Claude Skills by paulasilvatech

Define evidence-based typography, semantic color, layout, density, imagery, iconography, themes, and motion within an existing product system. Use this skill when frontend visual direction, design tokens, theming, composition, or visual-quality review is requested.

Explore a website with Playwright MCP, identify 3-5 core user flows, capture locators and expected outcomes, close the browser context, and propose test cases. Use this skill when the user asks to explore a site for testing, map UI functionality, discover test scenarios, or produce Playwright-ready interaction notes.

Generate, save, run, and stabilize Playwright TypeScript tests from a user scenario using Playwright MCP exploration evidence. Use this skill when the user asks to create a Playwright test, generate an @playwright/test spec from a scenario, automate a browser flow, or turn Playwright MCP history into a passing test.

Craft immersive, high-performance web interfaces with advanced motion, typography, scroll-driven interactions, responsive polish, and product-specific visual direction. Use this skill when the user asks for premium frontend UI, sophisticated animations, Awwwards-style components, high-end landing pages, layout polish, or high-end visual design implementation.

Inspect local or remote website design, identify layout, responsive, accessibility, and visual consistency defects, and make source-level fixes. Use when users ask to "review website design", "check the UI", "fix the layout", "find design problems", or validate a web page after changes.

Explore a website with Playwright MCP, identify 3-5 core user flows, capture locators and expected outcomes, close the browser context, and propose test cases. Use this skill when the user asks to explore a site for testing, map UI functionality, discover test scenarios, or produce Playwright-ready interaction notes.

Generate, save, run, and stabilize Playwright TypeScript tests from a user scenario using Playwright MCP exploration evidence. Use this skill when the user asks to create a Playwright test, generate an @playwright/test spec from a scenario, automate a browser flow, or turn Playwright MCP history into a passing test.

Analyze git diffs, staged changes, or plain change descriptions and generate narrative Conventional Commits messages that explain why the change matters. Use when asked to "write a commit message", "generate a commit", "describe my changes", "what should I commit this as", "commit this", "summarize my diff", or "help me commit".

Create, normalize, validate, and check out Git branches following the Conventional Branch specification with feature/, bugfix/, hotfix/, release/, and chore/ prefixes. Use when creating a new branch, naming a branch, or checking branch-name compliance.

Run a GitHub Copilot Code Review loop on a pull request: request review with GraphQL, wait, list open Copilot/human/advanced-security threads, triage fix/decline/escalate, dispatch bounded fixes, build/test/lint, commit per iteration, reply and resolve, then re-trigger until HEAD is reviewed and no threads await the agent. Use for address copilot comments, run a copilot review loop, fix this PR, or iterate on copilot feedback.

Comprehensive guide for configuring and managing GitHub Dependabot. Use this skill when users ask about creating or optimizing dependabot.yml files, managing Dependabot pull requests, configuring dependency update strategies, setting up grouped updates, monorepo patterns, multi-ecosystem groups, security update configuration, auto-triage rules, or any GitHub Advanced Security (GHAS) supply chain security topic related to Dependabot. For pre-commit dependency vulnerability scanning in AI codin...

Upload, download, and embed GitHub user-attachments with the gh attach extension for screenshots, images, PDFs, zip files, and videos. Use this skill when asked to attach a screenshot to a PR, add an image to an issue, embed before/after media, attach a local file, or download a GitHub attachment.

Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping

Analyze git status and diffs, classify work using the nvie Git Flow branching model, generate a semantic branch name, and create the branch from the correct source branch. Use this skill when the user asks to start a feature, bugfix, release, hotfix, or support branch, create a Git Flow branch, or choose a branch name from current changes.

Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, set issue fields (dates, priority, custom fields), set issue types, manage issue workflows, link issues, add dependencies, or track blocked-by/blocking relationships. Triggers on requests like "create an issue", "file a bug", "request a feature", "update issue X", "set the priority", "set the ...

Run an end-to-end GitHub library release workflow with git and gh: inspect tags, classify public API changes, choose a SemVer bump, update CHANGELOG.md, create release/vX.Y.Z, push, and open a release PR. Use when asked to cut a release, bump a version, generate a changelog, create a release branch, or publish a new GitHub repository version.

Generate commit messages that follow the gitmoji convention (https://gitmoji.dev) by choosing the single best emoji or shortcode for a diff, staged change, or plain-language change description. Use when asked to write a gitmoji commit, add an emoji to a commit message, choose a gitmoji, gitmoji this change, or follow a gitmoji-style commit history. Generates the message only and does not run git commands.

Bulk-migrate GitHub metadata into organization issue fields from repository labels or Project V2 fields. Use when asked to migrate labels to issue fields, copy project field values to issue fields, convert priority labels, adopt structured issue metadata, or clean up labels after migration.

