seo-audit wraps seomator cli for automated site auditing across 251 rules spanning seo, performance, security, and ai readiness, returning xml/json/html reports with severity levels and fix recommendations.

streaming covers assistant-ui protocol implementation for custom backends, with support for both vercel ai sdk and native assistant-stream integration paths, including event types and common debugging patterns.

ccc provides semantic search and index management for codebases via cli, delegating lifecycle operations (init, indexing, refresh) to the agent rather than the user.

csharp-tunit covers project setup, test structure conventions, and basic tunit patterns for c# unit testing. guidance is incomplete and lacks concrete examples for data-driven tests despite claiming that focus.

firebase-apk-scanner extracts firebase configuration from decompiled android apks and tests realtime databases, firestore, storage, and cloud functions for unauthenticated access, with fallback curl procedures for failed automated scans.

go-performance provides benchmark scripting and micro-optimization patterns for hot paths in go code, with emphasis on strconv over fmt and profiling discipline.

figma-implement-design maps visual designs from figma into working application code, with guardrails to defer specialized tasks (design creation, system rules, code connect) to sibling skills.

directory-submissions guides strategic product placement across startup, saas, ai, and agent directories. provides domain-rating and discovery rationale but lacks concrete submission workflows and prerequisite validation.

nemoclaw-setup automates deployment of nvidia's sandboxed ai agent platform with docker, k3s orchestration, and optional remote access via cloudflare tunnels. covers isolation layers (landlock, seccomp, namespaces) and model configuration.

ts-library provides patterns for typescript package authoring, covering dual-mode exports, build tool selection, type design, and testing setup. grounded in analysis of established projects (vite, zod, trpc, vueuse) but lacks procedural depth.

chatgpt-apps scaffolds MCP-backed ChatGPT applications with docs-first methodology, producing app archetypes, tool plans, server stubs, and widget code paired against a minimum contract.

code-maturity-assessor applies trail of bits' 9-category framework to evaluate blockchain codebases, mapping security posture against arithmetic safety, auditing, access controls, and other engineering dimensions. output is a scored maturity card with improvement roadmap.

translate-book-parallel chunks large documents into isolated translation tasks executed by parallel subagents in claude code, avoiding context window exhaustion and semantic drift across chapters.

dotnet-design-pattern-review audits c# code against six named patterns (command, factory, di, repository, provider, resource) but provides only a checklist without actionable review steps, decision logic, or guidance on what constitutes adequate pattern implementation.

source-management provides inventory and connection guidance for mcp sources used in enterprise search, mapping available tools to data categories without specifying operational workflows or failure recovery.

azure-cost enumerates cost management use cases (query, forecast, optimize) but lacks actionable procedure. appropriate as a capability index, insufficient as executable skill documentation.

skill-development outlines how to construct modular skill packages for Claude Code plugins, covering directory structure, frontmatter conventions, and progressive context loading patterns. prescriptive rather than procedural.

jupyter-to-marimo automates notebook conversion via uvx marimo convert, covering artifact removal, widget porting, and compatibility verification with minimal local setup.

designing-growth-loops helps structure viral and product-led acquisition by categorizing loop types, identifying sharing moments, and applying compounding principles drawn from practitioner experience.

omc-setup installs or refreshes oh-my-claudecode across plugin, npm, and local-dev environments, invoked after initial installation or repo updates.

x-twitter-scraper exposes xquik api bindings for tweet search, user lookup, follower extraction, and media download with mandatory api-key auth and extensive security guardrails against prompt injection and unauthorized actions.

mcp-management abstracts interaction with model context protocol servers, offering discovery and execution of external tools, prompts, and resources via configured instances. context-efficient subagent architecture, persistent catalog caching.

cloud-functions provides deployment and management guidance for cloudbase event and http functions, covering runtime selection, bootstrap configuration, logging, and trigger setup. lacks detailed workflow procedures and specific trigger phrase coverage.

