@alirezarezvani

stripe-integration-expert provides production patterns for subscriptions, upgrades, usage-based billing, and idempotent webhooks across next.js, express, and django. covers lifecycle state management, proration preview, customer portal, and local testing via stripe cli.

security-pen-testing covers offensive vulnerability discovery across web apps, apis, and infrastructure through systematic owasp top 10 audits, static analysis, dependency scanning, secret detection, and responsible disclosure workflows with structured reporting.

board-deck-builder structures executive narratives across 11 c-suite sections, enforcing specific targets, variance explanations, and credible ask statements rather than data-dump decks. it covers quarterly, monthly, and fundraising cadences with explicit guardrails against common pitfalls.

autoresearch-agent runs autonomous experiment loops that iteratively edit a target file, measure outcomes against a fixed metric, and retain only improvements via git. supports engineering (speed, size, tests), marketing (copy, ctr), and custom domains with built-in and user-defined evaluators.

pr-review-expert provides systematic code review for GitHub and GitLab with blast radius analysis, security scanning, test coverage deltas, and breaking change detection. produces prioritized findings across 30+ checklist items.

board-meeting orchestrates isolated c-suite deliberation across six phases to surface independent perspectives, flag groupthink, and extract founder-approved decisions into versioned memory. role-specific reasoning techniques and adversarial critique prevent consensus hallucination.

saas-scaffolder generates a complete next.js project with nextauth, drizzle orm, stripe billing, and shadcn/ui components. includes auth middleware, database migrations, webhook handlers, and a five-phase validation checklist for local and production deployment.

azure-cloud-architect guides infrastructure design across five patterns (web app, microservices, serverless, data pipeline, multi-region) with bicep generation, cost analysis, and security review checkpoints. produces actionable templates and ci-cd pipeline scaffolds.

contract-and-proposal-writer generates jurisdiction-aware business documents (contracts, proposals, SOWs, NDAs, MSAs) with templated markdown output and pandoc conversion instructions. covers us, eu, uk, and dach legal regimes with gdpr data processing addenda and clause customization.

chief-of-staff routes founder questions to c-suite roles based on complexity scoring, coordinates board meetings for irreversible decisions, and surfaces advisor disagreements without smoothing conflict. routes to 28 downstream skills with loop prevention and decision logging.

api-test-suite-builder scans framework-agnostic api route definitions and generates comprehensive test suites covering auth, validation, error codes, pagination, file uploads, and rate limiting. outputs ready-to-run test files for multiple frameworks and languages.

ab-test-setup provides structured guidance for designing statistically valid a/b tests, covering hypothesis formation, sample size calculation, variant design, and results interpretation. includes checklists and guardrail metrics to prevent common execution errors.

performance-profiler covers systematic bottleneck identification across node.js, python, and go via cpu/memory profiling, flamegraphs, bundle analysis, database optimization, and load testing with mandatory before-after measurement discipline.

database-schema-designer guides relational schema creation from requirements through normalization, migration generation, type synthesis, and multi-tenant patterns. covers rls policies, seed data, and erd diagramming with concrete examples.

prompt-engineer-toolkit provides structured A/B testing, version control, and regression workflows for prompt optimization across marketing and AI content tasks, with quantitative scoring and immutable history.

agent-protocol defines a formal syntax and ruleset for inter-agent communication within c-suite teams, including invocation format, loop prevention, isolation constraints, and response templates designed to prevent circular reasoning and enforce decision hierarchy.

init scaffolds a playwright testing environment by detecting the project framework, generating config files tailored to react/next/vue/angular, creating folder structure and ci workflows, then running the first test to verify setup.

pr-review-expert provides systematic code review for github and gitlab prs, combining blast radius analysis, security scanning, test coverage delta measurement, and breaking change detection into a structured 30-item checklist with prioritized findings.

chief-of-staff routes founder questions to c-suite roles based on complexity scoring, triggers board meetings for irreversible multi-domain decisions, synthesizes outputs with explicit conflict surfacing, and maintains a decision log for tracking and review.

ms365-tenant-manager provides step-by-step powershell automation for global administrators covering tenant setup, user lifecycle, conditional access policies, and offboarding workflows with validation checkpoints.

