Claude Skills by kmshihab7878

**Type:** Privacy incident · forward-state remediation **Status:** Forward state clean. GitHub-cache GC pending. **Owner:** Repository owner

Closed-loop ad performance optimization. Analyzes campaign results, identifies winning creatives by CPA/ROAS, reinforces winning patterns, and triggers regeneration of next creative batch. Use when analyzing ad performance, optimizing campaigns, identifying winning creatives, or running the generate-evaluate-regenerate cycle. Mirrors Eddie's Stage 5 (Self-Improvement Loop).

Autonomous competitor ad intelligence. Scrapes competitor ads from Meta Ad Library and other platforms, transcribes video ads, extracts hooks/angles/structure, and produces a full competitive intel dump. Use when researching competitor ads, analyzing ad creative strategies, building competitive ad intelligence, or preparing for ad script generation. Mirrors Eddie's Stage 1 (Competitor Intelligence).

Generate 100+ ad script variations from competitor intelligence. Takes ad-research output, rewrites competitor angles in brand voice, multiplies across ICPs, and produces production-ready scripts for UGC creators and AI video (Arcads). Use when creating ad scripts, generating creative variations, writing ad copy at scale, or building a creative testing pipeline. Mirrors Eddie's Stage 3 (Script Generation).

Open-source, pluggable agentic coding orchestrator. Manages durable coding agents (Claude Code, Codex, OpenCode) through a simple interface — spawn agents, track progress, and let feedback loops like PR reviews and CI failures automatically route to the right agents. Use for fixing bugs, building features, working on GitHub issues, checking status, and managing agent sessions.

AI design engine via MCP. Generates production-ready inline-Tailwind HTML from natural language prompts with full repo context awareness (framework, tokens, components, routes). Use for UI generation, iteration, and design-system-consistent page creation.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Automated metric anomaly detection and root cause correlation for the Operations department. Monitors system metrics for deviations, correlates anomalies across services, generates alert recommendations, and feeds the ops self-improvement loop. Use when investigating metric spikes, tuning alert thresholds, reducing false positives, or running the operations UAOP pipeline.

Universal anti-AI slop filter applied to ALL written output. Bans AI-overused words, enforces human tone, prevents generic marketing-blog copy. Use when generating any text content — docs, scripts, emails, PRDs, reports, commit messages, or any prose. Always active as a quality gate on written output.

REST and GraphQL API design patterns. Resource naming, HTTP methods, status codes, error formats, pagination, versioning, and rate limiting. Use when designing APIs, reviewing endpoints, or writing OpenAPI specs.

API testing with Bruno, Schemathesis, Hypothesis property-based testing, and OpenAPI validation for REST APIs

Automated technology trend scanning and architecture pattern extraction for the Engineering department. Monitors open-source trends, framework releases, and architecture patterns. Evaluates applicability to orchestrator stack, produces adoption recommendations, and feeds the engineering self-improvement loop. Use when evaluating new technologies, scanning for architecture patterns, planning tech radar updates, or running the engineering UAOP pipeline.

Connects Aster DEX market data to TimesFM forecasting. Pulls klines via Aster MCP, feeds price/volume series to TimesFM for zero-shot crypto price forecasting with quantile intervals. Use for trading signal generation and risk assessment.

Aster DEX trading skill for futures, spot, and market data via MCP tools

Score the AI OS out of 100 across the Four Cs (Context, Connections, Capabilities, Cadence). Read-only by default. Surfaces top 3 leverage gaps and recommends one next improvement. Saves audit to docs/audits/YYYY-MM-DD.md and logs a one-line entry in decisions/log.md.

Autonomous self-improvement loop — iteratively modify a target, evaluate against a scoring function, keep improvements, revert failures. Adapted from Karpathy's autoresearch pattern. Use for strategy optimization, code quality improvement, prompt engineering, config tuning, or any domain with an objective evaluation function.

Elite B2C iOS subscription app strategist. Runs full idea validation, MVP planning, App Store launch, and 5-channel marketing using the Ernesto Lopez playbook (12 apps, $73k MRR). Invoke when user says brainstorm storm, validate this idea, build strategy, analyze app, or wants to build a B2C app.

Validates animation durations, enforces typography scale, checks component accessibility, and prevents layout anti-patterns in Tailwind CSS projects. Mobile-first responsive design with breakpoints, fluid typography, container queries, and cross-device patterns. Use when building UI components, reviewing CSS utilities, styling React views, or enforcing design consistency.

Story implementation and code development specialist

Sprint planning and agile workflow specialist

User experience and interface design specialist

Guidance for verifying, presenting finish options, and closing feature branches safely.

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.

Hexagonal/Clean Architecture patterns for Python with ports-and-adapters, DDD, repository pattern, and dependency injection

Reverse-engineer and clone any website pixel-perfectly — extracts assets, CSS, and content section-by-section and dispatches parallel builder agents in worktrees. Triggers on "clone", "replicate", "rebuild", "reverse-engineer", "copy site", "pixel-perfect clone". Provide the target URL as an argument.

