Claude Skills by hamza-ali-shahjahan

Stress-test an idea or hypothesis. Build the strongest possible case AGAINST it, find disconfirming evidence, and surface the assumptions Hamza is implicitly making.

Generate startup ideas grounded in Hamza's existing patterns, current trends, and validated demand signals. Never just brainstorms — pulls from real signals.

Synthesize a batch of customer interviews into evidence-for + evidence-against the hypothesis, with pattern surfacing and bias flagging.

Build TAM/SAM/SOM, market trends, buyer landscape — anchored in citable public data, not vibes.

Turn vague problem observations into testable hypothesis statements with specific who/when/severity/current-workaround dimensions.

Build the brand foundation — positioning, story, voice, naming, visual primitives — so every other launch asset (landing, content, outreach) sings the same song.

First 100 customers by hand. Sourcing → personalized cold messages → follow-up cadence → tracking. Volume × signal, not spam.

Build a community around the product — Discord/Slack/forum, waitlist nurture, early-user comms. Choose the right venue, don't default to Discord.

Build content calendars and draft individual pieces — blog posts, social, LinkedIn, threads — anchored on keyword research and brand voice.

Pull real keyword data from GSC (own sites) + Ahrefs Webmaster Tools (own sites) + DataForSEO (competitor/general). Produce a clustered keyword brief.

Write landing page copy that converts. Hero + 3 value props + social proof + objections + CTA. Anchored on validated user language.

Plan and execute the launch — Product Hunt, Hacker News, X/Twitter, LinkedIn, newsletters, communities — sequenced for compounding signal.

Initial pricing for a product — packaging, tiers, anchor, monthly vs annual, free vs trial. Anchored on value-based pricing + van Westendorp where data exists.

Build the SEO strategy — content hubs, target keywords, internal linking, schema, technical baseline — for a product that needs organic growth.

Define a product's architecture BEFORE Claude Code writes a line. Produces CLAUDE.md, scope.md, and a 1-page architectural decisions doc.

Drive Claude Code build sessions inside a product folder. Enforces session discipline: read CLAUDE.md + scope.md first, log decisions after.

Define the measurement framework BEFORE launch. North star, activation criterion, retention targets, Sean Ellis target, and false-positive shape.

Block scope creep. Every feature ask gets pressure-tested against scope.md. Bar to amend: specific evidence from real users.

Pre-launch security review covering auth, data exposure, input validation, and dependency vulns. Produces a remediation list, not a "looks good" stamp.

Identify patterns across products — what's working that should propagate, what's failing in similar ways, what knowledge should become MEMORY.md entries.

Quarterly portfolio review. Hard call on what to kill, what to maintain, what to double down on. Forces decisions.

Decide where attention goes today across the 10-product portfolio. The "if you had 4 hours to work on the portfolio, do this" agent.

Pull metrics across all products into a single view. Powers the dashboard and the daily/weekly briefings.

Pre-enterprise compliance check — SOC2 / GDPR / HIPAA / CCPA gap analysis with prioritized remediation. Not a substitute for real audit.

Design growth loops (Reforge/Balfour framework). Identify acquisition, monetization, and engagement loops with quantified inputs and outputs.

Identify and deepen moats — workflow lock-in, data network effects, domain depth, integration depth. Audit current moats + propose investments.

Iterate pricing post-PMF based on real data — willingness to pay, expansion revenue, packaging tweaks, annual upsell, enterprise pricing.

Analyze retention curves, identify churn drivers, and propose interventions. Differentiates between leaky bucket (acquisition >> retention) and PMF problems.

Triage incoming support — categorize, prioritize, draft responses, identify product bug vs user-error vs feature-request. Routes to engineering when needed.

