waseemnasir2k26
User44 production Claude Code skills — content & reels, SEO/AEO, client delivery, code review, planning, token efficiency. One-command install.
Categories
Indexed Skills (41)
client-onboard
One command bootstraps a per-client repo so Claude Code starts pre-loaded. Detects project type (WP theme / React-Next / static / n8n / video) from files present → generates a tight CLAUDE.md (<200 lines: stack, architecture rationale, conventions + build/deploy commands) with the RIGHT deploy gotcha baked in automatically (Hostinger Node app = manual ZIP NOT GitHub; React = Vercel; video = NVENC-broken→libx264). Scaffolds .claude/, suggests relevant MCP (GHL/Hostinger), adds CLAUDE.local.md to .gitignore, enforces the CLAUDE.md-vs-Skill rule, and warns on lowercase claude.md dups. Fixes the gap: many client repos (travel, agency site, jewelry, fashion, car dealer, health clinic) ship with no CLAUDE.md, so Claude re-learns context every session. Trigger when user says: "onboard this client", "onboard repo", "bootstrap CLAUDE.md", "set up CLAUDE.md", "init client repo", "/client-onboard", or opens a client repo with no CLAUDE.md and asks Claude to start work on it. Auto-trigger heuristic: cwd is a client proje
critic-loop
LLM-as-judge quality gate. Before any deliverable ships, spawn an independent critic subagent (or N critics with distinct lenses) that ADVERSARIALLY grades the artifact against an explicit rubric, returns PASS/FAIL + a prioritized fix list, and loops (build → critique → fix) until it passes or N rounds hit. The builder must NOT grade its own work. Critic defaults to FAIL on uncertainty. Output is a scorecard + prioritized fixes + a hard ship/no-ship verdict. Domain rubrics baked in for SkynetLabs work: client website, content/copy, automation/n8n, Upwork/Fiverr proposal. Generic mode takes any artifact + rubric. Multi-critic mode runs 3 lenses + majority vote (ties to fanout-ship pattern). Trigger when user says: "critic loop", "/critic-loop", "judge this", "grade this before I send", "is this good enough to ship", "quality gate", "have a critic review", "second-agent review", or before ANY billable deliverable leaves. Auto-trigger heuristic: a deliverable (site, copy, workflow, proposal, audit) is about to b
deploy
Multi-target deploy router for SkynetLabs with deploy gotchas baked in as hard rules. Detect the deploy target from the repo, route to the correct procedure, and BLOCK the wrong path before it ships. Targets in active use: - Vercel — React/Next sites (your-site-react, your-app) via `vercel` CLI / git push - Hostinger manual ZIP — example.com (Next.js standalone on Hostinger Node app). HARD RULE: deploys via manual ZIP archive upload, NOT GitHub auto-deploy, NOT Vercel. Warn + refuse if anyone routes it to GitHub push or Vercel. - WordPress theme/plugin — ZIP upload or Hostinger MCP deployWordpressTheme/Plugin - Static site — plain HTML/CSS via Hostinger MCP deployStaticWebsite Runs a pre-deploy gate (build passes, no exposed secrets, security review, git committed), executes the routed procedure, then verifies the URL is live and records the rollback path. Trigger when user says: "deploy", "ship to prod", "push live", "/deploy", "deploy my site", "deploy to vercel/hostinger", "upload the theme", "publish the
skynet-site
Build a premium client website end-to-end — competitor research, niche-tuned design system, conversion funnel, SEO/AEO base, Vercel deploy, GitHub repo, speculative pitch with 5-8 scope-unlocking questions. Distilled from 9 shipped client wins (wedding, wellness, medical, luxury rental, clinic pitch, indie event, coach funnel, 20-niche demos, agency theme rebuild). Trigger when user says: "build a site for", "design website", "spec build for client", "/skynet-site", pastes a client brief / Upwork JD asking for a website, or wants a landing page / agency demo / niche site.
fanout-ship
Parallel multi-agent ship pattern. Decompose 1 parent task into N independent child tasks → spawn N background agents in isolated git worktrees → each opens PR targeting shared integration branch → smallest-first merge order with self-documenting rebase recipes → final PR integration → main. Collapses N×30min sequential work into ~30min wall-clock. Isolated blast radius (one agent crash ≠ kill others). Granular revert. Small review surface per PR. Background execution = no babysit. Trigger when user says: "fan out", "fanout", "split into N PRs", "parallel build", "parallel agents", "spawn N agents", "/fanout-ship", "ship in parallel", or pastes a parent issue + list of child tasks. Auto-trigger heuristic: task list ≥ 4 INDEPENDENT subtasks touching DISJOINT files, single repo, GitHub-hosted.