element-plus-vue3 documents component library setup and usage for vue 3 projects, covering installation, configuration, and api reference aligned to official docs.

design-qa-checklist provides categorical checklists for verifying visual accuracy, layout, and interaction states, but lacks procedural clarity on execution, triggering conditions, and failure recovery.

subagent-creator covers conceptual definitions and characteristics of subagents rather than procedural guidance. provides context on parallelization and isolation but lacks implementation steps.

mcporter provides cli access to mcp servers with flexible invocation syntax supporting http and stdio transports, though operational detail is sparse.

opencli-repair addresses adapter failures when target websites change structure or api behavior, offering error classification and self-repair mechanisms for broken opencli commands.

behavioral-modes defines seven task-specific operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate) with auto-detection via keywords or manual invocation. incomplete specification leaves implementation details unresolved.

assistant-ui is a react library providing composable primitives for building ai chat interfaces, with runtime layers supporting multiple backends including ai sdk, langgraph, and custom apis.

spreadsheet covers creation, editing, analysis, and visualization of xlsx/csv/tsv files using openpyxl and pandas, with basic workflow guidance for layout validation and formula handling.

uplifting-components-to-slds2 provides category mappings for migrating web components from slds 1 to slds 2 styling hooks, but lacks procedural depth and execution guidance for agents.

tdd covers test-driven development methodology with red-green-refactor workflow guidance. references 42 rules across categories but lacks concrete implementation details and decision trees for practitioners.

nuxt-ui covers component library setup and usage for vue 3 and nuxt 4+ with form validation, data tables, and theming via tailwind css and semantic colors. composables like usetoast and useoverlay manage interactions.

index-knowledge discovers project structure via parallel agents and complexity heuristics to generate hierarchical AGENTS.md knowledge bases across a codebase, with configurable depth and regeneration modes.

eol-message provides a template-based framework for writing end-of-life announcements that center customer impact over business justification, with guidance on tone, structure, and common pitfalls to avoid.

crap-score evaluates .net method quality by combining cyclomatic complexity and code coverage metrics into a single risk indicator, useful for identifying undertested complex code.

herdr controls a terminal multiplexer for coding agents, organizing workspaces and panes. guards against out-of-process invocation via environment check. delegates command syntax to runtime binary discovery.

no-ai-slop detects ai-generated patterns in writing or edits drafts toward human voice. covers two modes: rewriting for clarity while preserving author intent, and pattern detection without rewriting.

playwright-bot-bypass uses rebrowser-playwright with stealth techniques to remove webdriver signatures and fingerprinting vectors, enabling automation on sites with aggressive bot detection. does not handle captcha solving itself.

stored-procedures covers design and implementation of database functions, procedures, and triggers across postgresql and mysql. includes scalar function examples, error handling patterns, and basic best practices, but lacks depth on failure modes and recovery strategies.

mermaid-expert covers diagram creation across flowcharts, sequences, erds, and architectures. provides syntax guidance and styling options but lacks concrete procedural depth and failure mode acknowledgment.

experience-ui-bundle-app-coordinate orchestrates salesforce react ui bundle creation from natural language by sequencing specialized skills in dependency order, with explicit conflict detection before proceeding.

signup-flow-cro provides a comprehensive reference guide covering field optimization, multi-step patterns, and experiment templates for reducing friction in account creation flows. lacks actionable decision logic and structured procedure for actual optimization work.

code-review guides automated and manual review workflows using linting, style checking, and issue identification with severity-based feedback tiers. lacks specific trigger phrases and error handling.

influencer-marketing covers partner discovery and deal structuring for brand collaborations across social platforms and newsletters. lacks concrete procedures, decision trees, and failure-mode guidance needed for consistent execution.

meeting-notes provides a template structure for capturing discussion points, decisions, and action items in a standardized format. focuses on documentation layout rather than procedural guidance.