Affaan Mustafa

Handle customer billing issues with connected tools such as Stripe. Review subscriptions and invoices, classify the problem, address refunds or cancellations, and prepare a handoff with revenue impact, customer follow-up text, and product gaps.

• Investigating duplicate subscriptions or unexpected charges
• Handling failed renewals and payment method problems
• Restoring access to billing and cancellation controls

Coordinate parallel frontend, backend, or service development around one shared, machine-checkable interface specification. Generate consumer types, validate mocks and real responses against the same specification, and review changes together to prevent mismatched fields and incompatible integrations.

• Coordinating parallel frontend and backend development
• Aligning API or event formats across services
• Checking that mock and production responses match

Write Django and Django REST Framework tests with pytest-django, starting with tests before implementation. Covers test data generation, simulated external services, model and API checks, and coverage reports showing which code the tests exercise.

• Developing Django features by writing tests first
• Testing API authentication and input validation
• Generating reusable test data

Design task-specific workflows for repeated agent work, with pass/fail checks, progress records, and handoff notes. Identify when a temporary workflow should become a shared skill that teammates can run and evaluate again.

• Designing a workflow for repeated agent tasks
• Adding task-specific pass/fail checks
• Turning recurring work into a shared skill

Create images, videos, and audio with fal.ai through MCP, a connection to external tools. Find suitable models, estimate costs, edit source images, generate speech, and create sounds that match video content.

• Creating thumbnails or product images from text
• Changing an existing image's style
• Turning a still image into a video

Turn Claude Code session patterns into reusable behavior rules with confidence scores. Keep project-specific lessons separate, review and share learned rules, and combine related patterns into skills, commands, or agents.

• Capture lessons from corrections and repeated workflows
• Keep learned conventions separate for each project
• Turn related behavior rules into skills or commands

Summarize Claude Code token usage and estimated spending from the local ECC metrics log. Review costs by model, session, or date, compare spending with budgets, and export records to CSV while avoiding duplicate counting of session totals.

• Comparing today's spending with yesterday's
• Reviewing costs by model or session
• Checking spending against a budget

Define when an agent may respond in shared chats with customers or partners and what it may send. Separate authorized routine replies from approval-only drafts while keeping internal information out of external messages.

• Setting response rules for customer group chats
• Keeping internal details out of partner replies
• Routing prices and commitments to approval-only drafts

Turn an article, announcement, or existing post into distinct versions for X, LinkedIn, Threads, and Bluesky. Preserve the author's voice while adjusting length and context, with brief notes explaining the changes for each platform.

• Preparing a launch announcement for several social platforms
• Adapting an article into platform-specific posts
• Sharing release notes across social platforms

Investigate unexpected costs in the ECC Tools GitHub App by tracing events, queued jobs, analysis workers, and billing logic. Identifies repeated pull request creation, usage-limit bypasses, unintended premium-model calls, and duplicate retries, then verifies targeted fixes.

• Investigate excessive pull request creation
• Find races that bypass usage limits
• Check free-tier access to premium models

Support import and export compliance by classifying goods under tariff codes, reviewing customs documents, and assessing restricted-party matches. Covers trade agreement eligibility, duty-saving options, and customs inquiries across the US, EU, UK, and Asia-Pacific.

• Assess tariff classification from product specifications
• Review invoices and certificates of origin
• Evaluate eligibility for preferential trade agreements

Diagnose failed AI agent runs by capturing errors, checking likely causes, and choosing small, reversible recovery actions. The workflow produces a structured report of the failure, recovery steps, and evidence, helping explain repeated retries or stalled progress.

• Diagnosing repeated tool calls with no progress
• Investigating quality loss as context grows
• Checking file paths and environment mismatches

Turn scored competitor profiles into a report for strategic decisions. Organize market maps, comparison tables, unoccupied positions, threats, and prioritized recommendations so leaders can decide whom to compete with and how to differentiate.

• Preparing a competitive report for leadership or a board
• Combining completed competitor profiles
• Assessing room for differentiation and competitive threats

Design a persistent multi-agent workflow in Claude Code, with specialist roles, reusable commands, file-based memory, and scheduled tasks. Keep project context and decisions across sessions using JSON and Markdown files without an external database.

• Coordinate specialist agents for development and writing
• Preserve project context across sessions
• Schedule recurring morning briefings

Build shared interfaces for Android, iOS, Desktop, and Web with Compose. This skill guides screen state, navigation, reusable components, themes, and rendering performance, including ways to handle interface differences between platforms.

• Building shared screens across platforms
• Organizing screen state and user actions
• Implementing navigation and dialogs

Build a reusable writing style profile from real posts, articles, emails, and product copy. Use it to keep social posts, outreach, and launch announcements consistent in tone, sentence rhythm, and expression across related writing tasks.

• Keep a consistent voice across social channels
• Match outreach emails to an established writing style
• Reuse an author's tone in product announcements

Plan autonomous Claude Code workflows, from sequential development steps to parallel agents working from a specification. The material explains how to preserve progress between runs, check quality, coordinate merges, and set limits that stop repeated execution.

• Designing a sequential development pipeline
• Preserving progress across repeated agent runs
• Coordinating parallel work and merges

Set up recurring work in Claude Code by combining persistent memory, scheduled prompts, task queues, and optional computer control. The skill explains how to connect these components, including external scheduling for work that continues after a session closes.

• Reviewing pull requests at regular intervals
• Collecting and summarizing research findings daily
• Preparing meeting notes from saved context

Build or review server-side APIs in Node.js, Express, and Next.js. Apply patterns for organizing business logic and data access, reducing unnecessary database queries, caching results, validating requests, and handling authentication and errors.

• Designing APIs and separating business logic from data access
• Reducing repeated database queries
• Adding caching and background processing

Explore an unfamiliar codebase and turn its structure, request flow, and development conventions into a concise onboarding guide. Create or update CLAUDE.md with project-specific instructions, preserving existing guidance and identifying findings that remain uncertain.

• Understanding an unfamiliar project when joining a team
• Setting up Claude Code in an existing repository
• Creating CLAUDE.md from detected project conventions

Audit scheduled jobs, hooks, MCP servers, and external integrations using configuration files, logs, and recent runs. Distinguish configured tools from verified working ones, identify failures or overlap, and recommend what to keep, merge, remove, or fix next.

• Checking which automations are actually working
• Identifying broken jobs and authentication failures
• Finding duplicate hooks, scripts, and integrations

Design caching for repeated PDF parsing, text extraction, or image analysis using SHA-256 hashes, identifiers calculated from file contents. Reuse results after files move or change names, and process them again when their contents change.

• Caching repeated PDF text extraction
• Reusing results after files move or change names
• Adding caching around existing processing functions

Record software design decisions as numbered Markdown files, with context, rejected alternatives, benefits, drawbacks, and risks. Maintain an index and consult existing ADRs—architecture decision records—to explain why a framework, database, or design approach was chosen.

• Record reasons for framework or database choices
• Document design alternatives and trade-offs
• Find explanations for past technical decisions

Organize engineering work carried out by AI agents with clear completion criteria, small verifiable tasks, and evaluations before and after implementation. Match model choice to task complexity and track tokens, retries, time, and outcomes to manage cost.

• Planning development work for AI agents
• Splitting a large change into independently verifiable tasks
• Comparing evaluations before and after implementation