メニュー
Completes feature branch work by rebasing, pushing, monitoring CI, and squash merging to main
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when designing prompts for LLMs, optimizing model performance, building evaluation frameworks, or implementing advanced prompting techniques like chain-of-thought, few-shot learning, or structured outputs.
How to deploy Dravr infrastructure and apply Cloud Run config changes. Use when editing infra/ terraform, when a merged code change is live but a Cloud Run setting (cpu, memory, min/max instances, env var, scaling) hasn't taken effect, or when asked to plan/apply infra. Explains the two-pipeline model (app binary auto-deploys on push; terraform infra config is a separate manual apply) plus the cpu/cpu_idle guardrails.
Enforces zero-tolerance code quality policy using Clippy with strict lints, all warnings treated as errors
Write well-formatted notes to the dravr-vault Obsidian knowledge base. Use this skill whenever creating or updating an ADR, runbook, plan, API doc, guide, session output, or any structured document that should land in the vault — even when the user doesn't say "Obsidian" explicitly. Delegates to obsidian:obsidian-cli to write to the live vault and applies Dravr frontmatter and formatting standards.
Bootstrap Pierre server with database, admin user, coaches, and test users for development and testing
Validates coach markdown files for required frontmatter fields, sections, and naming conventions
| name | finish-worktree |
| description | Completes feature branch work by rebasing, pushing, monitoring CI, and squash merging to main |
| user-invocable | true |
CLAUDE: When this skill is invoked with /finish-worktree, immediately run:
./.claude/skills/finish-worktree/finish-worktree.sh
Then guide the user through CI monitoring and merge-and-cleanup.
Completes feature branch work with proper rebase, CI validation, and squash merge back to main.
/finish-worktree
./.claude/skills/finish-worktree/finish-worktree.sh
This script:
--force-with-leaseUse the first available method (never ask for a GitHub token):
gh run list --branch <branch> / gh run watch — if gh CLI is authenticatedmcp__github__*) — if MCP server is configuredhttps://github.com/dravr-ai/dravr-platform/actions — always availableWait for all checks to pass (green).
Fix the issues locally, then:
# Make fixes
cargo fmt
cargo clippy --all-targets -- -D warnings -D clippy::all -D clippy::pedantic -D clippy::nursery
# Amend or add commit
git add .
git commit --amend --no-edit # or new commit
# Push again
git push --force-with-lease origin <branch-name>
Repeat until CI is green.
Once CI is green, run from the main worktree:
cd /path/to/main/worktree
./.claude/skills/finish-worktree/merge-and-cleanup.sh
No arguments needed - branch info is saved by finish-worktree.sh.
This script:
# On feature branch in worktree
./.claude/skills/finish-worktree/finish-worktree.sh
# Wait for CI...
# If red, fix and push again
# Once green, go to main worktree:
cd /path/to/main/worktree
./.claude/skills/finish-worktree/merge-and-cleanup.sh
create-worktree - Creates worktree with environment setup