Skip to content

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows

ci: rename skills to imperative mood, add grounded-analysis guidance (#1303)

worktrunk-botaa33843a75a2
diff --git a/.claude/skills/pr-review/SKILL.md b/.claude/skills/review-pr/SKILL.md
similarity index 99%
rename from .claude/skills/pr-review/SKILL.md
rename to .claude/skills/review-pr/SKILL.md
index 2102520c4..a27201de8 100644
--- a/.claude/skills/pr-review/SKILL.md
+++ b/.claude/skills/review-pr/SKILL.md
@@ -1,5 +1,5 @@
---
-name: pr-review
+name: review-pr
description: Reviews a pull request for idiomatic Rust, project conventions, and code quality. Use when asked to review a PR or when running as an automated PR reviewer.
argument-hint: "[PR number]"
---
diff --git a/.claude/skills/running-in-ci/SKILL.md b/.claude/skills/running-in-ci/SKILL.md
index 08aa6d96f..b86f01b3a 100644
--- a/.claude/skills/running-in-ci/SKILL.md
+++ b/.claude/skills/running-in-ci/SKILL.md
@@ -191,6 +191,26 @@ session. This makes PRs easier to review, revert, and bisect.
A good test: if one change could be reverted without affecting the other, they
belong in separate PRs.
+## Thoroughness — Grounded Analysis
+
+CI runs are not interactive chat. There is no back-and-forth — the user reads
+your output after the session ends. Every claim must be grounded in evidence you
+actually examined.
+
+- **Do the work, don't speculate.** If you have access to logs, code, or API
+ data, read it before drawing conclusions. "This suggests X may be the cause"
+ is not acceptable when you can check whether X is actually the cause.
+- **Show evidence.** Cite specific log lines, file paths, commit SHAs, or API
+ responses. A conclusion without evidence is speculation.
+- **Trace causation, don't guess at correlation.** If two things co-occur, find
+ the mechanism — don't say "this may be related."
+- **Distinguish what you verified from what you inferred.** If you couldn't
+ verify something (e.g., logs weren't available), say so explicitly rather than
+ hedging with "may" or "suggests."
+
+The user can't ask follow-up questions in the same session. Treat every response
+as your final answer.
+
## Tone
You are a helpful reviewer raising observations, not a manager assigning work.
diff --git a/.claude/skills/issue-triage/SKILL.md b/.claude/skills/triage-issue/SKILL.md
similarity index 99%
rename from .claude/skills/issue-triage/SKILL.md
rename to .claude/skills/triage-issue/SKILL.md
index 091847289..31c7ddb08 100644
--- a/.claude/skills/issue-triage/SKILL.md
+++ b/.claude/skills/triage-issue/SKILL.md
@@ -1,5 +1,5 @@
---
-name: issue-triage
+name: triage-issue
description: Triages new GitHub issues — classifies, reproduces bugs, attempts conservative fixes, and comments. Use when a new issue is opened and needs automated triage.
argument-hint: "[issue number]"
---
diff --git a/.github/workflows/claude-issue-triage.yaml b/.github/workflows/claude-issue-triage.yaml
index 7caa695ae..d40368f1d 100644
--- a/.github/workflows/claude-issue-triage.yaml
+++ b/.github/workflows/claude-issue-triage.yaml
@@ -64,7 +64,7 @@ jobs:
actions: read
prompt: |
- Use /issue-triage ${{ github.event.issue.number }}
+ triage-issue ${{ github.event.issue.number }}
claude_args: |
--model opus
diff --git a/.github/workflows/claude-review.yaml b/.github/workflows/claude-review.yaml
index 06401a093..8fb9b42b1 100644
--- a/.github/workflows/claude-review.yaml
+++ b/.github/workflows/claude-review.yaml
@@ -79,7 +79,7 @@ jobs:
additional_permissions: |
actions: read
use_sticky_comment: ${{ github.event_name == 'pull_request_target' }}
- prompt: ${{ github.event_name == 'pull_request_target' && format('Use /pr-review {0}', github.event.pull_request.number) || '' }}
+ prompt: ${{ github.event_name == 'pull_request_target' && format('review-pr {0}', github.event.pull_request.number) || '' }}
claude_args: |
--model opus
--allowedTools Bash,Edit,Read,Write,Glob,Grep,WebSearch,WebFetch,Task,Skill