aeo-daily
Local AEO daily content engine — FORKED VOICE + voice filter (v0.4.2). One command → today's pack across 5 BUSINESS channels by default (was 11). Travel pack on-demand via --voice flag. BUSINESS voice (5 channels, default): LI personal, FB page, IG pro, YT pro, TikTok pro. Carousel + reels + comment-bait. TRAVEL voice (6 channels, on-demand): FB profile, IG travel x2, TikTok travel x2, Pinterest. Daily-life narrative, no agency talk. Pipeline writes single MASTER.html (all channels embedded as iframes + sticky TOC) at outputs/<DATE>/MASTER.html. All saved to <repo>\outputs\YYYY-MM-DD\copy.json (forked schema, see config/copy-schema.json). Legacy v0.3 still supported: --legacy flag falls back to single LI post + 8-slide carousel. Voice = the author's locked LinkedIn template (contrarian hook → reframe → → arrow lines → vulnerability beat → CTA + 5-8 hashtags). Authenticity layer required: 1 local anchor per post (named cafe / local currency / scooter / your local spot). 1 real client win referenced (a SaaS cli
social-stack
Build, render, and schedule social-media post packs end-to-end across LinkedIn, Instagram, Facebook, X/Twitter, Pinterest, YouTube. Picks the right template (carousel / single card / news mix / X pack / Pin / video drip), generates HTML w/ html2canvas PNG download, builds GHL CSV in canonical 6-col format, applies image rotation + no-fake-claims + humanizer rules, schedules cross-platform drips, wires ManyChat keyword funnels. Distilled from shipped patterns: - LinkedIn editorial dark+gold cards (Fraunces, 1080x1350) — 30+ batches - Tenfoldmarc-style cream+rust carousels (Archivo Black + circuit + robot mascot) - FB personal-news 9-card mix (4 info + 2 motiv + 3 sell + locked closer) - X 12-pack drip (MWF 3wk) - Pinterest 1000x1500 batch - GHL CSV format (canonical 6-col) - ManyChat keyword → WA template flow Trigger when user says: "build a carousel", "social pack", "LI cards batch", "FB news drip", "X pack", "Pinterest batch", "GHL CSV", "schedule drip", "post pack for [topic]", "/social-stack", or pastes a
etsy-empire
SkynetLabs Etsy Digital Empire Operating System — 6-niche launch strategy, 50→500 catalog scaling, year 1-3 vision, compliance guardrails, AI-leverage production pipeline. Generates listings, validates niches, plans builds, enforces 2026 Etsy policy.
plan-ceo-review
CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Three modes: SCOPE EXPANSION (dream big), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials).
plan-eng-review
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations.
review
Pre-landing PR review. Analyzes diff against main for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues.
ship
Ship workflow: merge main, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR.
code-audit-fanout
Five-way parallel code audit. User pastes a Python file / function / diff → orchestrator fans out 5 specialist sub-agents in ONE message, each reviewing a DIFFERENT axis (static analysis, library API correctness, standards/spec compliance, reproducibility, numerical correctness). Every finding MUST cite an exact URL + a quoted passage from the official documentation. Aggregator agent merges, dedupes, ranks by severity. Code returns reviewed 4-5 times before the user touches it. Trigger when user says: "audit this code", "review this diff", "debug this", "check my function", "find bugs", "/audit-code", "/code-audit-fanout", "fanout audit", or pastes a code block and asks for review. Auto-trigger heuristic: user pastes >20 lines of Python and asks for "review", "audit", "debug", "check", or "bug". HARD RULE: zero claims without a source. Every issue cites a URL to the official docs / paper / spec, plus the exact quoted passage. No hallucinated APIs, function signatures, or behaviors. If a specialist cannot veri
qa
Systematically QA test a web application. Use when asked to "qa", "QA", "test this site", "find bugs", "dogfood", or review quality. Four modes: diff-aware (automatic on feature branches — analyzes git diff, identifies affected pages, tests them), full (systematic exploration), quick (30-second smoke test), regression (compare against baseline). Produces structured report with health score, screenshots, and repro steps.
retro
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas.
