playwright automates browser tasks from the terminal using playwright-cli, covering navigation, form filling, snapshots, screenshots, and data extraction via a wrapper script that works without global installation.

openai-docs routes model selection, api migration, and prompt-upgrade requests to the official openai developer docs mcp server, with fallback to bundled references and domain-restricted web search when remote guidance is unavailable.

affaan-m-springboot-verification orchestrates a six-stage validation pipeline for spring boot services: build verification, static analysis (spotbugs/pmd/checkstyle), unit and integration testing with coverage reporting, dependency and secrets scanning, formatting checks, and pre-commit diff review.

sickn33-threejs-skills provides systematic three.js setup patterns, geometry/material/lighting guidance, and common interaction recipes (orbit controls, raycasting, particles). covers modern r183 practices but lacks explicit error recovery and performance constraints.

davila7-copywriting covers marketing copy for web pages (homepages, landing pages, pricing, feature, about). provides headline formulas, copywriting principles (clarity, benefits, specificity), section frameworks, and guidance for cta copy and page-specific strategies.

davila7-generate-image wraps openrouter api calls for photo, illustration, and artwork generation via flux and gemini models. covers generation and editing with clear cli examples and api key setup.

davila7-docker-expert covers dockerfile optimization, multi-stage builds, container security hardening, docker compose orchestration, and image size reduction. practical, code-heavy patterns for production deployment. handoff logic clear for kubernetes and ci/cd boundaries.

davila7-stable-diffusion-image-generation provides text-to-image, image-to-image, inpainting, and controlnet workflows via huggingface diffusers with memory optimization guidance and multiple model variants (sd1.5, sdxl, sd3, flux).

davila7-dspy covers declarative language model programming with automatic prompt optimization, modular pipeline construction, and multi-stage rag systems. extensive examples show signatures, modules, and optimizer patterns, though error handling and failure recovery remain largely absent.

anthropics-search-strategy decomposes natural language queries into source-specific searches, translates to connector syntax, ranks results by relevance and query type, with explicit fallback strategies for unavailable sources and no-result cases.

metabase-typescript-write enforces strict typing discipline, discriminated unions, and narrow type modeling for typescript/javascript development. covers no-any rules, generic reuse, immutability patterns, and null/undefined narrowing with concrete examples.

openai-integration-tests runs a pnpm-based test pipeline against a local verdaccio npm registry, handling sandbox permission escalation, registry lifecycle management, and storage mount integration coverage.

lobehub-project-overview maps the open-source monorepo structure, tech stack, and directory layout for developers onboarding or locating code across apps, packages, and src layers. covers architecture patterns and data flow.

langgenius-frontend-testing generates vitest and react testing library tests for dify components, hooks, and utilities using integration-first patterns. covers rendering, props, interactions, and edge cases with incremental multi-file workflows.

comet-ml-opik-frontend documents react patterns for opik apps including routing, data fetching with tanstack query, zustand state management, and layered architecture constraints. covers memoization gotchas and component structure conventions.

openai-knowledge routes queries to the openai developer docs mcp server when available, falling back to guided setup instructions. covers api schemas, endpoints, and platform features with emphasis on exact documentation retrieval over inference.

github-make-repo-contribution enforces discovery and adherence to repository-specific contribution workflows before filing issues, creating branches, committing, or opening pull requests. includes security guardrails against executing arbitrary commands or accessing external resources.

command-name documents standardized claude code plugin directory layout, manifest configuration, component organization (commands/agents/skills/hooks), auto-discovery mechanisms, and portable path references using ${CLAUDE_PLUGIN_ROOT}, covering both minimal and full-featured plugin patterns.

fact-checker evaluates claims systematically against evidence hierarchies, ratings across a six-point verdicts scale from true to unverifiable, and flags common manipulation patterns like cherry-picking and context removal.

agent-identifier teaches agent structure, frontmatter fields, system prompt design, and triggering via examples for claude code plugins. covers naming rules, model selection, tool restriction, and validation.

playground builder generates self-contained html explorers with live preview, interactive controls, and copyable prompt output. covers design, data, learning, and code review use cases via templates.

security-threat-model produces repository-grounded threat models anchored to code evidence, enumerating trust boundaries, assets, and abuse paths with explicit attacker capabilities and prioritized mitigations.

security-ownership-map analyzes git history to build people-file graphs, compute bus factor and sensitive-code clusters, and export for neo4j or gephi. flags orphaned sensitive code, ownership drift vs codeowners, and hidden concentration risk in auth/crypto.

paid-ads covers strategy, creative, and targeting across google, meta, linkedin, twitter, and tiktok. includes campaign structure, audience segmentation, retargeting funnels, and optimization levers with platform-specific setup checklists.