aws-solution-architect guides users through designing and deploying scalable aws architectures via six-step workflow: requirement gathering, pattern selection, iac generation, cost analysis, deployment, and validation. covers serverless, microservices, and three-tier patterns with cloudformation and cdk templates.

loop runs recurring ai experiment iterations at configurable intervals (10m, 1h, daily, weekly, monthly), automating one strategic change per cycle, committing results, and evaluating against stored metrics until manual stop or 3-day expiry.

senior-data-scientist covers a/b testing, feature engineering, model evaluation, and difference-in-differences causal inference with working code examples and checklists. domain-specific but lacks explicit failure mode handling and deployment specifics.

experiment-designer covers hypothesis formulation, sample size estimation, experiment prioritization via ice scoring, and statistical result interpretation for product decisions.

email-template-builder provides react email templates, multi-provider integration (resend, postmark, sendgrid, aws ses), i18n support, dark mode, and a local preview server. covers welcome, verification, invoice, and digest templates with spam optimization guidance.

intl-expansion provides a structured framework for entering new markets via market selection scoring, entry mode selection, localization planning, and go-to-market execution. covers regulatory assessment, team structure decisions, and common failure patterns.

research-summarizer extracts key findings from academic papers, articles, and reports into structured briefs with proper citation handling. includes multi-source comparison, quality assessment scoring, and five citation formats.

spec-to-repo interprets natural language project descriptions and generates complete, runnable starter repositories with real code across multiple stacks. it parses specs into structured interpretations, designs architecture before generation, and validates output against a comprehensive checklist.

code-tour generates persona-targeted CodeTour JSON files for VS Code, creating structured walkthroughs that anchor to specific files and line numbers without modifying source code.

fix diagnoses and repairs flaky playwright tests by running targeted reproduction steps, categorizing failures against a taxonomy, and applying targeted fixes with verification loops.

product-strategist provides okr cascade generation, alignment scoring, and quarterly planning templates for heads of product. covers five strategy archetypes (growth, retention, revenue, innovation, operational) with configurable team structures and json export.

competitor-alternatives covers creation of comparison and alternative pages across four formats (singular alternative, plural alternatives, vs pages, and competitor-vs-competitor). includes research process, content architecture, seo strategy, and output templates but lacks concrete step-by-step procedures for execution.

agent-workflow-designer provides pattern templates and scaffolding for multi-agent orchestration, covering sequential, parallel, and hierarchical workflows with handoff contracts and cost controls. focuses on structural decisions before implementation rather than runtime execution.

merge integrates winning agent branches into base, archives losing branches via git tags, and cleans up worktrees after competitive evaluation sessions.

eval ranks agent results across a session using configurable metrics, git diffs, or llm judgment. supports metric mode, judge mode, and hybrid evaluation with tie-breaking logic.

promote migrates learned patterns from claude's auto-memory into the project rule system, converting descriptive notes into enforced instructions scoped to files or the entire codebase.

cs-google-workspace-cli automates google workspace administration via the gws command-line tool, covering gmail, drive, sheets, calendar, and tasks through recipes, personas, and security audits. installation and authentication are documented but edge cases are sparse.

senior-data-engineer covers architectural decisions (batch vs streaming, lambda vs kappa) and tech stack selection for scalable pipelines. decision frameworks and trigger phrases present, but procedural depth and failure mode coverage lag behind.

marketing-strategy-pmm covers positioning, ICP definition, competitive intelligence, and launch planning with structured templates and workflows. lacks specific trigger phrases and edge case handling for real-world constraints.

browserstack integrates playwright testing across cloud browsers and devices via remote websocket endpoints. covers setup, execution, results retrieval, and local tunnel support for cross-browser validation.

content-production covers research, drafting, and optimization workflows for long-form technical and saas content. it structures work across three modes (brief, draft, polish) with emphasis on competitive analysis, readability gates, and seo fundamentals.

adversarial thinking partner that stress-tests plans, surfaces hidden assumptions, and prepares founders for hard decisions with no good options. focuses on finding failure modes before boards or customers do.

monorepo-navigator covers workspace analysis, selective builds, dependency visualization, and migrations across turborepo, nx, pnpm, and lerna. includes remote caching optimization and npm publishing workflows with claude code integration.

migrate converts Cypress or Selenium test suites to Playwright with file-by-file translation, framework detection, and scope assessment. requires external mapping references and manual verification of each converted file.

