Code Review
Automated code review and analysis
contributing
by manastalukdar
Contribution readiness assessment analyzing project guidelines and requirements
loop-address-pr-feedback
by corygabrielsen
Systematically address AI and human review feedback on PR stacks. Triage issues, fix valid ones, respond to comments, restack, and request re-reviews until all reviewers are satisfied.
robot-move-check
by Idate96
Immediately send joint velocity commands for Mole/Menzi M4 via /mole/actuator_commands (MoleActuatorCommands). Use when the user asks to move boom/stick/tele/turn joints or run a quick motion check and wants minimal startup time.
github-integration
by manastalukdar
Advanced GitHub automation via MCP GitHub server or gh CLI
servel
by K-NRS
Self-hosted deployment platform via Docker Swarm. Deploys applications, manages 45+ infrastructure types (databases, queues, caches, platforms), handles secrets, domains, backups, and server operations. Triggers on deploy, infrastructure, postgres, redis, supabase, backup, restore, logs, secrets, SSL, domains, dev mode, CI/CD, alerts, traefik, routing, server management, capacity, rebalance, registry, node management, or access control.
verification
by SipengXie2024
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
k8s-hpa-cost-tuning
by microlinkhq
Tune Kubernetes HPA scale-up/down behavior, topology spread, and resource requests to reduce idle cluster capacity and ensure nodes can drain. This skill should be used when auditing cluster costs on a schedule, analyzing post-incident scaling behavior, or investigating why replicas or nodes do not scale down.
commit
by manastalukdar
Analyze changes and create meaningful conventional commits with pre-commit quality checks
code-registry
by The-Code-Registry
Use The Code Registry MCP server to create accounts, create code vaults, run LOCAL_AGENT analysis, poll completion correctly, and present business-focused code intelligence for any purpose including due diligence, security, and tech debt workflows.
deploy-validate
by manastalukdar
Pre-deployment validation with environment config, dependencies, DB migrations, and API compatibility checks
code-review-checklist
by manastalukdar
Generate context-aware code review checklists for changes
pr-responder
by linuxlewis
Review and respond to GitHub PR comments. Use when analyzing PR feedback, determining which comments to address, classifying review comments by priority, or implementing fixes for code review feedback.
git-worktree
by manastalukdar
Manage git worktrees for parallel feature development
powerpoint-presentation-editing
by Idate96
Edit and restructure PowerPoint presentations (.pptx) with an iterative render-and-inspect loop. Use when you must preserve existing media (images, GIFs, embedded videos), update slide text/layout, reorder slides, or export slide previews (PDF/PNGs) for visual review.
debug-root-cause
by manastalukdar
Root cause analysis with dependency tracing and call stack analysis
copilot-review-loop
by xpepper
Use when you want GitHub Copilot to review a PR and automatically address its feedback within the current agent session. For any reviewer (human or bot), use pr-review-loop; for a fresh-context-per-comment approach, use ralph-wiggum-loop.
idea-capturer
by PrakharMNNIT
Provides a structured system for capturing fleeting thoughts, developing raw ideas into actionable concepts, and organizing your creative thinking.
decompose-pr
by corygabrielsen
Break down a complex PR into focused, atomic commits for learning. Creates a temporary branch with one commit per logical change, making it easier to study how each piece works.
env-sync
by qiaoshouqing
"Sync .env files from git root repository to worktrees. Use when asked to sync env, copy env, environment file, or when working in a git worktree that is missing a .env file. Automatically detects missing .env in worktrees."
openclaw-notify
by linuxlewis
Notify OpenClaw gateway when background tasks complete. Use when you were dispatched by OpenClaw/TARS for background work and need to ping the user that you're done, failed, or blocked.
modelscope-notebook-adapter
by VoyagerXvoyagerx
Adapt and reproduce Jupyter notebooks, Colab notebooks, GitHub tutorial notebooks, or local notebook folders in ModelScope Notebook. Use when Codex must port a tutorial to ModelScope, replace Hugging Face/Google Drive/Colab downloads with ModelScope model or dataset repositories, prepare/upload missing assets with README metadata and license/source information, execute notebooks locally or in ModelScope-compatible environments, debug dependency/data/model issues, and update reports with reproducibility results.
loop-codex-review
by corygabrielsen
Automated code review loop with progressive reasoning levels. Runs n parallel Codex reviews (configurable via -n), Claude addresses issues, climbs from low→xhigh reasoning until fixed point (all n clean). Human approval at each iteration.
subagent-driven
by SipengXie2024
Use when executing implementation plans with independent tasks in the current session
license-check
by manastalukdar
License compliance checking and conflict detection