A library of real, hard-won website-launch failure modes — each with what happened, the root cause, and how to prevent it. Use before starting a launch, when debugging a launch-time SEO/analytics/performance problem (indexation not happening, redirect or canonical issues, analytics undercounting, schema validation failing, CWV regressions, robots.txt mistakes), or when a launch checklist item refuses to verify. These are the mistakes that normally only get learned by being burned. Companion t...

Quality and indexation discipline for programmatic / templated SEO at scale — sites with hundreds to tens of thousands of generated pages (directories, /tool, /compare, /category, location or entity pages). Use when planning, launching, or auditing a large templated page set: preventing mass thin-content, designing sitemap-index architecture, locking slug discipline, staging the indexation ramp, and deciding what to index vs noindex. The risk at scale is not one bad page — it's 15,000 mediocr...

Run a website launch as a verification-gated process, not a to-do list. Use when taking a site (or a major site section) to production — scoping a launch, building or walking a launch checklist, deciding if a site is ready to ship, or setting up post-launch monitoring. Emits a per-project tracking workbook, enforces a refuse-to-launch sign-off gate (every P0/P1 must be Verified, not just Done), and routes commodity SEO/security/performance work to specialist skills. Pairs with launch-gotchas ...

Intelligent workflow orchestrator that automatically chains the right skills (spec, plan, build, test, review, code-simplify, ship) based on the current state of the work. Use when you want Claude to drive a feature or task end-to-end without manually invoking each skill.

Generate a product's full brand-asset set at finishing time — two logo concepts to choose from, then the square app icon, favicon set, horizontal lockup, and a separate square auth-provider logo. One SVG source of truth, rendered with rsvg-convert. Every product needs all of these before launch.

Tests in real browsers. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data via Chrome DevTools MCP.

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

Compose interfaces that hold together — skeleton before aesthetics, one alignment per row, sizing by declaration. Use when building or reviewing any UI component, fixing "it looks off but I cannot say why", or adding an element to an existing layout.

Launch the factory's control plane — scaffold and fill FACTORY-ORDERS (weekly mandate + hard budget), STANDING-ORDERS (autonomous-program authority), HEARTBEAT (weekly pulse), and write lifecycle gates for every registered product. A deliberate one-time ritual (re-run to audit); invoke as /factory-launch, not auto-triggered.

Slice a goal into the smallest feature slices that can each be PROVEN — every slice ships with a named eval and an end-to-end test, and a slice you can't evaluate or test doesn't get selected. Use after the goal is set and before the spec, so only provable features make the build.

Builds production-quality UIs. Use when building or modifying user-facing interfaces. Use when creating components, implementing layouts, managing state, or when the output needs to look and feel production-quality rather than AI-generated.

Guided, stateful provisioning of a product's production stack — deep-links, key-format validation, a secrets backend (fnox recommended, or user-touched .env.local), a resumable ledger, CLI automation after signup, and a blocking A1–A10 live gate. Hands off to /security-check → /ship. The walked version of SETUP.md.

Refines ideas iteratively. Refine ideas through structured divergent and convergent thinking. Use "idea-refine" or "ideate" to trigger.

Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.

Quarterly portfolio review with forced verdicts (DOUBLE-DOWN / MAINTAIN / MINIMAL / KILL) for every product.

Compress a month of market research into ~3 hours, evidence first. Use before positioning, pricing, GTM, or betting on a new idea — harvests competitor sites, incumbent filings, reviews, and complaint threads into a local corpus, then interrogates it with every claim cited to a source file or flagged as speculation.

Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.

Assess an external GitHub repo for Hamzaish — verify health, clone read-only, run a facts-only deep-dive, and land a references-grammar draft in the scout backlog for operator review. Use when the operator drops a repo URL to evaluate, asks "can we leverage X repo," or on a trending sweep (--trending). Drafts only — nothing enters references/, credits, or the factory without an approved PR.

One-shot a new product — folders, Next.js starter, product.config.json, CLAUDE.md, scope.md, PRD skeleton, SETUP.md checklist. The Lovable-like ignition.

Prepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.