board provides a markdown-based message board for multi-agent coordination, supporting channel-scoped posts with metadata, read/list/post operations, and thread replies via a python script interface.

api-design-reviewer checks rest apis against naming conventions, http semantics, and status code correctness. linting is rule-based, but the skill lacks clear triggering context and actionable remediation steps.

changelog-generator automates release notes from conventional commits by parsing, semantic versioning detection, and keep a changelog rendering. supports ci integration and editorial oversight via structured output.

ad-creative coaches the user through gathering product and audience context before generating ad copy, but the actual generation procedure remains underspecified and the skill lacks explicit decision logic or platform-specific constraints.

landing-page-generator outputs production-ready tsx components with hero variants, feature grids, pricing tables, and faq sections. generates tailwind-styled markup with seo meta and copy frameworks targeting web vitals targets.

board-prep coaches founders through adversarial preparation for board meetings, emphasizing cold memorization of metrics, anticipation of hard questions, and narrative framing that acknowledges weakness. covers five phases from number fluency through post-meeting follow-up.

social-content guides multi-platform content creation via content pillars, hook formulas, repurposing workflows, and engagement routines. covers strategy over execution, lacks platform-specific api integration and failure mode handling.

competitive-intel maps competitor landscape, builds sales battlecards, and tracks win/loss patterns. triggers cover common queries (landscape, battlecard, winloss) but procedure lacks depth and edge cases go unaddressed.

copywriting covers marketing page copy across page types (homepage, landing, pricing, feature, about) with emphasis on clarity, specificity, and benefit framing. includes discovery questions, writing principles, section templates, and output formats but lacks concrete decision logic.

analytics-tracking covers ga4 and gtm setup, event taxonomy, and data quality audits. it emphasizes avoiding duplicate events and unconsented tracking but lacks concrete step-by-step procedures and specific trigger phrases.

tech-stack-evaluator provides frameworks for comparing technologies via weighted scoring, tco analysis, and ecosystem health metrics. execution relies on referenced scripts rather than embedded procedure, limiting actionability without external tooling.

prompt-engineer-toolkit provides a/b testing and versioning for prompt engineering workflows, supporting quantitative scoring and regression detection across prompt iterations and model changes.

cs-onboard captures founder context through a 45-minute structured conversation across 7 unstated dimensions, with lightweight quarterly refresh option. conversation-first approach, but procedural specifics and failure modes absent.

context-engine bootstraps c-suite advisor skills by loading and validating company context from disk, detecting staleness over 90 days, and prompting refresh workflows. core memory layer, but execution details remain vague.

senior-qa provides command-line scaffolding for jest unit tests, coverage analysis, and playwright e2e tests in react/next.js projects. lacks procedural depth and failure handling.

self-improving-agent curates claude code's auto-memory into durable project knowledge by analyzing pattern frequency, promoting proven learnings to persistent config, and extracting reusable skill templates from recurring solutions.

incident-commander covers severity triage, timeline reconstruction, and post-incident review generation with templated communication and runbook integration, but lacks concrete procedural depth and failure mode guidance.

a11y-audit scans codebases for wcag 2.2 violations, provides framework-specific fixes for react/vue/angular/svelte/next.js/html, and generates compliance reports suitable for ci/cd integration.

decision-logger separates raw meeting transcripts from founder-approved decisions across two layers, preventing stale consensus from contaminating future deliberations. includes conflict detection and overdue action tracking.

marketing-context establishes foundational positioning and messaging for downstream marketing workflows by maintaining a single source of truth document. operates in three modes: auto-draft from repo analysis, guided interview, or incremental updates.

release-manager covers changelog generation from conventional commits, semantic versioning, release readiness checks, and coordination templates. lacks step-by-step procedures and explicit failure handling for production scenarios.

run conducts a single experiment iteration: loads prior context, proposes edits to a target file, evaluates outcomes, and stores results for review. incomplete specification leaves implementation ambiguous.

llm-wiki guides incremental knowledge base construction in obsidian where an lm agent ingests sources, updates markdown notes, and maintains cross-references as a persistent compounding system rather than ephemeral rag.

sql-database-assistant translates requirements into sql queries, optimizes performance across multiple database engines, generates migrations with rollback strategies, and integrates with popular orms. intended for day-to-day database operations bridging application code and schema.

