Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions .agents/skills/label-issue/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -23,9 +23,11 @@ Stop when further reading is unlikely to change classification. Technical fetch

## Choose the desired set

First identify the requested outcome, affected OpenShell boundary and substantive technical concerns; topics follow those concerns. Routine implementation or verification alone adds no topic. Testing work retains its testing topic.
First identify the requested outcome, affected OpenShell boundary and substantive technical concerns. Choose the area whose reviewers are the right people to review the work. Add a topic when the work has a clear, substantive connection to it and its reviewers would be interested in seeing and potentially reviewing the change. Omit topics with only incidental or speculative relevance. Supporting documentation or tests can warrant their topic when that reviewer audience is relevant; their presence alone does not.

Choose exactly one area and every supported topic from the canonical scopes. Report missing definitions or routing preparation as prerequisites; do not omit a needed label or invent replacements.
Do not add `topic:testing` merely because a PR adds or extends tests to cover its own code changes, including routine test-task or CI wiring needed to run those tests. Judge any substantive changes to testing structure, tooling or strategy separately under the reviewer-relevance rubric; this exclusion does not rule out test-only work.

Choose exactly one area and the topics supported by this rubric from the canonical scopes. Report missing definitions or routing preparation as prerequisites; do not omit a needed label or invent replacements.

Choose the best-supported set despite ordinary uncertainty. Record meaningful alternatives and medium/low confidence in `ambiguity`; use null for high-confidence choices. Ambiguity requires no escalation or extra approval.

Expand Down
Loading