ghl-video-drip
Schedule N already-uploaded GHL videos as a one-per-day, multi-platform drip via a GoHighLevel Social Planner CSV. You give the CDN MP4 links (videos already in GHL Media Library) + a start date + time + captions; this builds a validated 39-column / 2-header-row Social Planner CSV that posts each clip to TikTok + Instagram Reel + YouTube Short + LinkedIn (+ a pinned lead-magnet comment), one video per day. Distilled from batch7 (2026-05-30): 10 reels → 06-01→06-10 @ 7PM ET. Hard-won rules baked in: - Video URL MUST sit in videoUrls (col 6), NOT gifUrl (col 5) — the col-misalignment trap that makes GHL render a clip as a broken GIF. - GHL location timezone must be America/New_York (auto-DST), NOT America/Cancun (fixed GMT-05, 1h off in summer). CSV clock-time = location TZ. - 39 columns, 2 header rows (row1 platform groups, row2 field names). - Validate with .NET TextFieldParser (Import-Csv FAILS — duplicate "type" header). - Always test row 1 in GHL before trusting the full drip. Trigger when user says: "ghl
ralph-copywriter
Use this skill when the user asks to "analyze my content", "learn my writing style", "research competitors", "find content angles", "improve my blog", "write like me", "embody my brand voice", or mentions content strategy, voice analysis, competitive research, or iterative content improvement.
browse
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence.
setup-browser-cookies
Import cookies from your real browser (Comet, Chrome, Arc, Brave, Edge) into the headless browse session. Opens an interactive picker UI where you select which cookie domains to import. Use before QA testing authenticated pages.
gstack
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence.
flagship-build
Build a 1-of-1 bespoke flagship demo site (NOT a template variant). Use when user wants premium $5K-15K-tier showcase site that must look like it cost $50K+. Distilled from SkynetLabs niche-demo audit 2026-05-10 — found template DNA killed pitch credibility. Trigger phrases — "flagship build", "bespoke flagship", "premium demo", "/flagship-build", "build amazing site for [niche]".
caveman-review
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
cinematic-reel
Turn one raw landscape/cinematic clip (DJI Osmo Pocket, drone, phone) into a polished vertical 9:16 cinematic reel — scale/crop, color grade, beat-snapped chapter/title cards, optional ElevenLabs VO + ducked BGM — in a SINGLE ffmpeg pass (NVENC with libx264 auto-fallback), then optionally auto-schedule it across all socials via GHL MCP with a different human caption + hashtag set per platform. Distilled from a SkynetLabs sunset/landscape reel (2026-05-29). Trigger when user says "cinematic reel", "/cinematic-reel", "make a reel from this clip", "sunset/landscape reel", "cut this DJI footage", drops a single scenic .mp4 and wants a vertical cinematic cut, or wants a reel rendered AND scheduled to socials.
comment-bait-reel
Build a "Comment X for the links" lead-magnet reel (9:16, ~14s) from the creator's OWN clips + REAL YouTube tutorial thumbnails. Proven format: [b-roll + "POV: you want X" caption] -> [black + "Watch this" + a real YouTube card] xN -> CTA "Comment KEYWORD / it's free". Single-ffmpeg-per- segment then concat. NVENC not needed (fast at this length). Pairs with a ManyChat/GHL keyword funnel that DMs the actual link list. Distilled from the SkynetLabs Claude link-drop reel (2026-06-09, critic-passed). Trigger: "comment bait reel", "/comment-bait-reel", "comment X for links reel", "link-drop reel", "lead magnet reel", "make a reel like this" + a reference showing the POV->Watch this->Comment format, or "watch this YouTube card reel".
demo-promo
Turn a raw screen-recording / product demo into a polished, branded LANDSCAPE promo video that drives engagement. Pipeline — cut dead air, color-grade, hook card, persistent rotating TOP purpose-strap (Mike Chang style), image PiP inserts (show the actual artifact built), platform/feature chip strip, benefit callout ("this saves you HOURS"), outro CTA card, British/American AI voiceover (ElevenLabs) + sidechain-ducked cinematic BGM. Whisper-syncs overlays to the narration. Distilled from the SkynetLabs "Claude Code auto-publishes content" promo (2026-05-29). Trigger when user says "polish this demo", "make a promo from this recording", "edit this screen recording", "add hook + strap + voiceover", "/demo-promo", "Mike Chang style heading", or pastes a raw .mkv/.mp4 screencast asking to make it engaging.