agenthub orchestrates parallel competitive agents in isolated git worktrees, evaluating and merging results. lacks concrete procedural steps and failure handling for production use.

ciso-advisor provides risk quantification and compliance sequencing for growth-stage companies, translating technical security gaps into dollar impact and regulatory roadmaps. incomplete procedures and vague execution pathways limit adoption.

ma-playbook outlines frameworks for acquisition and being acquired, covering strategic rationale, due diligence, valuation, and integration. structure and sequencing present but incomplete, missing detailed decision trees and measurable outcomes.

resume restarts paused experiments by loading full context from git branches and results history, then presents the user with actionable next steps (single iteration, autonomous loop, or review).

brand-guidelines provides a templated approach to brand consistency work, with special handling for anthropic systems. lacks concrete decision trees and failure recovery strategies.

churn-prevention addresses voluntary and involuntary churn through cancel flow design, save offers, exit surveys, and dunning sequences. establishes context-gathering requirements but lacks concrete implementation steps.

coverage maps application surfaces against existing tests to identify untested routes, components, and api endpoints. it produces a prioritized gap analysis ranked by business impact, with effort estimates and template recommendations for remediation.

pricing-strategy covers value-based positioning and tier design for saas, but lacks concrete procedures and decision gates. treats pricing as philosophy rather than workflow.

onboarding-cro helps diagnose and optimize new user activation by identifying drop-off points and defining measurable aha moments, but lacks concrete implementation procedures.

cloud-security detects iam privilege escalation, public storage exposure, and infrastructure misconfigurations through systematic posture assessment, explicitly excluding active incident response and application vulnerability scanning.

site-architecture covers website structure, navigation design, and internal linking strategy. lacks concrete procedural steps and assumes significant user knowledge about information architecture principles.

ms365-tenant-manager provides powershell command templates for auditing and provisioning m365 tenants, but lacks procedural depth, error handling documentation, and actionable intent mapping.

review audits playwright test files for anti-patterns and coverage gaps. it checks for critical issues like hardcoded waits and missing assertions, then generates file-by-file scores and fix recommendations.

quality-manager-qms-iso13485 outlines iso 13485 qms workflows for medical device orgs, but lacks actionable procedure depth, specific trigger phrases, and failure mode handling needed for operational use.

quality-manager-qmr outlines iso 13485 compliance responsibilities for senior quality leadership including management review, kpi oversight, and regulatory governance, but lacks actionable procedures and concrete trigger conditions.

confluence-expert provides basic mcp operations for space and page management but lacks actionable workflows, decision logic, and guidance on permission hierarchies or failure scenarios.

rag-architect describes chunking strategies and vector database concepts but lacks actionable procedures, decision trees, or failure recovery paths. reads as reference material rather than executable workflow.

internal-narrative helps teams craft audience-specific messaging around core facts without contradicting the underlying truth. it identifies narrative gaps and aligns communication across employees, investors, customers, candidates, and partners.

signup-flow-cro provides a framework for reducing friction in account creation and trial flows. covers audit structure, common patterns, and experiment ideas, but lacks actionable step-by-step procedures and concrete decision criteria.

apple-hig-expert frames itself as a senior design lead offering guidance on apple interface standards, liquid glass aesthetics, and accessibility across iOS, macOS, watchOS, and visionOS. lacks concrete procedural steps and testable outputs.

social-media-analyzer computes engagement rates, roi, and platform benchmarks for instagram, facebook, twitter/x, linkedin, and tiktok campaigns. identifies top/bottom posts and flags performance anomalies.

ceo-advisor provides frameworks for executive leadership including strategy, fundraising, and board management, but the execution guidance is mostly aspirational rather than procedural.

extract turns recurring debugging solutions or patterns into reusable, portable skills with structured SKILL.md output, supporting interactive and templated workflows.

senior-computer-vision outlines production cv work across detection, segmentation, and deployment. table of contents maps to workflows and selection guides but lacks procedural depth and concrete decision-making logic.

senior-pm catalogs portfolio management patterns and risk quantification frameworks, but lacks actionable procedures, specific trigger conditions, and recovery strategies for real-world execution.

