Skills Directory
Claude Skills by ShaheerKhawaja
github.com/ShaheerKhawajaProductionOS instinct-based learning system. Observes sessions via hooks, extracts patterns, creates atomic instincts with confidence scoring, and auto-promotes high-confidence patterns across projects.
ProductionOS frontend quality scanner. Auto-activates when editing React/Vue/Svelte components, CSS, or layout files. Checks accessibility, responsive design, performance, and design system consistency.
ProductionOS — dual-target AI engineering operating system for repo-wide audits, upgrade plans, code reviews, strategic product reviews, security sweeps, UX audits, and recursive quality improvement.
ProductionOS security scanner. Auto-activates when editing auth, payment, credential, or admin files. Runs OWASP Top 10 checks, dependency audit, and secret detection.
Niche-agnostic agentic evaluator using CLEAR v2.0 framework — 6-domain assessment, 8 analysis dimensions, 6-tier source prioritization, evidence strength ratings, and decision trees. Evaluates any plan, codebase, or research output.
Idea-to-running-code lifecycle orchestration. 10-phase pipeline with 5 hard decision gates, wave-based parallelism, and STATE.json resumability. Composes /deep-research, /auto-swarm-nth, /production-upgrade, /security-audit, and /ship into a single end-to-end flow.
Self-improving agent optimization — generates challenger variants of any agent/command, benchmarks against baseline, promotes winners, logs learnings to instincts. Inspired by Karpathy's autoresearch pattern.
Nth-iteration agent swarm — spawns parallel agent waves, evaluates strictly per wave, re-swarms gaps until 100% coverage and 10/10 quality. Can invoke any ProductionOS skill or command within waves.
Distributed agent swarm orchestrator — spawns parallel subagent clusters for any task with configurable depth, swarm size, and convergence criteria
Autonomous recursive improvement loop for a single target. Runs gap analysis, recursive refinement, evaluation, and convergence checks until the target reaches quality threshold or converges.
Idea exploration before building — understand the problem, propose approaches, present design, get approval. HARD-GATE: no implementation until design is approved.
Headless browser for QA testing, site inspection, and interaction verification. Navigate, screenshot, click, fill forms, capture snapshots.
ProductionOS smart router — single entry point that routes to the right pipeline based on intent. The ONLY command new users need to know.
Context engineering agent — researches context window optimization from arxiv, builds token-efficient context packages for downstream agents, manages cross-session persistence via MetaClaw.
Systematic debugging with hypothesis tracking — reproduce, hypothesize, test, narrow, fix. Never guess-and-check.
8-phase autonomous research pipeline with multi-source discovery, 4-layer citation verification, hypothesis generation, and PIVOT/REFINE/PROCEED decision loops. Confidence-gated — loops until 95%+ confidence.
Full UI/UX redesign pipeline — audits design, creates design systems, generates interactive HTML mockups, launches local browser for user interaction. Fuses /production-upgrade rigor with design agency methodology.
ProductionOS Mission Control — launch Claude DevTools, show session dashboard with eval convergence, agent dispatches, cost tracking, and hot file intelligence.
Post-ship documentation update — reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped.
Full-stack frontend upgrade pipeline — fuses /production-upgrade iterative audit with /plan-ceo-review vision and /plan-eng-review rigor. Deploys parallel auto-swarm agents for iterative audit and execution. Enriched with /deep-research for competitive parity.
Interactive code tutor — breaks down codebase logic, explains complexities, translates technical concepts for the user. Ideal after /btw commands. Teaches the WHY behind the code, not just the WHAT.
Business idea → production-ready plan pipeline. User provides an idea or business plan, agent researches market, competitors, existing solutions, challenges assumptions, identifies flaws, and builds a comprehensive execution plan with auto-document population.
Nuclear-scale autonomous research — deploys 500-1000 agents in ONE massive simultaneous wave for exhaustive topic saturation. Deep-research methodology × auto-swarm scale = maximum parallel intelligence. WARNING: Extreme resource consumption.