Follow repository contribution guidance safely before creating issues, branches, commits, pushes, or pull requests. Use when the user asks for contribution guidelines, issue creation, commit messages, pushing code, PR creation, or repository-specific contribution workflow.

Open a browser-based GitHub pull request dashboard for a date range and role filter using the bundled CLI. Use when the user asks to show my PRs, open PR dashboard, check pull request status, see requested reviews, assigned PRs, all involved PRs, or review PR activity for a week, month, year, or explicit date range.

Audit GitHub Actions workflow efficiency and recommend fixes that reduce CI runtime, runner minutes, and wasted workflow runs. Use when the user asks about caching, concurrency, path filters, matrix reduction, job optimization, workflow cost, or CI baseline design.

Review, audit, author, and harden GitHub Actions workflows against Actions-specific threats: untrusted-input script injection, privileged trigger escalation, mutable action references, over-scoped GITHUB_TOKEN permissions, unsafe GITHUB_ENV/GITHUB_OUTPUT writes, secret exposure, OIDC misuse, and self-hosted runner risk. Use for .github/workflows/*.yml, secure my CI, pull_request_target danger, SHA pinning, or permissions lockdown.

Upgrade GitHub Actions workflow dependencies to supported runtimes while preserving behavior. Use this skill when logs report deprecated Node.js action runtimes, when editing `.github/workflows/*.yml` or `.github/workflows/*.yaml`, or when choosing pinned action versions and validating upgraded workflow runs.

Generate a complete Go Model Context Protocol server project using github.com/modelcontextprotocol/go-sdk with module layout, typed tools, resources, config, graceful shutdown, tests, and README. Use when the user asks for a Go MCP server project generator, Go MCP tools, stdio transport, or a production-ready MCP server scaffold.

Analyze ad campaign performance data to diagnose waste, identify winners, validate A/B tests, compare channels, and recommend cuts, scaling, tests, and budget reallocation. Use when the user asks to analyze ad campaigns, find wasted spend, optimize Google Ads, Meta Ads, LinkedIn Ads, ROAS, CPA, CAC, or multi-channel ad budgets.

Analyze public competitor paid ads from Meta Ad Library and Google Ads Transparency Center, cluster creative hooks, inspect landing pages, infer funnel strategy, identify vulnerabilities, and recommend counter-plays. Use this skill when asked what ads a competitor is running, to tear down ad strategy, reverse-engineer a paid funnel, find paid ad angles, or audit the ad landscape.

Launch new products from idea to first customers by choosing direct outreach over vanity press, diagnosing stalls with positioning/experience/alignment layers, finding the first 10-50 customers, running 2-week experiments, validating PMF, and building launch playbooks. Use when launching products, finding early adopters, building launch week plans, or diagnosing stalled adoption.

Create go-to-market strategy for AI products, including enterprise positioning, buyer readiness, trust sequencing, variable-cost pricing, and copilot/agent/teammate framing. Use this skill when positioning AI products, handling production-responsibility objections, pricing variable-cost AI, or selling autonomous tools into enterprises.

Board meeting preparation, investor updates, and executive communication. Use when preparing board decks, writing investor updates, handling bad news with the board, structuring QBRs, or building board-level metric discipline. Includes the "Three Things" narrative model, the 4-tier metric hierarchy, and the pre-brief pattern that prevents board surprises.

Build and scale developer-led adoption through ecosystem programs. Use when deciding open vs curated ecosystems, building developer programs, scaling platform adoption, or designing student program pipelines.

Build enterprise account plans, MEDDICC qualification, stakeholder maps, economic-buyer validation, deal-health checks, and mutual action plans for complex sales cycles. Use when planning strategic enterprise deals, diagnosing stalled opportunities, deciding whether to send a proposal, or asking whether a stale MAP means the deal is dead.

Four-phase framework for onboarding enterprise customers from contract to value realization. Use when implementing new enterprise customers, preventing churn during onboarding, or solving the adoption cliff that kills deals post-go-live. Includes the Week 4 ghosting pattern.

Design operating cadence for scaling companies: meeting architecture, weekly metrics, quarterly planning, decision rights, async communication, CEO updates, and role clarity. Use when meetings do not produce decisions, alignment worsens during growth, decisions take too long, or leadership is stuck in meetings all day.

Design and scale go-to-market partner ecosystems with tiering, value exchange, build-vs-partner decisions, co-marketing, and crawl-walk-run deployment. Use when asked to structure a partner program, decide whether to build or partner, recruit or tier partners, assess partnership leverage, or plan partner-led revenue motions.

Diagnose and improve go-to-market positioning by auditing competitor messaging, finding defensible differentiation, testing claims, and planning Crawl-Walk-Run rollout. Use when messaging sounds like competitors, conversion is weak despite awareness, sales cannot explain differentiation, buyers see the product as interchangeable, or a team wants to test positioning before rebrand.