database-designer covers schema normalization analysis, constraint detection, and erd generation. lacks concrete procedures, decision logic, and failure-mode handling required for production migration and query optimization work.

contract-and-proposal-writer generates templated business documents across multiple jurisdictions (us, eu, uk, dach) with markdown output and docx conversion notes. lacks actionable procedural depth and specific integration triggers.

cfo-advisor provides financial modeling templates and metric calculators for startup finance leaders, covering burn rate, unit economics, and board reporting. execution details and integration paths are absent.

paid-ads covers campaign creation and optimization across google ads, meta, linkedin, and other platforms. requires gathering campaign goals, budget, and constraints before proceeding. lacks structured decision logic and concrete procedures.

competitive-teardown captures product and competitive positioning by aggregating pricing pages, app store reviews, job postings, and social signals into actionable market analysis. it lacks procedural specificity and failure-mode awareness.

dependency-auditor claims comprehensive multi-language dependency analysis covering vulnerabilities, licenses, and upgrade planning, but the skill.md is incomplete and lacks actionable procedures.

org-health-diagnostic claims to score eight organizational dimensions on a traffic-light scale but provides no actual scoring methodology, dimension definitions, benchmarks, or decision logic. the skill.md is essentially marketing copy without procedural substance.

company-os frames operational dysfunction as a systems problem, sketching frameworks (eos, okr, l10 meetings) for explicit management rhythms but stops short of actionable integration.

popup-cro covers conversion-focused popup design, modal optimization, and exit-intent strategies. provides purpose taxonomy and initial assessment framework, but lacks actionable implementation steps and failure mode handling.

seo-audit provides a framework for systematic SEO diagnosis with clear output templates and tool references, but lacks concrete procedural steps and fails to account for common failure modes like access restrictions or incomplete data.

ai-seo teaches optimization for generative engine visibility, helping content get cited by major ai platforms rather than ranked in traditional search. focuses on audit and inventory gathering before execution.

scenario-war-room models compound what-if scenarios across business functions to expose cascading failure modes. lacks procedural depth and concrete decision logic.

referral-program provides a conversational framework for building referral mechanics by gathering product and customer context. lacks concrete procedure, measurement spec, and failure-mode coverage.

marketing-ops acts as a router and orchestrator for the marketing skill ecosystem, directing questions to appropriate specialists, coordinating multi-skill campaigns, and running cross-functional audits. works best with prerequisite context.

skill-security-auditor scans skills for security risks and produces pass/warn/fail verdicts. lacks detailed procedural steps, edge case handling, and specific trigger definitions.

hard-call is a framework for navigating irreversible decisions with no clearly correct outcome. it identifies why certain calls are cognitively and emotionally difficult but lacks actionable procedure.

cto-advisor provides keyword lists and script references for technology strategy work, but lacks procedural substance, decision frameworks, or actionable guidance on architectural choices, team scaling, or tech debt remediation.

risk-management-specialist outlines iso 14971 compliance across medical device lifecycles via planning, analysis, evaluation, and control workflows. structure provided but lacks procedural depth and executable steps.

founder-coach outlines founder development as a scaling constraint, identifying common leadership ceilings and archetypes, but lacks actionable procedures and concrete trigger conditions to activate coaching interventions.

chro-advisor maps business goals to people planning across hiring, compensation, and org structure, but lacks operational specificity and decision trees needed for reliable execution.

migration-architect outlines strategic migration planning capabilities including phasing, risk assessment, and rollback approaches, but lacks procedural specificity and actionable implementation details.

cro-advisor covers revenue frameworks and forecasting models aimed at b2b saas scaling, but the skill.md lacks procedural depth, trigger specificity, and failure-case handling needed for reliable execution.

culture-architect frames culture as observable operational behavior rather than aspiration, providing some workshop scaffolding and diagnostic lenses. coverage is fragmentary and lacks actionable instrumentation for sustained measurement or change.

marketing-skills bundles 42 marketing agent tasks across 7 domains (content, seo, cro, channels, etc) with routing via marketing-ops. lacks concrete procedures, error handling, and actionable step-by-step guidance.

isms-audit-expert attempts to organize iso 27001 audit workflows via table of contents sections, but lacks actionable procedures, trigger specificity, and failure mode coverage. mostly structural promises without operational depth.

