Frontend

End-to-end guide for creating React components in AgenticFleet's frontend, from design tokens through Tailwind styling, shadcn/ui integration, state management, to testing.

Guides systematic code refactoring following the DRY (Don't Repeat Yourself) principle. Use when user asks to eliminate code duplication, refactor repetitive code, apply DRY principle, or mentions code smells like copy-paste, magic numbers, or repeated logic. Implements a 4-step workflow from identifying repetition to verified refactoring.

Creates unique, production-grade frontend interfaces with exceptional design quality. Use when user asks to build web components, pages, materials, posters, or applications (e.g., websites, landing pages, dashboards, React components, HTML/CSS layouts, or styling/beautifying any web UI). Generates creative, polished code and UI designs that avoid mediocre AI aesthetics.

This skill should be used when the user asks to "analyze my product", "research competitors", "find feature gaps", "create feature request", "prioritize backlog", "generate PRD", "plan roadmap", "what should we build next", "competitive analysis", "gap analysis", "sync issues", or mentions product management workflows. Provides AI-native PM capabilities for startups with signal-based feature tracking, the WINNING prioritization filter, and GitHub Issues integration with deduplication.

Systematic approach for creating minimal-change, reversible implementation plans. Claude invokes this skill when transforming requirements/research into executable blueprints. Emphasizes simplicity, safety, and clear verification steps.

Systematic validation methodology for ResearchPacks and Implementation Plans. Provides scoring rubrics and quality gates to ensure outputs meet standards before proceeding to next phase. Prevents garbage-in-garbage-out scenarios.

Complete guide for writing Claude Code and SDK hooks with security-first design. Triggers: hook creation, hook writing, PreToolUse, PostToolUse, UserPromptSubmit, tool validation, logging hooks, context injection, workflow automation Use when: creating new hooks for tool validation, logging operations for audit, injecting context before prompts, enforcing project-specific workflows, preventing dangerous operations in production DO NOT use when: logic belongs in core skill - use Skills instead. DO NOT use when: complex multi-step workflows needed - use Agents instead. DO NOT use when: behavior better suited for custom tool. Use this skill BEFORE writing any hook. Check even if unsure.

Record browser sessions using Playwright for web UI tutorials. Captures video of browser interactions that can be converted to GIF. Triggers: browser recording, playwright, web demo, ui recording Use when: creating browser-based tutorials showing web UI interactions

Employ the Hexagonal (Ports & Adapters) pattern to decouple domain logic from infrastructure, maximizing flexibility and testability. Triggers: hexagonal architecture, ports and adapters, infrastructure independence, dependency inversion, clean architecture, domain isolation, adapter pattern, infrastructure abstraction, database independence, framework independence Use when: designing systems with strong business logic separation, anticipating infrastructure changes, needing easy mocking for tests, building portable domain code DO NOT use when: selecting from multiple paradigms - use architecture-paradigms first. DO NOT use when: building simple CRUD apps without complex domain logic. Consult this skill when implementing hexagonal patterns or migrating to port-based design.

Design skills as modular building blocks for predictable token usage. Triggers: skill design, skill architecture, modularization, token optimization, skill structure, refactoring skills, new skill creation, skill complexity Use when: creating new skills that will be >150 lines, breaking down complex monolithic skills, planning skill architecture, refactoring overlapping skills, reviewing skill maintainability, designing skill module structure DO NOT use when: evaluating existing skill quality - use skills-eval instead. DO NOT use when: writing prose for humans - use writing-clearly-and-concisely. DO NOT use when: need improvement recommendations - use skills-eval. Use this skill BEFORE creating any new skill. Check even if unsure.

Declarative release readiness checklist that mirrors GitHub checks, deployment issues, and documentation requirements. Triggers: release gates, release readiness, deployment checklist, release review, quality signals, rollout scorecard, QA handshake, deployment gates Use when: preparing releases, validating deployment gates, conducting release reviews, embedding release gate snippets in PRs DO NOT use when: weekly status updates - use github-initiative-pulse. DO NOT use when: code reviews - use pensive review skills. Standardizes release approvals with GitHub-aware checklists.

Methodology for summarizing changes, extracting insights, and identifying follow-up actions. Triggers: catchup, what changed, summarize changes, context acquisition, handoff, progress review, recent changes, git log analysis, sprint summary Use when: resuming work after absence, preparing handoff documentation, reviewing sprint progress, analyzing git history for context DO NOT use when: doing detailed diff analysis - use diff-analysis instead. DO NOT use when: full code review needed - use review-core instead. Use this skill to quickly understand "what changed and what matters".

Workflow for capturing evidence and citations to create reproducible analyses and audit trails. Triggers: evidence capture, citations, reproducible analysis, audit trail, documentation, evidence logging, findings documentation Use when: conducting any review that needs evidence trails, creating audit documentation, ensuring reproducibility of analyses DO NOT use when: quick informal checks without documentation needs. DO NOT use when: structured output is the focus - use structured-output. Use this skill as foundation for all evidence-based review workflows.

Guide to effective Claude Code skill authoring using TDD methodology and persuasion principles. Triggers: skill authoring, skill writing, new skill, TDD skills, skill creation, skill best practices, skill validation, skill deployment, skill compliance Use when: creating new skills from scratch, improving existing skills with low compliance rates, learning skill authoring best practices, validating skill quality before deployment, understanding what makes skills effective DO NOT use when: evaluating existing skills - use skills-eval instead. DO NOT use when: analyzing skill architecture - use modular-skills instead. DO NOT use when: writing general documentation for humans. YOU MUST write a failing test before writing any skill. This is the Iron Law.

Use a Layered (N-Tier) architecture to separate presentation, domain logic, and data access responsibilities within a system. Triggers: layered architecture, n-tier, separation of concerns, presentation layer, data access layer, service layer, traditional architecture, monolith structure, layer enforcement, dependency direction Use when: building traditional applications with clear boundaries, working with moderate-sized teams, needing familiar and well-understood patterns, compliance requirements demand clear separation DO NOT use when: selecting from multiple paradigms - use architecture-paradigms first. DO NOT use when: high scalability needs independent component scaling. DO NOT use when: teams need independent deployment cycles - use microservices. Consult this skill when implementing layered patterns or enforcing layer boundaries.

Enforces "prove before claim" discipline - validation, testing, and evidence requirements before declaring work complete. Triggers: completion, finished, done, working, should work, configured, ready to use, implemented, fixed Use when: claiming ANY work is complete, recommending solutions, stating something will work, finishing implementations DO NOT use when: explicitly asking questions or requesting clarification DO NOT use when: work is clearly in-progress and not claiming completion CRITICAL: This skill is MANDATORY before any completion claim. Violations result in wasted time and eroded trust.

Systematically uncover and fix bugs using language-specific expertise and reproducible evidence. Triggers: bug hunting, defect detection, debugging, fix verification, bug fix, regression check, error investigation, defect documentation Use when: deep bug hunting needed, documenting defects, verifying fixes, systematic debugging required DO NOT use when: test coverage audit - use test-review instead. DO NOT use when: architecture issues - use architecture-review. Use this skill for systematic bug hunting with evidence trails.

Detect codebase bloat through progressive analysis: dead code, duplication, complexity, and documentation bloat. Triggers: bloat detection, dead code, code cleanup, duplication, redundancy, codebase health, technical debt, unused code Use when: preparing for refactoring, context usage is high, quarterly maintenance, pre-release cleanup DO NOT use when: actively developing new features, time-sensitive bug fixes. DO NOT use when: codebase is < 1000 lines (insufficient scale for bloat). Progressive 3-tier detection: quick scan → targeted analysis → deep audit.

Evaluate and upgrade test suites with TDD/BDD rigor, coverage tracking, and quality assessment. Triggers: test audit, test coverage, test quality, TDD, BDD, test gaps, test improvement, coverage analysis, test remediation Use when: auditing test suites, analyzing coverage gaps, improving test quality, evaluating TDD/BDD compliance DO NOT use when: writing new tests - use parseltongue:python-testing. DO NOT use when: updating existing tests - use sanctum:test-updates. Use this skill for test suite evaluation and quality assessment.

Scope-focused PR code review that validates against original requirements and routes out-of-scope findings to GitHub issues. Triggers: PR review, pull request review, scope validation, requirement compliance, backlog triage, code review, blocking issues Use when: reviewing PRs, validating against requirements, triaging findings to backlog, preventing overengineering DO NOT use when: preparing PRs - use pr-prep instead. DO NOT use when: deep code review - use pensive:unified-review. Use this skill for scope-focused PR reviews.