Build and evaluate product-led growth motions for self-serve acquisition, activation, freemium conversion, growth equations, channel economics, PQL handoff, forecasting, and PLG versus sales-led decisions. Use when asked whether to build PLG or sales-led, drive self-serve adoption, fix freemium conversion, plan developer-led adoption, choose growth channels, or test whether PLG will work.

Design pricing strategy for technical products by choosing seat-based, usage-based, outcome-based, hybrid, freemium, enterprise, and price-positioning models. Use when asked to price an API, developer tool, SaaS, infrastructure product, freemium tier, enterprise plan, price increase, or GTM monetization motion.

Audit a landing page, sales page, opt-in page, product page, or checkout flow for conversion leaks and return a ranked fix list ordered by expected revenue impact. Use this skill when conversion rate is low, paid traffic is not converting, CPA is above target, checkout drop-off is high, or the user asks why a page is not converting or wants a CRO review.

Set up server-side conversion tracking so purchases are reported accurately to Facebook, TikTok, Google, and Bing despite iOS restrictions, ad blockers, cookie loss, and cross-domain hops. Use this skill when conversions are under-reported, platform purchases do not match real orders, CAPI, Conversions API, Events API, offline conversions, click id passthrough, fbclid, ttclid, gclid, msclkid, or degraded ad optimization are mentioned.

Investigate AWS production incidents with CloudWatch Logs Insights, Metrics, Alarms, CloudTrail correlation, blast-radius narrowing, metric math, and incident timelines. Use when the user asks to debug CloudWatch alarms, query Logs Insights, correlate alarms to deployments, find Lambda cold starts, OOMs, timeouts, throttling, or reconstruct an AWS incident timeline.

Close bugs and incidents with an auditable BUG RECEIPT that states VERIFIED, PARTIAL, or BLOCKED based on baseline, root cause, change, proof, gaps, and evidence source. Use when the user asks for defect repair, regression proof, production incident closeout, issue closure, machine-readable receipt JSON, or CI integration of bug evidence.

Turn vague, intermittent, or environment-specific bug reports into minimal evidence-backed reproductions before diagnosis or repair. Use when a bug report is incomplete, mixed with an assumed cause, hard to reproduce, or needs observed failure, environment, expected/actual behavior, repeatability, and safe next hypothesis.

Generate production-ready DevOps rollout plans for infrastructure, application, configuration, and data changes, including preflight checks, phased deployment, verification signals, rollback procedures, communication plan, contingency handling, and post-deployment tasks. Use when the user asks for a rollout plan, deployment plan, release plan, production change plan, or go/no-go checklist.

Rank impediments and countermeasures with a value-stream scoring model using ROI, Cost to Implement, Ease of Deployment, Risk Factor, and a fixed priority formula. Use when prioritizing, sequencing, triaging, or ranking remediation items, risks, findings, gaps, action items, GHQR findings, audit results, retrospective actions, or improvement backlogs.

Use when an outage, production incident, or significant service degradation has occurred and the team needs to write a structured blameless post-mortem. Triggers on phrases like "write a post-mortem", "incident review", "what went wrong", "outage report", "root cause analysis", or "RCA". Covers timeline reconstruction, contributing factor analysis, impact quantification, and action item generation with owners.

Design and implement Arduino integration with Azure IoT Hub and IoT Edge, including secure provisioning, MQTT telemetry, gateway topologies, offline buffering, command handling, OTA configuration, and production guardrails. Use when connecting Arduino sensors or actuators to Azure IoT or edge gateways.

Design and plan end-to-end Azure IoT and Smart City solutions with requirements, architecture, device and edge strategy, ingestion, analytics, security, operations, cost controls, and phased delivery artifacts. Use when asked to build an IoT solution on Azure, design Smart City traffic, lighting, waste, water, energy, or public safety platforms, or create an urban IoT roadmap.

Generates breadboard circuit mockups and visual electronics diagrams with HTML5 Canvas conventions for retro computers, 6502 builds, 555 timer circuits, EEPROM/RAM/VIA wiring, 7400-series logic, LEDs, resistors, capacitors, switches, and wires. Use this skill when asked to create circuit layouts, visualize component placement, draw breadboard diagrams, mock up vintage electronics, or design Ben Eater-style projects.

Build and operate Python Azure IoT Edge modules with reliable messaging, deployment manifests, observability, security, and production readiness checks. Use when creating Python IoT Edge modules, deploying edge manifests, processing telemetry at the edge, handling disconnected operation, or validating IoT Edge readiness.

Create a Spring Boot Java project skeleton from Spring Initializr with Maven, Java 21, common data dependencies, SpringDoc, ArchUnit, local Docker Compose services for Redis, PostgreSQL, and MongoDB, application.properties settings, .gitignore entries, and Maven validation. Use when asked to create or scaffold a Spring Boot Java project.