MCP App StoreMCP App Store
from ryanb/dotfiles2,379
Generate a ranked, clickable list of open PRs prioritized by review ease, with grouping for PR dependency chains and optional preference directives.
Review Queue automates preparation of a prioritized pull-request review list. It expects a preformatted pipeline output (scripted in the repo) and turns that into a sequential, clickable list of PRs ranked by how easy they are to review. It preserves optional PREFERENCES: directives embedded in the pipeline output to adjust ordering or highlighting.
Invoke when you need to triage or batch code reviews across one or more repositories, especially useful for maintainers who want a quick, actionable list of reviewable PRs. It requires the helper scripts present in the repo (pr-data.sh, format-queue.sh) and a git/gh-capable environment. If the pipeline fails, the skill should report the error and stop.
pr-data.sh and format-queue.sh which produce the pipeline output consumed by this skill.PREFERENCES: if present, re-number the list, and output only the final list with preserved format.Suited to agents with Bash and Read permissions or environments that can run the repo-provided scripts (local dev environments, maintenance bots with GH CLI access).
Review Queue is a simple skill that runs two local shell scripts (pr-data.sh and format-queue.sh) via pipeline to generate a ranked list of open PRs needing review. No scripts were bundled for auditing. The SKILL.md is concise and functional with clear error handling instructions, but lacks depth — no documentation on what the scripts do internally or how to customize behavior beyond the PREFERENCES directive.
Clean skill with no security concerns. Uses only local shell scripts and gh CLI. Architecture is minimal — frontmatter present but no scripts, references, or progressive disclosure. Niche but practical for repo maintainers.
Fix-All Review Automation
Run the project's review tool (`bin/claude-review --print`), report the findings, and iteratively apply fixes, committing each change individually.
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
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.