Pre-implementation checklist, incremental development workflow, and code organization patterns. Use before starting implementation to ensure readiness and maintain quality throughout.

When the user wants to write, improve, or build a sequence of B2B cold outreach emails to prospects who haven't asked to hear from them. Use when the user mentions 'cold email,' 'cold outreach,' 'prospecting emails,' 'SDR emails,' 'sales emails,' 'first touch email,' 'follow-up sequence,' or 'email prospecting.' Also use when they share an email draft that sounds too sales-y and needs to be humanized. Distinct from email-sequence (lifecycle/nurture to opted-in subscribers) — this is unsolicit...

Docker image hardening, rootless containers, K8s security contexts, network policies, pod security standards, and OPA/Gatekeeper policies

Measure and optimize token overhead across agents, skills, MCP servers, and CLAUDE.md. Identifies bloated components and produces prioritized savings recommendations.

10-stage governed orchestration pipeline mirroring the CoreMind orchestrator — intent parsing, policy gates, DAG planning, delegation, reflection, and outcome tracking for all non-trivial tasks

Autonomous Security Ecosystem — 14 AI-powered agents, 48 tools, 9 attack chains for macOS native pentesting

Cloud cost optimization with Infracost for Terraform, ccusage for Claude Code tokens, and AWS Cost Explorer patterns

High-stakes decision-making system with 5 advisors, anonymous peer review, and chairman synthesis. Activates on "council this", "war room this", or "pressure-test this". Outputs HTML report + markdown transcript. Saves to disk and optionally to Obsidian. Uses full ecosystem: MCP data gathering, semantic memory, sequential thinking, domain-aware advisors.

Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Use when assessing technical debt, scaling engineering teams, evaluating technologies, making architecture decisions, establishing engineering metrics, or when user mentions CTO, tech debt, technical debt, team scaling, architecture decisions, technology evaluation, engineering metrics, DORA metrics, or technology strategy.

Morning planning loop. Reads context/Priorities.md, kb/wiki/_hot.md, and last 7 days of decisions/log.md. Proposes ONE top focus for the day and identifies one AI-assisted task. Read-only — does not modify anything except (optionally) decisions/log.md with a single-line entry.

AI-powered data analysis patterns. Natural language to SQL/pandas, visual data exploration, ETL pipeline design, database modeling, and automated insights generation. Use when analyzing datasets, building dashboards, designing databases, or processing CSV/Excel data.

Database design and operations patterns. Schema design, migration best practices, indexing strategy, query optimization, and PostgreSQL patterns. Use when designing schemas, writing migrations, or optimizing queries.

Extract design tokens, component inventory, and interaction patterns from any live website using Playwright MCP. Outputs structured design system docs without cloning. Triggers on "inspect design", "extract design tokens", "analyze design", "design audit", "what design system does this site use". Provide the target URL as an argument.

DevOps and cloud infrastructure patterns for Terraform, Kubernetes, Docker, and CI/CD. Use when writing infrastructure code, configuring deployments, or setting up pipelines.

Anti-AI-slop frontend aesthetics enforcement from Anthropic's cookbook. Typography, color, motion, backgrounds, and spatial composition guidelines that produce distinctive, non-generic UI. Use when building any web UI, landing page, dashboard, or component.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Automated documentation coverage analysis and gap detection for the Documentation department. Scans codebase for undocumented APIs, stale docs, missing examples, and knowledge graph gaps. Produces prioritized documentation targets. Use when auditing doc coverage, finding undocumented code, planning doc sprints, or running the documentation UAOP pipeline.

Generate professional Word documents with structured content, tables, headers, styles, and formatting. Uses python-docx. Use when creating reports, proposals, contracts, specs, or any structured document as DOCX/Word format.

Elite Ship Mode operations system. Activates owner-engineer execution posture for production-grade implementation. Triggers on implementation tasks, feature builds, complex changes, or when explicitly invoked. Provides repo assimilation, decision framework, implementation standard, validation protocol, and ship criteria.

Evening reflection loop. Records what changed today, what skills worked, what failed, what context was missing. Proposes updates to skills/references/wiki/connections. Logs a one-line entry in decisions/log.md. Does not build anything.

Append one JSONL record to ~/.claude/evolution/records/ when a correction, a non-obvious win, or a repeated rework pattern occurs. Use sparingly — only when the event is load-bearing for future behavior. Do not log routine tool calls; the PreToolUse usage-logger already does that.

Guidance for executing approved plans sequentially with branch checks, progress tracking, and verification.

Run adversarial browser tests against code changes. Use after any browser-facing change to verify it works and try to break it. Prefer this over raw browser tools (Playwright MCP, chrome tools).

ML-driven financial analysis patterns. Price prediction models, portfolio optimization, risk metrics, technical indicators, backtesting methodology, and financial data processing. Use when building trading strategies, analyzing financial data, or integrating with Aster DEX.

Advanced financial modeling with DCF, Monte Carlo, portfolio optimization, risk metrics, and Aster DEX integration for backtesting