MCP App StoreMCP App Store
from galyarder-framework12
Dispatch a focused code-review subagent and follow a strict review contract to catch critical issues before merging or continuing development.
This skill provides a structured protocol for requesting and handling code reviews inside an agentic development framework. It defines when to request reviews, how to dispatch a reviewer subagent or native subagent mechanism, required placeholders (BASE_SHA, HEAD_SHA, WHAT_WAS_IMPLEMENTED), and how to act on reviewer feedback. The guidance enforces traceability, gating, and rigorous testing practices.
Use this skill after completing tasks in subagent-driven development, before merging to main, after major features, or when stuck and a fresh perspective is needed. It is mandatory for batch or mission work where review gating is part of the release process.
Designed for agent runtimes and CI-integrated flows — compatible with Codex/Gemini/Copilot-style subagent dispatch environments and any platform that supports named subagent dispatch or native subagent launches.
A code-review dispatch skill from the Galyarder Framework that instructs agents to request focused code review via subagents. Well-written with clear instructions, placeholder system, and good example flow. However, it's deeply coupled to the Galyarder ecosystem (requires Linear, Obsidian, rtk execution proxy, specific directory structures) making it largely unusable outside that framework. No scripts were bundled, so only static analysis was performed.
No security concerns. The skill mentions redacting secrets/PII before sharing with subagents — a positive security practice. Heavy framework coupling limits real-world applicability. The global protocols section (nearly half the content) is noise for anyone not using Galyarder.
Playwright Test Reviewer
Automated Playwright test auditor: finds anti-patterns, scores files, and generates concrete fixes and patch suggestions to improve stability and coverage.
Verification Before Completion
Require and verify concrete evidence (command outputs, test results, build exit codes) before claiming work is complete or creating PRs.
E2E Runner (compatibility)
Compatibility skill that maps legacy `e2e-runner` calls to current runtime capabilities, routing requests to modern plugins or agents.
Remotion Engineer (compatibility)
Compatibility/adapter skill that maps legacy `remotion-engineer` capability names to the modern runtime and enforces the framework’s operational protocols.
Requesting Code Review
Dispatches a focused code-review subagent and provides a template-driven process to request reviews before merges, feature completion, or risky changes.
Remotion Engineer (compatibility)
Compatibility skill that maps legacy `remotion-engineer` references to current runtime practices and enforces the framework's operational protocols for agentic
Pricing & Monetization Strategy
Evaluates pricing models, packaging, and monetization tradeoffs against positioning, conversion, and margins.
Galyarder Release Coordinator
Coordinates full framework releases including changelogs, canary verification, Docker smoke tests, and GitHub release creation.
Ubiquitous Language Specialist
Extracts and formalizes DDD-style ubiquitous language glossaries from conversations.
Playwright Test Generator
Automatically generates production-ready Playwright E2E tests based on user stories, components, or URLs, adhering to strict TDD protocols.
NGINX Integration
Integrate with NGINX via the Membrane CLI to query, manage, and proxy requests to NGINX for configuration, logs, and runtime operations.
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Sync Production Database to Development
Run a safe, scripted workflow to download production database dumps and restore them into a development environment (download-only and restore options).
Run Execute
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
Sandbox0 Integration
Guidance and templates for integrating Sandbox0 sandboxing into AI agents — CLI/SDK patterns, templates, volumes, network policy, and deployment choices.
Alpha Forge Pre-Ship Quality Gates
Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.
Codex Collab
Bridge Claude and Codex to run tasks, perform code reviews, and run background jobs for research or implementation workflows.
Skill Issue — Skill Auditor
Scan and audit installed agent skills to produce a health report covering inventory, usage, dependency checks, version status, and actionable recommendations.