yellow-core
claudecodexDev toolkit with review agents, research agents, and workflow commands for TypeScript, Python, Rust, and Go
23 skills · 19 commands · hooks
Multi-agent PR review with adaptive agent selection, parallel comment resolution, and sequential stack review
Plugin yellow-review from marketplace yellow-plugins in KingInYellows/yellow-plugins. Commands read from the repo's manifest — today.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
yellow-thermonuclear-reviewOpt-in structural maintainability rubric adapted from Cursor's thermo-nuclear code-quality review. Use only when explicitly asked for a thermonuclear review, a code-judo simplification pass, spaghetti-growth analysis, giant-file review, or an unusually strict architecture-quality audit; never apply
pr-review-workflowInternal reference for PR review workflow patterns. Use when agents or commands need shared conventions for adaptive selection, output format, or error handling.
stack-traversalInternal reference for the bottom-up Graphite stack-traversal procedure shared by /review:all and /review:resolve-stack. Use when a yellow-review command needs to walk a Graphite stack PR by PR in dependency order.
/yellow-review:review:merge-readyRead-only merge gate for one PR: unresolved review threads (outdated included), CHANGES_REQUESTED reviewers, conversation-resolution enforcement, CI, pending P0-P2 ledger findings and the risk-tier human approval. Use before adding graphite-queue or merging; it never writes to GitHub and adds no led
/yellow-review:review:resolve-prParallel resolution of unresolved PR review comments with actionability filtering and same-region clustering. Drops non-actionable threads (LGTM, nit:, 👍, thanks) before dispatch and consolidates threads on the same file region into a single resolver task. It replies to and resolves threads, files
/yellow-review:review:resolve-stackWalk a Graphite stack bottom-up and run /review:resolve on every open PR fully autonomously — no prompts, pushing and restacking as it goes. Use when you have unresolved reviewer comments across a multi-PR stack and want them all addressed in one unattended pass.
/yellow-review:review:review-allSequential review of multiple PRs — your Graphite stack, all open PRs, or a single PR. Use when you want to review an entire stack in dependency order or batch-review all your open PRs.
/yellow-review:review:review-prAdaptive multi-agent review of a single PR with a tiered persona pipeline, learnings pre-pass, and confidence-rubric aggregation. Use when you want comprehensive code review with automatic agent selection based on PR size and content.
/yellow-review:review:setupValidate review command prerequisites and optional yellow-core integration. Use when first installing the plugin or when review commands fail before analysis begins.
/yellow-review:review:sweep-allRun /review:sweep on every open non-draft PR authored by the current user, sequentially, with one upfront confirmation. Use when you want to clear review + resolve backlog across all your open PRs in one batch.
/yellow-review:review:sweepRun /review:pr then /review:resolve on the same PR in one unattended pass — no gates, no per-step prompts. Use when you want both an AI review pass and cleanup of any open bot or human reviewer comment threads without manually re-invoking on the same PR number.
/yellow-review:review:triageTriage the review-findings ledger of one PR: re-verify every residual finding against the PR head, then fix, dismiss, restore or skip each one. Use when a sweep summary or the session-start notice reports pending review findings; --non-interactive and --prune are the unattended modes /review:sweep a
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session-start.sh"
Dev toolkit with review agents, research agents, and workflow commands for TypeScript, Python, Rust, and Go
23 skills · 19 commands · hooks
GitHub-native stacked-PR provider — full command surface (setup, status, plan, submit, amend, sync, nav, cleanup, merge)
9 skills · 9 commands · hooks
CI failure diagnosis, workflow linting, and runner health management for self-hosted GitHub Actions runners
8 skills · 9 commands · hooks
Deep research plugin with Ceramic, DeepWiki, Perplexity, Tavily, EXA, and Parallel Task MCP servers, plus optional ast-grep CLI code search. Code research inline; deep research saved to docs/research/.
3 skills · 4 commands · 6 MCP servers · hooks
Graphite-native workflow commands for stacked PRs, smart commits, sync, and stack navigation
11 skills · 1 MCP server · hooks
Persistent vector memory and semantic code search for Claude Code agents via ruvector
3 skills · 8 commands · 1 MCP server · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Use Alibaba Open Code Review from local Codex.
2 skills
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.