caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
PR review agents specializing in code, security, performance, UX, tests, comments, error handling, type design, and code simplification. Includes a findings-triager that fact-checks reviewer output, dedupes findings, separates pre-existing from PR-introduced issues, and recommends actions on a falsifiable scope/risk/relatedness axis. Fork of Anthropic's pr-review-toolkit.
Plugin pr-review from marketplace onreza-claude-plugins in ONREZA/claude-plugins. Commands read from the repo's manifest — 1 month ago.
/pr-review:review-prComprehensive PR review using specialized agents with file-based exchange and triage
code-reviewerUse this agent when you need to review code for adherence to project guidelines, style guides, and best practices. This agent should be used proactively after writing or modifying code, especially before committing changes or creating pull requests. It will check for style violations, potential issu
code-simplifierSimplify and refine recently modified code for clarity, consistency, and maintainability while preserving exact functionality. Run this agent on demand after fixes are in place — it is not part of the standard review pipeline. The agent reads the project's `CLAUDE.md` (and nearest module docs) to fo
comment-analyzerUse this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. This includes: (1) After generating large documentation comments or docstrings, (2) Before finalizing a pull request that adds or modifies comments, (3) When reviewing existing comments f
findings-triagerUse this agent at the end of /pr-review:review-pr to fact-check, dedupe, and categorize findings that reviewer agents wrote to $FINDINGS_PATH. ALWAYS run — even with one reviewer. Triager reads every <agent>.md in the directory, verifies each finding against the actual code (reproducing in /tmp when
performance-reviewerUse this agent to review pull requests for performance issues that could degrade user experience or infrastructure cost in production. It analyzes both backend and frontend changes for issues like N+1 queries, missing indexes, blocking I/O in async contexts, unbounded loops, missing pagination, unne
pr-test-analyzerUse this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n<example>\nContext: Daisy has just created a pull request wi
security-reviewerUse this agent to review pull requests for security vulnerabilities. It analyzes code changes for issues like missing authentication/authorization checks, secret exposure, input validation gaps, injection vulnerabilities (SQL, command, XSS, path traversal), CSRF, sensitive data leaks in logs or resp
silent-failure-hunterUse this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. This agent should be invoked proactively after completing a logical chunk of work that involves error handling, catch blocks, fallback logic, or a
type-design-analyzerUse this agent when you need expert analysis of type design in your codebase. Specifically use it: (1) when introducing a new type to ensure it follows best practices for encapsulation and invariant expression, (2) during pull request creation to review all types being added, (3) when refactoring ex
ux-reviewerUse this agent to review user-facing UI/UX changes in pull requests. It analyzes frontend code (HTML/CSS/JS/TSX/JSX/Vue/Svelte/Astro components, templates, layout files) for interaction states, accessibility, focus management, copy quality, form ergonomics, mobile/responsive concerns, and visible er
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.