MCP App StoreMCP App Store
from ryanb/dotfiles2,379
Run the project's review tool (`bin/claude-review --print`), report the findings, and iteratively apply fixes, committing each change individually.
This skill automates a review-and-fix workflow driven by a repository-local review command. It runs bin/claude-review --print, prints the full review output verbatim to the user, parses issues, and then attempts to fix them sequentially. For each issue it spawns a fixer workflow that reads the file, writes or updates tests when appropriate, applies the change, runs relevant tests, and commits the result with a descriptive message.
Use this skill when a repository provides a bin/claude-review or similar command that enumerates lint, style, or correctness issues and you want an automated, auditable pass to resolve them. It's appropriate for small-to-medium fixes (bugfixes, style changes, suggestions) but avoids large risky refactors without human approval. It triggers when the repo includes bin/claude-review, or when a user requests an automated review-and-fix pass.
Agents capable of running repository-local commands, reading and writing files, spawning sub-agents, and creating git commits (advanced developer agents like Codex/GitHub Copilot-style agents).
Fix-all is a review automation skill that runs a project's `bin/claude-review --print` tool, parses the output into issues by severity, and iteratively fixes them using sub-agents with individual git commits. It includes a re-review loop (up to 5 rounds) and a deferral mechanism for issues that conflict with branch intent. No scripts were bundled — the skill is purely instruction-based. Well-structured with clear steps but narrowly scoped to projects using the specific review CLI tool.
Clean skill, no security concerns. Well-written instructions with good safeguards (deferred issues, user confirmation for risky changes, loop limits). Niche applicability since it depends on a specific review CLI tool.
Interactive Rebase
Guided interactive rebase skill: rebases the current branch onto a base branch, helps resolve conflicts, runs related tests, and compares the result to the remo
Review Queue
Generate a ranked, clickable list of open PRs prioritized by review ease, with grouping for PR dependency chains and optional preference directives.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
Readwise Reader Document Management
Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Junshi — Research Advisor
Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
ezBookkeeping API Tools
Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi
Feishu Voice Sender
Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.