easton-reel
Turn a raw vertical talking-head clip into an "Easton" finance-bro / hustle style reel — kinetic ONE-WORD red-serif punch captions snapped to speech (big Times-bold, red glow, scale-in punch), cinematic crushed-black warm grade, 9:16 1080x1920, single ffmpeg pass with NVENC→libx264 fallback. Word timestamps via faster-whisper (local, $0). Optional yellow CapCut-style sub track for b-roll lines. Trigger when user says "easton reel", "/easton-reel", "finance bro reel", "red kinetic caption reel", "one-word punch captions", "make my talking-head clip look like easton/hamza/hustle reels", or drops a vertical talking-head .mp4 and wants big red one-word-at-a-time captions.
reel-studio
ONE skill for ALL SkynetLabs professional short-form reels. Replaces saddamh1-replicator + interview-clipper + voiceover-batch. Five modes — `interview` (long video → 9:16 shorts), `saddamh1` (talking-head from script), `tts` (voiceover-only reel), `kinetic-stoic` (text-only quote reel), `mograph` (motion-graphics explainer w/ UI chips + halos, no face cam — decoded from @beingmayy + @mister.usb). Default style = saddamh1 (Hinglish/Urdu freelancer-business advice reels). Trigger when user says "reel for X", "script for", "clip this interview", "edit my video", "/reel-studio", "make reel", "saddamh1 style", "voiceover reel", "mograph", "motion graphics reel", "explainer reel", "beingmayy style", "mister.usb style".
jarvis-secure
One-command laptop security sweep + speed/hardening pass for Windows (Jarvis core). Read-only audit first (Defender status, threat history, live connections, listening ports, firewall, autoruns, scheduled tasks, network neighbors), then OPTIONAL hardening (Public firewall inbound block, disable SMB1, remove Lenovo SoftLanding bloat) and OPTIONAL cleanup (measure %TEMP%/caches/Recycle Bin, then clean safe targets). Ends with a hardware verdict (RAM / SSD vs HDD / CPU / free disk / power plan). Use when user says "run jarvis", "antivirus scan", "scan my laptop", "scan my network", "is my laptop safe", "clean temp files", "make my laptop faster", "security check", "/jarvis-secure", "harden my pc", or asks to check the machine/network for threats.
n8n-code-javascript
Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, or choosing between Code node modes.
n8n-code-python
Write Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes.
n8n-expression-syntax
Validate n8n expression syntax and fix common errors. Use when writing n8n expressions, using {{}} syntax, accessing $json/$node variables, troubleshooting expression errors, or working with webhook data in workflows.
n8n-mcp-tools-expert
Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.
n8n-node-configuration
Operation-aware node configuration guidance. Use when configuring nodes, understanding property dependencies, determining required fields, choosing between get_node detail levels, or learning common configuration patterns by node type.
n8n-validation-expert
Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, or the validation loop process.
n8n-workflow-patterns
Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, or scheduled tasks.
simmer-generator
Generator subskill for simmer. Produces an improved version of the artifact based on the judge's ASI feedback. Handles both single-file and workspace targets. Do not invoke directly — dispatched as a subagent by the simmer orchestrator.
simmer-judge-board
Judge board subskill for simmer. Dispatches a panel of judges with different lenses, runs one deliberation round where they challenge each other's scores, then synthesizes consensus scores + single ASI. Drop-in replacement for simmer-judge that produces identical output format. Do not invoke directly — dispatched by the simmer orchestrator when JUDGE_MODE is board.
simmer-judge
Judge subskill for simmer. Scores a candidate artifact against user-defined criteria on a 1-10 scale and produces ASI (highest-leverage direction) for the next generator round. Supports judge-only, runnable evaluator, and hybrid evaluation modes. Do not invoke directly — dispatched as a subagent by the simmer orchestrator.
simmer-reflect
Reflect subskill for simmer. Records iteration results in trajectory table, tracks best candidate, handles regression rollback, and passes ASI forward to the next round. Supports both single-file and workspace modes. Do not invoke directly — called by simmer orchestrator after each judge round.
simmer-setup
Setup subskill for simmer. Inspects the artifact or workspace, infers evaluation contracts and search space, proposes a complete assessment to the user, and produces a setup brief after confirmation. Conversational, not form-based — the agent does the work of understanding the problem, then presents what it found. Do not invoke directly — called by simmer orchestrator.
simmer
Use when user says "simmer this", "refine this", "hone this", "iterate on this", or asks to improve a specific artifact over multiple rounds. Runs an iterative refinement loop with investigation-first judges that read the code, understand the problem, and propose evidence-based improvements. Auto-selects single judge or multi-judge board based on complexity. Works on any artifact type: documents, prompts, specs, emails, creative writing, API designs, pipelines, codebases. Supports multi-file workspace targets, runnable evaluators, and open-ended optimization (model selection, pipeline topology, prompt tuning).
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.