anthropics-command-development covers slash command creation, yaml frontmatter configuration, dynamic arguments, bash execution, and file references for claude code. provides concrete examples and organizational patterns for building reusable workflows.

davila7-humanizer detects and removes 24 distinct ai writing patterns including vague attribution, em dash overuse, rule of three repetition, and promotional language. builds on wikipedia's ai cleanup guidance with emphasis on adding voice and personality alongside pattern removal.

anthropics-webapp-testing provides playwright-based automation for local web app testing via helper scripts and reconnaissance patterns. covers screenshot capture, dom inspection, selector discovery, and multi-server orchestration.

davila7-web-quality-audit provides structured guidance across four audit domains (performance, accessibility, seo, best practices) with detailed checks and severity classification, but lacks executable steps and failure-mode handling.

davila7-scvi-tools covers single-cell omics analysis with probabilistic deep generative models. provides domain-specific guidance for scRNA-seq, ATAC-seq, multimodal integration, spatial transcriptomics, and specialized modalities through a consistent pytorch-based API.

github-microsoft-code-reference provides lookup and verification tools for Azure SDKs, .NET libraries, and Microsoft APIs via official docs and code samples. detects hallucinated methods, wrong signatures, and deprecated patterns to prevent runtime errors.

davila7-api-fuzzing-for-bug-bounty covers reconnaissance, authentication testing, idor exploitation, injection attacks, and graphql-specific vectors with concrete payloads and tool references, but lacks decision logic for determining when to escalate findings or adjust testing strategy based on responses.

sickn33-stitch-ui-design provides detailed guidance on constructing effective prompts for google stitch, covering specificity, visual styling, multi-screen flows, and iteration strategies with templates and common use cases.

github-git-commit automates conventional commit creation by analyzing diffs to infer type and scope, with interactive staging and message generation. enforces safety constraints around hooks and destructive operations.

obra-writing-plans guides creation of detailed implementation roadmaps from specs, with task decomposition, file mapping, and bite-sized step breakdowns. targets engineers new to a codebase by enforcing complete code samples and exact file paths.

davila7-writing-clearly-and-concisely applies strunk's elements of style and ai pattern detection to improve prose for documentation, commits, ui text, and reports. covers grammar, composition principles, and anti-patterns to avoid.

coder-code-review analyzes pull requests and diffs for bugs, security flaws, and quality issues with coder-specific patterns for authorization, error handling, and shell scripting. emphasizes impact-driven feedback and skips theoretical problems.

davila7-pricing-strategy covers value-based pricing frameworks, research methods (Van Westendorp, MaxDiff), tier design, and monetization tactics. provides structured guidance on packaging, value metrics, and pricing increases with examples but lacks explicit failure handling.

davila7-referral-program provides structured guidance for designing and optimizing customer referral and affiliate programs. covers program mechanics, incentive frameworks, viral coefficient modeling, and fraud prevention with example implementations and email templates.

affaan-m-coding-standards provides conventions and code examples for typescript, javascript, react and node.js projects, covering naming, immutability, error handling, and file organization. lacks decision logic and explicit failure recovery guidance.

anthropics-audit-support provides sox 404 control testing frameworks covering scoping, sample selection methodology, workpaper standards, and deficiency classification. structured reference material for audit professionals but lacks invocation triggers and operational workflows.

affaan-m-java-coding-standards covers naming, immutability, optional handling, streams, exceptions, generics and project layout for spring boot services. establishes principles but lacks actionable decision logic for enforcement.

anthropics-claude-opus-4-5-migration handles model string updates and beta header removal across four platforms, with conditional prompt adjustments for known behavioral differences. limited to sonnet/opus migrations, excludes haiku.

davila7-it-operations covers itil frameworks, incident management, monitoring strategies, and operational excellence. provides decision matrices and workflows for alert configuration, change management, and capacity planning, but lacks concrete triggering conditions and vendor-specific automation examples.

davila7-gene-database wraps ncbi gene search and retrieval via e-utilities and datasets api, supporting symbol/id lookups, batch processing, and structured data output for annotation workflows.

wshobson-architecture-decision-records provides templates and governance patterns for capturing technical decisions. covers lifecycle management, review processes, and multiple template formats (madr, lightweight, y-statement, deprecation, rfc). lacks specific trigger phrases and acknowledges few failure modes.

deep-research provides a templated research framework with systematic source evaluation and structured output formatting. covers multi-perspective synthesis and citation discipline but lacks concrete fallback strategies for information gaps or source conflicts.

openai-vercel-deploy handles instant project deployment to vercel with preview-by-default behavior, cli detection, and a fallback script-based method when authentication fails.