// Review current branch changes against a target branch. Use when the user asks to review a branch, review changed files, compare current work to main, origin HEAD, or master, or run a file-by-file code review with aggregated markdown results.
Search the internet by delegating to another AI CLI when local web tools are unavailable or when a second-opinion search is wanted. Use when the user asks to use Gemini or Claude for web research, asks for AI-backed web search, or wants an external CLI to verify current information with source URLs.
Simplify and reduce code while preserving behavior. Use when the user asks to simplify, clean up, refactor, audit, report on, or reduce recently changed code. Supports apply mode for edits and report mode for findings only.
Simplify and reduce tests while preserving coverage. Use when the user asks to simplify, deduplicate, reduce, or clean up test files using techniques such as equivalence class partitioning, decision tables, or pairwise testing.
Fast, MVP-focused grilling session for plans, prototypes, designs, or feature ideas. Use when the user wants to stress-test direction, clarify assumptions, reduce scope, or get challenged without a long decision-tree interview.
Personal Obsidian CLI mechanics and patterns not covered by the base `obsidian-cli` skill. Load when driving the Obsidian CLI for content creation, file operations, vault hygiene, or version history. Triggers on: "search my vault", "find notes about", "show orphan notes", "find broken links", "rename this note", "move this note", "show note history", "restore version", "list backlinks", "show outline", "heredoc obsidian", "obsidian fallback", "vault hygiene".
Durable repo-specific notes: project findings, investigations, decisions, coding lessons, failure analyses, and implementation findings. Distinct from the agent's native memory feature. Triggers: "save to project notes", "project notes", "save this to my notes", "note this for the project", "log this finding", "save project notes", "save this project finding", "log this investigation", "coding lesson", "project decision", "remember this for this repo", "document this bug investigation".
| name | review-branch |
| description | Review current branch changes against a target branch. Use when the user asks to review a branch, review changed files, compare current work to main, origin HEAD, or master, or run a file-by-file code review with aggregated markdown results. |
Act as orchestrator.
Delegate actual code review to code-reviewer subagents when available.
If named subagents are unavailable, use the generic subagent mechanism and pass the code-reviewer constraints from local agent definitions when present.
origin/HEADUse three repo-root files:
| File | Purpose |
|---|---|
review_context.md | Shared context for subagents |
review_files.md | Todo list of files to review |
review_result.md | Aggregated review results |
If review_files.md exists with unchecked items, continue from it.
Otherwise ask whether to start fresh.
Before launching subagents, create review_context.md with:
Exclude images, lock files, binary files, and generated files.
Tell each subagent:
Review context available at: review_context.md
Format review_files.md exactly:
- [ ] relative/path/to/file1.ext
- [ ] relative/path/to/file2.ext
No extra content.
Format review_result.md:
# Code Review [date] [time] [branch name]review_result.md immediatelyFilter out: