Agent skill
review-package
Create a self-contained review package of current work for external review by another AI model or human reviewer. Bundles relevant files with a contextual README and instructional prompt. Triggers: "review package", "create review package", "hand off for review", "get a second opinion", "external code review", "cross-model review", "package for review", "prepare code review". Accepts an optional focus area argument to scope the analysis.
Install this agent skill to your Project
npx add-skill https://github.com/petekp/claude-code-setup/tree/main/skills/review-package
SKILL.md
Review Package Creator
Bundle current work into a self-contained zip with a contextual README and review prompt, ready to hand off to any external reviewer.
Phase 1: Gather Requirements
Ask the user two questions using AskUserQuestion:
Question 1: Review Type
- Header: "Review type"
- Question: "What type of review do you need?"
- Options:
- Code review — Line-by-line feedback on implementation, bugs, edge cases, best practices
- Architecture review — High-level feedback on patterns, structure, design decisions
- Both — Comprehensive review covering code and architecture
Question 2: Specific Concerns
- Header: "Focus areas"
- Question: "Any specific concerns you want the reviewer to address?"
- multiSelect: true
- Options:
- General review — No specific focus, broad feedback welcome
- Performance — Efficiency, optimization opportunities
- Security — Vulnerabilities, input validation, auth patterns
- Maintainability — Code clarity, complexity, future extensibility
Wait for responses before proceeding.
Phase 2: Analyze Codebase
Spawn the analyzer agent:
- subagent_type:
review-package-analyzer - prompt: Include focus area ($ARGUMENTS or "current work"), review type from Phase 1, and project root (cwd).
Wait for the agent to return its structured analysis.
Phase 3: Generate README
Generate a unique suffix for temp files (e.g., timestamp: date +%s). Use this for all temp paths in subsequent phases.
Read references/readme-guide.md for structure guidelines. Write the README to /tmp/review-readme-{suffix}.md.
Adapt the README to the project — don't fill in a rigid template mechanically. The guide provides the sections and priorities; use judgment about what to emphasize based on the review type and analysis results.
Phase 4: Create File List
Extract all file paths from the analysis (Core, Related, Tests, Config). Write one path per line to /tmp/review-filelist-{suffix}.txt.
Phase 5: Create Package
Locate the packaging script:
find ~/.claude -path "*/review-package/scripts/create-review-zip.sh" -type f 2>/dev/null | head -1
Run it:
/path/to/create-review-zip.sh \
"$(pwd)" \
"/tmp/review-readme-{suffix}.md" \
"/tmp/review-filelist-{suffix}.txt" \
"review-package-$(date +%Y%m%d-%H%M%S)"
Phase 6: Generate Instructional Prompt
Read references/prompt-guide.md for the template. Customize based on review type, focus areas, and concerns from the analysis.
Write to /tmp/review-prompt-{suffix}.md and copy to clipboard:
cat /tmp/review-prompt-{suffix}.md | pbcopy
Phase 7: Report
Tell the user: zip location, file counts (core/related/tests), display the instructional prompt inline, and list next steps (open a new chat with any AI model, paste prompt, upload zip). Mention the prompt is on the clipboard and saved to the temp path.
Clean up temp files (keep the prompt file):
rm -f /tmp/review-readme-{suffix}.md /tmp/review-filelist-{suffix}.txt
Notes
- If $ARGUMENTS is empty, the analyzer auto-detects current work from git status and recent changes
- For non-git projects, the analyzer falls back to recently-modified files
- The package is self-contained — the reviewer needs no other context
- Files are copied with directory structure preserved
- Binary files and build artifacts are excluded automatically
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
ubiquitous-language
Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".
every-style-editor
This skill should be used when reviewing or editing copy to ensure adherence to Every's style guide. It provides a systematic line-by-line review process for grammar, punctuation, mechanics, and style guide compliance.
manage-codex
Autonomous Codex batch orchestrator. Use for "/manage-codex", "manage codex", "use codex", "dispatch to codex", or long-running Codex work.
seo-audit
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," or "indexing issues." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup. For AI search optimization, see ai-seo.
capture-learning
Analyze recent conversation context and capture learnings to project knowledge files (for project-specific insights) or skills/commands/subagents (for cross-project patterns). Use when the user asks to "capture this learning", "update the docs with this", "remember this for next time", "document this issue", "add this to CLAUDE.md", "save this knowledge", or "update project knowledge". Also triggers after resolving build/setup issues, discovering non-obvious patterns, or completing debugging sessions with valuable insights.
agent-changelog
Compile an agent-optimized changelog by cross-referencing git history with plans and documentation. Use when asked to "update changelog", "compile history", "document project evolution", or proactively after major milestones, architectural changes, or when stale/deprecated information is detected that could confuse coding agents.
Didn't find tool you were looking for?