Nth-iteration omni-plan — recursive orchestration that chains ALL ProductionOS skills and agents, evaluates strictly per iteration, and loops until 10/10 is achieved. Each iteration can invoke any command or skill in the system.
ProductionOS flagship — 13-step orchestrative pipeline with tri-tiered evaluation, recursive convergence, CEO/Eng/Design review chain, CLEAR framework evaluation, multi-model judge tribunal, and autonomous PIVOT/REFINE/PROCEED decisions. Targets 100% production-ready output.
CEO/founder-mode plan review — rethink the problem, find the 10-star product, challenge premises. Four modes: SCOPE EXPANSION, SELECTIVE EXPANSION, HOLD SCOPE, SCOPE REDUCTION.
Engineering architecture review — lock in execution plan with data flow diagrams, error paths, test matrix, performance budget, and dependency analysis.
Run the full product upgrade pipeline — 55-agent iterative review with CEO/Engineering/UX/QA parallel loops
Show how to use ProductionOS — explains commands, recommended workflows, best flows to run, and usage guidelines.
Save current pipeline state for later resumption. Creates a checkpoint at .productionos/CHECKPOINT.json with all active context.
Resume a paused pipeline from .productionos/CHECKPOINT.json. Restores context and routes to the correct step.
Display ProductionOS system statistics — agent count, command count, hook count, test count, version, instinct count, and session history.
Update ProductionOS plugin to the latest version from GitHub
Report-only QA testing — produces structured report with health score, screenshots, and repro steps. No fixes applied.
Systematic QA testing with health scoring — tests web app, finds bugs, fixes them iteratively. Regression mode for re-testing known issues.
Review and refine flagged outputs, using critique and focused iteration to improve weak results.
Retrospective workflow that summarizes what shipped, what broke, and what should improve next.
Pre-landing code review — analyzes diff for SQL safety, LLM trust boundaries, conditional side effects, missing tests, dependency risks, and security issues.
7-domain security hardening audit — OWASP Top 10 2025, MITRE ATT&CK mapping, NIST CSF 2.0 alignment, secret detection, supply chain audit, container security, DevSecOps pipeline. Grounded in 734 cybersecurity skills.
Run self-evaluation on recent work — questions quality, necessity, correctness, dependencies, completeness, learning, and honesty. Enabled by default in all flows. Standalone invocation for on-demand evaluation.
End-of-session self-training — captures session metrics, extracts patterns via metaclaw-learner, updates instincts, and generates optimization hypotheses for the next run.
Ship workflow — detect base branch, merge, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR.
Test-driven development workflow that writes failing tests first, implements minimally, and refactors safely.
UX improvement pipeline — creates user stories from UI guidelines, maps user journeys, identifies friction, dispatches fix agents. The user-experience equivalent of /production-upgrade.
Implementation planning workflow that turns approved ideas into dependency-aware execution plans.
Niche-agnostic agentic evaluator using CLEAR v2.0 framework — 6-domain assessment, 8 analysis dimensions, 6-tier source prioritization, evidence strength ratings, and decision trees. Evaluates any plan, codebase, or research output.
Composite: security audit -> production upgrade -> self-evaluation. Use when user says 'audit', 'check the codebase', 'find and fix issues', or 'is this production-ready'.
Idea-to-running-code lifecycle orchestration. 10-phase pipeline with 5 hard decision gates, wave-based parallelism, and STATE.json resumability. Composes /deep-research, /auto-swarm-nth, /production-upgrade, /security-audit, and /ship into a single end-to-end flow.
Self-improving agent optimization — generates challenger variants of any agent/command, benchmarks against baseline, promotes winners, logs learnings to instincts. Inspired by Karpathy's autoresearch pattern.
Nth-iteration agent swarm — spawns parallel agent waves, evaluates strictly per wave, re-swarms gaps until 100% coverage and 10/10 quality. Can invoke any ProductionOS skill or command within waves.