Affaan Skills Repo

Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.

A comprehensive verification system for Claude Code sessions.

Audits and improves search visibility through technical SEO, on-page optimization, structured data, Core Web Vitals, and content strategy.

Use for latency-sensitive systems such as realtime dashboards, market data, streaming agents, execution gateways, queues, caches, or HFT-like infrastructure where freshness and p95 latency matter.

Provides a creative-direction layer for music videos and short-form edits, defining an angelcore/cloud-trance/hyperpop aesthetic with mood, color, light, and beat-synced editing grammar, and orchestrating video production skills into a pipeline.

Integrates with the X (Twitter) API to post tweets and threads, read timelines, search content, and track analytics using OAuth authentication and rate-limit handling.

Convenes four independent advisor voices to surface structured disagreement on ambiguous decisions, tradeoffs, and go/no-go calls before choosing a path.

Records polished UI demo videos of web applications using Playwright, with an injected cursor overlay, natural pacing, and a discover-rehearse-record workflow.

Manage Uncloud clusters with the `uc` CLI: bootstrap machines, deploy Compose services, publish ports, configure Caddy ingress, scale, inspect logs, and manage volumes.

Ingests video and audio from files, URLs, live feeds, or desktop capture; indexes and searches moments with timestamps; transcodes, edits timelines, generates media assets, and emits real-time alerts.

Measures performance baselines, detects regressions before and after PRs, and compares stack alternatives.

Turns a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects, with self-contained context briefs, adversarial review, and dependency graphs.

Creates CodeTour `.tour` files with real file and line anchors for guided codebase walkthroughs, including onboarding, architecture, PR, and RCA tours.

Periodically scans Claude Code configuration for redundant, stale, or orphaned items and walks the user through a confirm-each-deletion cleanup.

Adapts a single piece of content into platform-specific versions for X, LinkedIn, Threads, and Bluesky, preserving the author's voice and avoiding duplicate copy.

Guides users through ECC's components and installation by inspecting the live repository before answering.

Organizes email triage, drafting, replying, and sending with verification that messages landed in the Sent folder.

Blocks Edit/Write/Bash actions until the agent presents concrete facts about imports, data schemas, and the user's instruction, improving output quality.

Implements accessible, performant UI motion for React and Next.js apps, covering tokens, patterns, and modal behavior.

Audits source code across C++, Android, iOS, and Web to classify files, detect embedded third-party libraries, and produce four-level verdicts with interactive HTML reports.

Batch-converts UI design screenshots into Vue 3 Composition API components, with support for Vant, Element Plus, and Ant Design Vue.

Compares coding agents head-to-head on reproducible tasks, measuring pass rate, cost, time, and consistency.

Builds an evidence-backed ECC install plan for a repository by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes.

Builds persistent multi-agent workflows on Claude Code using a kernel config, specialist agents, slash commands, file-based memory, and scheduled automation without external databases.

Design consistent, developer-friendly REST APIs with resource naming, HTTP methods, status codes, pagination, filtering, sorting, authentication, and rate limiting.

Automates visual testing and UI interaction verification using browser automation after deploying features.

Guides test-driven development for Django applications using pytest, factory_boy, and Django REST Framework, covering models, views, serializers, and API testing.

Performs neural web, code, company, and people searches through the Exa MCP server, with guidance on tool usage and parameters.

Manage GitHub repositories via the gh CLI: triage issues, review PRs, debug CI failures, create releases, and monitor security alerts.

Teaches how to write growth logs that extract reusable patterns from complex tasks, failures, and reviews, with templates and quality checks.

Builds a reusable writing style profile from real source material and applies it across content, outreach, and social workflows for consistent brand voice.

Adopt Bun as a JavaScript runtime, package manager, bundler, and test runner, including migration from Node and Vercel deployment.

Provides a workflow for writing, updating, and fixing C++ tests with GoogleTest/GoogleMock, configuring CMake/CTest, diagnosing failures, and adding coverage or sanitizers.

Provides Playwright patterns for building stable E2E test suites, including Page Object Model, configuration, flaky test strategies, artifact management, and CI/CD integration.

Maps a described workflow to the right ECC command-group with run-order and stop condition, and browses all command-group recipe families.

Queries live GPU inventory, submits authenticated fixed-rate RFQs, and checks status via the canonical Itô compute CLI or MCP server, with gated node qualification.

Write and run test-driven Laravel applications using PHPUnit, Pest, factories, HTTP tests, and Sanctum authentication.

Creates technical explainer animations with Manim, covering graphs, workflows, and system diagrams, and produces storyboards, scene plans, and rendered MP4s.

Opens plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or when feedback like "move this, change that" is easier pointed at than typed.

Guides test-driven development for Quarkus 3.x services with JUnit 5, Mockito, REST Assured, Camel testing, and JaCoCo, targeting 80%+ coverage for event-driven architectures.

Searches local, marketplace, GitHub, and web sources for existing skills before creating a new one, then ranks and vets candidates to avoid duplication.

Monitors a deployed URL after releases to catch regressions in HTTP status, console errors, network failures, performance metrics, content, API health, static assets, and SSE streams.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.

Generates images, videos, and audio using fal.ai models via MCP, covering text-to-image, text/image-to-video, text-to-speech, and video-to-audio.

Guides Git version control practices: branching strategies, commit conventions, merge vs rebase, conflict resolution, and pull request workflows for collaborative teams.

Generate iOS app icons as PNG imagesets for Xcode asset catalogs from SF Symbols or the Iconify API, with options for color, size, and output location.

Provides JPA/Hibernate patterns for Spring Boot data modeling, including entity design, relationships, query optimization, transactions, auditing, indexing, pagination, and connection pooling.

Retrieves live messages from local messaging surfaces, including iMessage and DMs, recovers recent one-time codes, and inspects threads before replying, with evidence of the source checked.

Turns model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

Write and run Perl tests using Test2::V0, Test::More, prove, mocking, and Devel::Cover coverage with a TDD workflow.

Validates product direction before building, runs product diagnostics, founder reviews, user journey audits, and feature prioritization, producing actionable briefs and recommendations.

Runs evidence-first research workflows, choosing the lightest useful path from search to deep synthesis, and labels facts, inference, and recommendations.

Guides writing Rust tests with TDD, covering unit, integration, async, property-based, mocking, and coverage patterns.

Prevents destructive operations on production systems and restricts edits to a specified directory when running agents autonomously.

Runs a multi-agent adversarial verification loop where two independent reviewers must both pass before output ships, with a fix cycle for convergence.

Guides the agent to research existing tools, libraries, and patterns before writing custom code, using parallel searches across package registries, MCP servers, skills, and GitHub, then evaluating and deciding to adopt, extend, or build.

Measures whether coding agents actually follow skills, rules, or agent definitions by generating test scenarios, running agents, and classifying tool calls to report compliance rates.

Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests when writing features, fixing bugs, or refactoring code.

Composes ad-hoc teams of AI agents from local markdown personas and dispatches them in parallel on a task, then synthesizes their outputs.

Executes terminal commands, inspects git state, debugs CI or builds, and makes narrow fixes with exact proof of what was executed and verified.