capa-officer outlines a quality management framework for corrective and preventive actions but lacks operational depth, specific procedures, and actionable decision logic needed for skill automation.

observability-designer attempts to guide metric selection and dashboard layout for monitoring systems, but lacks concrete procedures, specific triggers, and actionable guidance on implementation or failure recovery.

engineering-skills is a catalog index listing 32 skill names and folders with minimal procedural content. it reads as a table of contents rather than actionable guidance, lacking step-by-step workflows or decision logic for any individual skill.

deprecated redirect skill that maps legacy content-creator requests to content-production or content-strategy based on user intent. provides no actionable procedure, only routing logic.

postmortem provides a framework for analyzing organizational failures without blame, focusing on systemic root causes and learning extraction rather than scapegoating or superficial remediation.

scrum-master attempts to provide sprint analytics and team coaching but remains schematic, deferring substance to external references rather than containing complete, actionable procedures.

content-humanizer applies voice transformation to machine-generated text by consulting brand guidelines and audience context, but lacks concrete procedural steps and actionable decision criteria.

cmo-advisor covers strategic marketing leadership including brand positioning, growth model design, and budget allocation. execution details are sparse and the skill lacks actionable procedure.

cpo-advisor covers strategic product leadership (vision, portfolio, pmf, org design) at the company level. includes a pmf scoring script but lacks actionable procedures for actual decision-making.

senior-secops is a collection of high-level capability labels without concrete procedures, decision logic, actionable steps, or failure handling. it reads as a table of contents for documentation that was never written.

gdpr-dsgvo-expert promises compliance automation via codebase scanning and dpia generation, but the provided skill.md is a table of contents skeleton with no actionable procedures, trigger phrases, or recovery logic.

fda-consultant-specialist outlines major regulatory topics (510(k), qsr, hipaa, cybersecurity) but lacks substantive procedural depth, actionable steps, or specific trigger conditions for medical device regulatory guidance.

generate creates playwright test files from user stories or component names. the skill lacks detail on implementation steps, error handling, and specification of what production-ready actually means in this context.

testrail covers bidirectional sync between playwright tests and testrail, with environment setup and test case import capability mentioned but procedures incomplete.

incomplete skill definition consisting only of section headers with no executable procedures, inputs, outputs, or decision logic implemented.

senior-fullstack is a stub with no actionable procedures, trigger phrases, or implementation details. it reads as an incomplete template.

Router/index for the 2 finance skills bundled in this plugin: financial-analyst (ratio analysis, DCF valuation, budget variance, rolling forecasts) and…

Router/index for the 4 business & growth skills bundled in this plugin: customer-success-manager (health scoring, churn risk, expansion), sales-engineer (RFP…

Use when coordinating project-delivery work across the 8 project-management sub-skills — sprint/velocity analytics, portfolio health, Jira/JQL, Confluence,…

10 C-level advisory agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. CEO, CTO, COO, CPO, CMO, CFO, CRO, CISO, CHRO, Executive…

spawn — an installable skill for AI agents, published by alirezarezvani/claude-skills.

stress-test — an installable skill for AI agents, published by alirezarezvani/claude-skills.

challenge — an installable skill for AI agents, published by alirezarezvani/claude-skills.

setup — an installable skill for AI agents, published by alirezarezvani/claude-skills.

ra-qm-skills — an installable skill for AI agents, published by alirezarezvani/claude-skills.

remember — an installable skill for AI agents, published by alirezarezvani/claude-skills.

Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, ex...

Generates high-converting landing pages as complete Next.js/React (TSX) components with Tailwind CSS. Creates hero sections, feature grids, pricing tables, F...

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when...

Atlassian Administrator for managing and organizing Atlassian products (Jira, Confluence, Bitbucket, Trello), users, permissions, security, integrations, sys...

When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions \"content…

Analyzes campaign performance with multi-touch attribution, funnel conversion analysis, and ROI calculation for marketing optimization. Use when analyzing…

This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement…

focused-fix — an installable skill for AI agents, published by alirezarezvani/claude-skills.

