently without needing to pull in local sources.
The implementation includes schema updates, validation (required fields, duplicate-name detection, context restrictions), a new InlineSkill type with mixed YAML/JSON parsing, and updates to the skills toolset and TUI to handle inline skill retrieval and display.
Also includes a fix for test hermeticity:
pkg/worktree/worktree_test.gonow disables commit signing in the test bootstrap repo to prevent leakage from the developer's global 1Password SSH commit-signing config, which was flaky in tests.