performing-code-review
Orchestrates a full code review for the current branch or a GitHub PR. Detects context, delegates to code-reviewer agent, displays the report, then optionally posts to the PR as line comments or a single comment via gh-pr-review. Use when the user asks for a code review, PR review, or audit.
What this skill does
# Performing Code Review
Orchestrate a full code review: detect context, delegate to `code-reviewer`, display the report, then optionally publish to GitHub.
## Quick Start
```
/performing-code-review # auto-detect context
/performing-code-review 123 # review PR #123 explicitly
```
## Process Flow
```mermaid
flowchart TD
A([Start]) --> D[Detect context\npr-info.sh or $ARGUMENTS]
D --> E{PR found?}
E -- No --> R[Spawn code-reviewer\nlocal branch review]
E -- Yes --> R2[Spawn code-reviewer\nPR-targeted review]
R --> OUT[Output report]
OUT --> Z([Done])
R2 --> SHOW[Display report to user]
SHOW --> Q[AskUserQuestion\nhow to post?]
Q --> L{Choice}
L -- Line comments --> GH[Use gh-pr-review skill\ncreate PENDING review]
L -- Single comment --> SC[gh pr comment\nfull report as one comment]
L -- Stop --> Z
GH --> CONFIRM[Confirm: review ID + URL]
SC --> CONFIRM
CONFIRM --> Z
```
## Workflow
### Step 1: Detect Context
**If `$ARGUMENTS` is a number:** use it as the PR number directly — skip detection.
**Otherwise, run:**
```bash
${CLAUDE_SKILL_DIR}/scripts/pr-info.sh
```
- Output contains `"error": true` or `"code": "NO_PR"` → **local branch review**
- Output returns a valid `pr_number` → **PR review** with that number
If the script is not accessible, fall back to local branch review and note this to the user.
---
### Step 2: Delegate Review
Spawn `Agent(code-reviewer)` to perform the full review.
- **Local:** `"Review the current branch changes using git diff."`
- **PR:** `"Review PR #<number>. Use git diff to identify the changed files and focus the review on those."`
Wait for the complete markdown report before continuing.
---
### Step 3: Output Report
Display the full markdown report to the user.
**Local branch review:** stop here.
**PR review:** continue to Step 4.
---
### Step 4: Ask How to Post (PR mode only)
Use `AskUserQuestion` to ask:
> "The review is ready. How would you like to post it to PR #[number]?"
Options:
1. **Line comments** — create a PENDING review with individual line-level comments (one per Critical Issue / Warning)
2. **Single comment** — post the full report as one PR comment
3. **Stop** — report shown above, no GitHub posting
---
### Step 5: Post to PR
#### Line comments
Use the `gh-pr-review` skill to create a PENDING review. Pass the report and PR number — the skill handles parsing findings and constructing the review. Only Critical Issues and Warnings become line comments; Suggestions are excluded.
After posting, inform the user:
```
## GitHub PR Review Created (PENDING)
PR #[number]: [url]
[N] line comments — not yet visible to the PR author.
Next steps: visit the PR, review comments, then click "Submit review".
```
#### Single comment
```bash
gh pr comment <pr_number> --body "<full markdown report>"
```
Inform the user with the comment URL returned by `gh`.
#### Stop
Nothing to do — report was already displayed.
---
## Edge Cases
| Situation | Behavior |
|-----------|----------|
| PR number passed but not found | Report error; fall back to local branch review |
| No local changes | Warn: "No changes found. Reviewing HEAD." Proceed. |
| `code-reviewer` returns no report | Report failure; do not attempt to post |
| `gh-pr-review` auth error | Tell user to run `gh auth login` |
## Requirements
- `code-reviewer` agent (installed via this plugin)
- `gh-pr-review` skill (installed via this plugin, for PR line comments)
- `gh` CLI authenticated (PR mode only)
- `jq` installed (PR mode only, used by pr-info.sh)
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.