UI design system toolkit for Senior UI Designer including design token generation, component documentation, responsive design calculations, and developer…

App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on…

ISO 13485 internal audit expertise for medical device QMS. Covers audit planning, execution, nonconformity classification, and CAPA verification. Use for…

Honestly evaluate AI work quality using a two-axis scoring system. Use after completing a task, code review, or work session to get an unbiased assessment.…

When the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages…

When the user wants to optimize any form that is NOT signup/registration — including lead capture forms, contact forms, demo request forms, application forms,…

|

When the user wants to develop social media strategy, plan content calendars, manage community engagement, or grow their social presence across platforms. Also…

Use when defining product KPIs, building metric dashboards, running cohort or retention analysis, or interpreting feature adoption trends across product stages.

>

Use when preparing roadmap narratives, release notes, changelogs, or stakeholder updates tailored for executives, engineering teams, and customers.

Use when the user asks to set up secret management infrastructure, integrate HashiCorp Vault, configure cloud secret stores (AWS Secrets Manager, Azure Key…

Generate pragmatic CI/CD pipelines from detected project stack signals — fast baseline generation, repeatable checks, environment-aware deployment stages. Use…

When the user wants to plan a product launch, feature announcement, or release strategy. Also use when the user mentions 'launch,' 'Product Hunt,' 'feature…

Manage environment-variable hygiene and secrets safety across local development and production. Practical auditing, drift awareness, rotation readiness. Use…

Security engineering toolkit for threat modeling, vulnerability analysis, secure architecture, and penetration testing. Includes STRIDE analysis, OWASP…

Comprehensive toolkit for product managers including RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, and go-to-market…

runbook-generator — an installable skill for AI agents, published by alirezarezvani/claude-skills.

Atlassian Administrator for managing and organizing Atlassian products (Jira, Confluence, Bitbucket, Trello), users, permissions, security, integrations,…

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed…

terraform-patterns — an installable skill for AI agents, published by alirezarezvani/claude-skills.

saas-metrics-coach — an installable skill for AI agents, published by alirezarezvani/claude-skills.

skill-tester — an installable skill for AI agents, published by alirezarezvani/claude-skills.

When the user wants to implement, audit, or validate structured data (schema markup) on their website. Use when the user mentions 'structured data,'…

Scan codebases for technical debt, score severity, track trends, and generate prioritized remediation plans. Use when users mention tech debt, code quality,…

Use when the user asks to create a demo video, product walkthrough, feature showcase, animated presentation, marketing video, or GIF from screenshots or scene…

Audit datasets for completeness, consistency, accuracy, and validity. Profile data distributions, detect anomalies and outliers, surface structural issues, and…

When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,'…

Operations leadership for scaling companies. Process design, OKR execution, operational cadence, and scaling playbooks. Use when designing operations, setting…

When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth…

Analyzes meeting transcripts and recordings to surface behavioral patterns, communication anti-patterns, and actionable coaching feedback. Use this skill…

Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when…

Use when the user asks to design multi-agent systems, create agent architectures, define agent communication patterns, or build autonomous agent workflows.

When the user wants to build a free tool for marketing — lead generation, SEO value, or brand awareness. Use when they mention 'engineering as marketing,'…

Helm chart development agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw — chart scaffolding, values design, template patterns,…

When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates. Also use when the user mentions "paywall,"…

Use when validating product opportunities, mapping assumptions, planning discovery sprints, or testing problem-solution fit before committing delivery…

>

When the user wants to write, improve, or build a sequence of B2B cold outreach emails to prospects who haven't asked to hear from them. Use when the user…

When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental…

Framework for rolling out organizational changes without chaos. Covers the ADKAR model adapted for startups, communication templates, resistance patterns, and…

Use when the user asks to automate browser tasks, scrape websites, fill forms, capture screenshots, extract structured data from web pages, or build web…

email-sequence — an installable skill for AI agents, published by alirezarezvani/claude-skills.

When the user wants to optimize, improve, or increase conversions on any marketing page — including homepage, landing pages, pricing pages, feature pages, or…

soc2-compliance — an installable skill for AI agents, published by alirezarezvani/claude-skills.

interview-system-designer — an installable skill for AI agents, published by alirezarezvani/claude-skills.

Use when writing, reviewing, or committing code to enforce Karpathy's 4 coding principles — surface assumptions before coding, keep it simple, make surgical…

Frontend development skill for React, Next.js, TypeScript, and Tailwind CSS applications. Use when building React components, optimizing Next.js performance,…