shrek-abaper/sap-engineering-skill
Plugin Claude Code
SAP ABAP engineering skills for AI coding agents.
not rated 46
changed yesterday A
tokens not measured
original MIT
llm-wiki
458Plugin Claude Code
Bundles 2 skills, 2 agents · 254 tokens together
Official Scraps LLM Wiki bundle. Skills and agents for ingesting sources, querying the wiki, applying the default Scraps LLM Wiki schema, and running purpose-driven lint via the scraps CLI.
not rated 45
changed 19d ago A
tokens not measured
original MIT
IndianOldTurtledove/codex-oss-maintainer-toolkit
Skill Claude CodeCodex
Build Codex-native workflows for open-source maintenance. Use when creating AGENTS.md guidance, maintainer skills, issue triage flows, PR review prompts, release-note routines, or repository verification scripts.
not rated 45 7mo ago A 49 tokens
original MIT
copilot
460Plugin Claude Code
Bundles 3 skills, 7 commands, 1 agent, 3 hooks · 234 tokens together
Use Copilot from Claude Code to review code or delegate tasks.
not rated 45 7mo ago A
tokens not measured
original Apache-2.0
mehmetakinn/gitlab-mcp-code-review
MCP server Claude CodeCodexCursor +2
MCP server "gitlab-mcp-code-review" as configured in mehmetakinn/gitlab-mcp-code-review. Runs locally from the gitlab-mcp-code-review Python package.
not rated 45 1y ago A
tokens not measured
original MIT
Skill Claude Code
Produces a single-story walkthrough of AI-authored code changes from runtime trigger to final behavior, weaving changed and unchanged code into one narrative with annotated diffs, trade-offs, alternatives, and risk analysis. Use when asked to "explain what changed", "walk me through this diff", "summarize agent…
not rated 45 3mo ago A 87 tokens
review-all
463Plugin Claude Code
Bundles 1 skill, 12 agents · 467 tokens together
Comprehensive, project-agnostic, multi-agent code review for Claude Code with verification to eliminate false positives.
not rated 45
+1
changed 3d ago A
tokens not measured
original MIT
open-pr
464Plugin Cursor
Bundles 8 skills, 1 command, 1 plugin · 437 tokens together
Review GitHub Pull Requests and GitLab Merge Requests across many stacks, learning each repo's own conventions over time and posting one review via that vendor's own CLI.
not rated 45
+1 yesterday A
tokens not measured
original MIT
code-review
465YuDefine/nuxt-supabase-starter
Agent Claude Code needs its repo
A code-review agent for Nuxt 4, Vue 3, TypeScript, and Supabase projects. Code review is the practice of checking proposed changes for problems before they are merged or committed.
not rated 44
changed 12d ago A 30 tokens
original MIT
pi
466Plugin Claude Code
Bundles 3 skills, 8 commands, 1 agent, 3 hooks · 219 tokens together
Use the Pi coding agent from Claude Code to review code or delegate tasks.
not rated 44 2mo ago A
tokens not measured
original Apache-2.0
Skill Claude CodeCodex
Follow-up review that never trusts a commit message — always re-reads the actual diff before resolving a thread. Cites a real source for new issues, matching review-advanced.
not rated 44 3d ago A SkillSpector: warn 41 tokens
original MIT
pr-review
468Skill Claude CodeCodex
Review a GitHub pull request and post one formal review — advance the existing discussion and give precision-first, high-signal feedback. Judgement on the diff, not a build gate — CI validates that it builds, and a targeted probe is allowed as evidence. Use when asked to review a PR or on a cron PR scan.
not rated 44
+3
changed 1mo ago A SkillSpector: warn 69 tokens
original MIT
claude-playbook
469Plugin Claude Code
Bundles 5 skills, 4 agents, 3 hooks · 361 tokens together
Engineering guardrails for Claude Code: path-scoped rules, review and verification skills, specialist subagents, and hooks that enforce what instructions only request.
not rated 44
+1 1mo ago A
tokens not measured
original MIT
agent-verifier
470Plugin Claude Code
Bundles 5 skills · 218 tokens together
Verifies AI agent code before it ships: hardcoded secrets, unbounded loops and retries, hallucinated tool references, oversized prompts, and language-specific quality checks. No telemetry.
not rated 44
changed 24d ago A
tokens not measured
original MIT
smartbear
471Plugin Claude Code
Connects Claude to SmartBear tools, including BearQ, BugSnag, Collaborator, PactFlow, QMetry, QTM4J, Reflect, Swagger and Zephyr, through the SmartBear MCP server.
not rated 44
changed 3d ago A
tokens not measured
original MIT
Skill Codex
Use when reviewing architecture, refactors, state/data ownership, duplication, code and test structure, failure handling, debug discipline, work-in-progress hygiene, or concurrency policy against Alex's eight fixed invariants.
not rated 43
changed 1mo ago A 46 tokens
original MIT
git-iris
473Skill Claude CodeCodex
Use this skill when generating commit messages, pull request descriptions, release notes, changelogs, or code reviews in a repository where git-iris is available. Activates on requests like "commit this", "write a commit message", "draft a PR", "generate release notes", "write a changelog", or "review my changes" when…
not rated 43 3d ago A 81 tokens
original Apache-2.0
dev-pipeline
474Plugin Claude Code
Bundles 17 skills · 1,307 tokens together
A 5-phase development pipeline (requirement engineering, system architecture, task generation, verified implementation, code review) with an optional QA gate (plan-qa + execute-qa) for changes that have a running surface worth driving — independent of /review, run sequentially or in parallel at the developer's…
not rated 43
changed 2mo ago A
tokens not measured
Skill Claude CodeCodex
Effect development guidance. Use when implementing or reviewing code that composes Effect APIs or patterns, or that adds or changes API signatures.
not rated 43
+4 today A 29 tokens
original MIT
Agent Claude Code
Enterprise-grade code quality guardian ensuring production standards and architectural excellence.
not rated 42 8mo ago A 16 tokens
original MIT
cpp-oop-style
477Skill Codex
High-quality C++ OOP coding style (archibate / parallel101 lineage) that overrides sloppy AI-default C++. Use this skill WHENEVER writing, editing, refactoring, or reviewing C++ code (.cpp / .h / .hpp / .cc / .cxx), designing C++ classes, interfaces, APIs, or libraries, or when the user mentions C++ design, OOP…
not rated 42
changed 1mo ago A 216 tokens
Skill Claude CodeCodex
Pair-program a feature with another agent in the office. You drive (scope, design, implement); they review at design and code stages. Optionally takes the peer's name and a feature prompt as arguments.
not rated 42
changed 8d ago A SkillSpector: warn 50 tokens
original
kimi
479Plugin Claude Code
Bundles 12 skills, 11 commands, 7 agents, 1 hook, 1 MCP server · 1,177 tokens together
Kimi for Claude Code: code questions, independent reviews, bounded fixes, autonomous goals, parallel tasks, and MCP tasks through the local Kimi Code CLI, with PreToolUse safety hooks.
not rated 42
changed 5d ago A
tokens not measured
original Apache-2.0
Skill Claude CodeCodex
Run this as the FINAL review step once you have finished a UI change you can load in a browser — it is the visual-regression gate, run once at the end (not after every edit), and the change is not done until it reports score: 100. It drives a real browser over the page, auto-detects its relevant elements (no…
not rated 42
+2 yesterday A SkillSpector: pass 190 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: