fellowship-of-the-workflows

Identify and remove AI slop from code comments, documentation, and prose. Use when cleaning up AI-generated output, reviewing for AI tells, or improving signal-to-noise ratio in any text.

Design review for front-end code changes using Playwright for live browser testing. Covers visual hierarchy, accessibility (WCAG AA+), responsive design, and interaction patterns. Use when reviewing UI/UX changes before merge.

Adversarial code review that assumes the worst. Finds failure modes, race conditions, blast radius, and edge cases that optimistic reviewers miss. Use when you want brutal honesty about code resilience.

Perform thorough code review on a PR using the Pragmatic Quality framework. Integrates with Jira to validate implementation matches ticket requirements. Use when reviewing pull requests or providing PR feedback.

Validate implementation plans for completeness, specificity, and actionability. Catches vague language, missing sections, and untestable outcomes.

Interactive PRD creation and iteration for non-technical users. Use this skill whenever the user wants to define product requirements, write a PRD, spec out a feature, describe what to build, or says "what should we build", "write requirements", "create a PRD", "define the product". Also use when updating an existing PRD based on stakeholder or engineering feedback. Guides through structured requirement definition using plain-language facilitation prompts with discovery questions upfront. Auto-validates with /prd-validator after completion.

Translates an approved PRD into a unified ROADMAP.md with phased feature descriptions and implementation checklists. Use this skill whenever an engineer receives a PRD and needs to break it into phases, when the user asks "how do I turn this PRD into a plan", "create a roadmap from requirements", or "decompose this into milestones". Gates on PRD validation — refuses to proceed if the PRD hasn't passed /prd-validator.

Validates PRD.md files for structural completeness, specificity, and actionability before handoff to engineering. Use this skill whenever a PRD exists and needs quality review, before handing requirements to engineers, when the user asks "is this PRD ready" or "validate my requirements", or automatically after /prd-author completes. Checks for required sections, acceptance criteria, scope boundaries, vague language, and requirement ID consistency. Supports --draft mode for work-in-progress PRDs.

Systematic code refactoring with smell detection, safe transformation patterns, and test-verified execution. Triggered by: refactor this, clean up this code, code smells, extract method, dead code, reduce complexity, this code is messy, too much coupling, simplify this. Analyzes code structure, produces a prioritized refactoring plan, and executes changes with test verification at every step.

Perform security-focused code review to identify HIGH-CONFIDENCE vulnerabilities with real exploitation potential. Based on Anthropic's claude-code-security-review. Minimizes false positives with >80% confidence threshold. Use when reviewing PRs for security issues.

Creates handoff documents for AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue without ramp-up time.

Generate and maintain a session index with cross-session dependencies. Scans .ai/sessions/ directories and produces INDEX.md.

Structured root-cause analysis for bugs, test failures, and unexpected behavior. Four-phase methodology: investigate, analyze patterns, hypothesize, implement fix. Use when encountering any technical issue before proposing fixes. Prevents brute-force retry loops.

Enforce RED-GREEN-REFACTOR cycle for any implementation task. Write failing test first, implement minimally, refactor. Triggered by: write tests first, do TDD, red-green-refactor, test-first approach, I want to follow TDD, test-driven. Use when implementing features, fixing bugs, or refactoring code.

Coordinate multiple subagents to complete a large task. Decomposes work, delegates to specialists, aggregates results, handles failures. Use for tasks spanning multiple domains or requiring parallel workstreams.

Scan for new AI coding tool features and assess impact on your project. Covers Claude Code, Cursor, Copilot, Windsurf, Codex, Roo, and Goose. Use to track AI tooling changes and identify workflow improvements.

Generate, optimize, and manage CI/CD pipelines for GitHub Actions and GitLab CI. Creates working pipeline configs tailored to your project's tech stack with built-in caching, secret handling, matrix testing, and deployment strategies. Triggered by: CI/CD, pipeline, GitHub Actions, GitLab CI, deploy, deployment, workflow, build cache, matrix test, pipeline optimization, environment management, secret handling.

Identifies the right software design pattern for a given coding task. Use this skill whenever the user is designing a class, module, system, or architecture and would benefit from a known pattern — or when they're about to misapply one. Triggers include: asking "what pattern should I use", "how should I structure this", "is there a better way to organize this code", refactoring discussions, architecture planning, code review where structural improvements are relevant, or any task involving object creation strategies, decoupling components, managing state, handling errors across boundaries, or coordinating complex workflows. Also trigger when the user is ALREADY using a pattern and you detect they may be misapplying it or overengineering — the skill covers anti-patterns and "when NOT to use" guidance with equal weight. This skill is language-agnostic but accounts for language idioms that replace patterns natively.

Interactive git workflow assistant. Generates conventional commits, PR descriptions, enforces branch naming, guides merge conflict resolution, manages worktrees, and handles branch completion. Triggered by: commit, PR, branch, merge conflict, worktree, finish branch, conventional commit, squash, rebase.

Sync documentation with code changes. Detects stale docs, generates/updates READMEs, changelogs, and API docs after implementation. Use after completing a feature, fixing a bug, or before a release.

Run skill evaluations, generate golden test files, and promote learnings. Wraps the fotw eval CLI with interactive guidance.

Analyze code for performance bottlenecks including N+1 queries, algorithmic complexity, memory leaks, caching gaps, bundle size issues, and database query optimization. Triggered by: slow query, performance issue, N+1, memory leak, optimize this, bundle size, cache miss, profiling, this is slow, latency. Produces a prioritized performance report. Use when reviewing PRs for performance impact or auditing existing code.

WCAG 2.1/2.2 accessibility audit covering all POUR principles, keyboard navigation, screen reader strategy, color contrast, ARIA patterns, and semantic HTML. Triggered by: a11y audit, accessibility check, screen reader test, keyboard navigation, WCAG compliance, color contrast check, accessible, aria labels. Use when reviewing UI changes for accessibility compliance or conducting pre-release accessibility checks.

Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.

Design REST and GraphQL APIs. Covers endpoint naming, versioning, OpenAPI 3.1 specs, pagination, error handling, and auth patterns. Triggered by: design an API, REST endpoints, GraphQL schema, OpenAPI spec, API versioning, pagination strategy, error response format, create endpoints for, review API. Use even when the user just describes endpoints they need without explicitly asking for 'API design'.

Structured design thinking for technical decisions. Captures constraints, surfaces assumptions, generates alternatives, analyzes trade-offs, and records decisions. Triggered by: brainstorm, design, explore options, what approach, how should we, which way.

Design SQL and NoSQL database schemas. Covers normalization, indexing, migration patterns, constraints, and performance tuning. Triggered by: design a schema, create tables, database design, data model, normalize this, add indexes, migration strategy, ERD, entity relationship. Use when the user describes entities and relationships even casually, or asks about database structure for any project.

Scaffold E2E and integration tests using Playwright. Covers Page Object Model setup, test data management, configuration generation, coverage tracking, and CI/CD integration. Triggered by: set up Playwright, write E2E tests, integration test, end-to-end test, test this user flow, scaffold test suite, browser testing. Use when creating new test suites, adding E2E coverage to features, or setting up Playwright from scratch.

Cross-platform incident management router. Detects the alerting/on-call platform in use (Grafana IRM, incident.io, Better Stack, Datadog, PagerDuty) and routes to the appropriate specialist skill. Handles platform-agnostic tasks — alert design, on-call setup, runbook authoring, and blameless postmortems — without requiring platform knowledge.

Review work accomplished over a time period by correlating Jira tickets with git commits. Triggered by: what did I do this sprint, prepare for standup, self-review, peer review, sprint retro, summarize my work, performance review prep, what have I been working on, status update. Use for self-reviews, peer reviews, sprint retrospectives, or performance discussions.

Use when writing prose humans will read — documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing. Triggered by: clean up this text, rewrite this, make this clearer, fix this README, improve this error message, edit for clarity, tighten this up, too wordy, writing quality.

Create an Agent Team from a predefined roster. Spawns multiple Claude Code sessions that coordinate via shared tasks and direct messaging.

Go patterns and idioms. Use when writing, reviewing, or refactoring Go code. Covers error handling, concurrency, testing, and project structure.

Python patterns and idioms. Use when writing, reviewing, or refactoring Python code. Covers error handling, async, type system, testing, and project structure.

Rust patterns and idioms. Use when writing, reviewing, or refactoring Rust code. Covers error handling, type system, concurrency, testing, and project structure.

TypeScript patterns and idioms. Use when writing, reviewing, or refactoring TypeScript code. Covers type system, error handling, async, testing, and project structure.

Author, review, deploy, and migrate AWS infrastructure using CloudFormation, CDK, or SAM. Auto-detects which tool the project uses. Modes: generate, review, diff, security, migrate. Use for any AWS infrastructure-as-code task.

AWS security patterns: IAM policy design, least-privilege principles, Secrets Manager vs Parameter Store, KMS envelope encryption, IRSA/OIDC for Kubernetes, and compliance checklists. Triggered by: IAM, least privilege, Secrets Manager, Parameter Store, KMS, IRSA, OIDC, permission boundary, SCP, CloudTrail, compliance, secret rotation.

AWS serverless architecture patterns: Lambda functions, Step Functions orchestration, EventBridge event-driven design, SQS/SNS messaging, and SAM/CDK templates. Triggered by: Lambda, serverless, Step Functions, EventBridge, SQS, SNS, SAM, cold start, event-driven, async invoke, DLQ, fan-out.

AWS credential setup, SDK patterns (Go/Python/TypeScript/Rust), IaC decision tree, CLI workflows, S3, VPC basics, and MCP server configuration. Triggered by: AWS, cloud, boto3, aws-sdk, CDK, CloudFormation, SAM, Terraform for AWS, S3, VPC, ECS, RDS, DynamoDB, IAM role, SSO, aws configure.