cleanexpo

@cleanexpo source repo

430 skills
0 followers
last month last updated

▌
Remotion Motion Language · cleanexpo
Designs a brand-specific motion vocabulary — easing curves, default scene durations, signature entry/exit, transition frames. Each brand gets one signature move (rise / sweep / pulse / iris / whip) that recurs across compositions to build motion-recognition. Triggered when BrandConfig.motion is empty.

7 installs
▌
Remotion Professionalism · cleanexpo
Use when a Remotion video needs a professional marketing QA pass for brand fit, readability, pacing, typography, polish, and not-looking-generated.

8 installs
▌
Remotion Render Pipeline · cleanexpo
Final step. Synthesises ElevenLabs voiceover for each scene, runs `npx tsx render/render.ts` to produce an MP4, validates duration / codec / resolution / size, uploads to Supabase storage, ships the result via Telegram, and opens a Linear ticket. Triggered after remotion-composition-builder reports ready. Failure modes (timeout, hang, type error) escalate to Linear.

8 installs
▌
Skill Authoring Standard · cleanexpo bundle
Use when creating, editing, reviewing, or generating any skill — a SKILL.md, skill frontmatter, or a skill-foundation packet. Load BEFORE writing the skill so the four gates and frontmatter schema apply from the first line.

9 installs
▌
Compound Development Loop · cleanexpo
Agentic development operating loop for non-engineer-led builds: expand the idea, research surrounding advances, produce artifacts, plan, build, review, and compound learnings back into the 2nd brain and CRM.

8 installs
▌
Telegram Draft For Review · cleanexpo
Draft an outbound Telegram message and gate it behind a human reaction (👍 send, ❌ revise) before any actual send happens. Sits in front of swarm/telegram_alerts.py for human-addressed messages. Required path for every Scribe outbound.

9 installs
▌
Growth Sustainability Data · cleanexpo
Method for collecting and gathering data for growth and sustainability across the 11-business portfolio. Defines the two-layer stack — Analyst (direction + analysis) commands collector skills (CMO, CFO, CTO, CS, Margot, wiki, Scout, marketing) — and the handoff contract between them. Use when framing executive visibility, research sprints, board prep, or any question about whether the business can grow and endure.

8 installs
▌
Marketing Campaign Planner · cleanexpo
Designs an end-to-end marketing campaign — objectives, audience, channels, creative concept, timeline, budget, success metrics — for any portfolio or customer brand. Use when a brief asks for a "campaign", "marketing plan", "promo", "GTM motion", or "launch plan" beyond a single artifact. Triggered by marketing-orchestrator wave 1 or directly by name. Produces a structured Campaign Plan markdown + JSON consumed by every downstream marketing skill.

10 installs
▌
Analyzing Customer Patterns · cleanexpo
Outcome feedback loop analyser. Reads shipped feature records + post-ship signals, detects patterns in what worked vs what didn't, and writes outcome lessons back into the build pipeline. Feeds the BVI "features delivered" component.

9 installs
▌
Remotion Screen Storyteller · cleanexpo
Writes the on-screen script for a video — scene-by-scene voiceover, on-screen text, b-roll callouts, and CTA. Triggered when the brief is a goal or topic but lacks scene structure. Produces a Storyboard JSON consumed by remotion-composition-builder and remotion-render-pipeline (for ElevenLabs voiceover synthesis).

10 installs
▌
Marketing Channel Strategist · cleanexpo
Selects the channel mix and per-channel cadence for a campaign — LinkedIn, YouTube, X, email, paid ads, SEO, partnerships, podcasts, communities. Use when a brief asks "what channel", "where should we post", "channel strategy", "cadence", or upstream of any content production. Reads BrandConfig.defaultChannel and ICP watering-holes; outputs a per-channel spec consumed by copywriter, social-content, copywriter, and remotion-orchestrator (channel sets aspect ratio / duration).

5 installs
▌
Remotion Composition Builder · cleanexpo
Authors or extends a Remotion composition (.tsx) wired to BrandConfig + Storyboard + layout spec + motion. The actual builder skill — runs as a Sonnet-tier worker. Triggered after brand, storyboard, designer, and motion-language outputs are ready. Produces the file under remotion-studio/src/compositions/ and registers it in src/Root.tsx.

9 installs
▌
Remotion Marketing Strategist · cleanexpo
Tunes a video's format and message for the target channel — LinkedIn, YouTube, Instagram Reel, internal training. Sets aspect ratio, total duration, hook timing, CTA timing, and pacing. Triggered when the brief mentions a specific channel or campaign goal. Output feeds remotion-screen-storyteller and remotion-composition-builder.

9 installs
▌
Marketing Analytics Attribution · cleanexpo
Designs the UTM scheme, attribution model, and KPI dashboard for a campaign — before launch, not after. Use when a brief asks for "UTM", "tracking", "attribution", "analytics", "dashboard", "KPI", "ROI", "measurement plan". Outputs a UTM-builder spec, an attribution-model decision, a per-channel KPI dashboard structure, and a retro template. Composes with marketing-channel-strategist (per-channel UTM tags) and marketing-launch-runbook (gate at T-7).

10 installs
▌
Connecting Meta Facebook Instagram · cleanexpo
Use when connecting or fixing Facebook/Instagram (Meta) OAuth in a web app — Connect button no-ops or errors, "Meta Login for Business config missing", config_id/app mismatch, "Can't load URL / App Domains not included", pages_manage_posts / instagram_content_publish rejected, or repointing Synthex-style social posting to a Meta app you actually control after an ex-employee set it up.

10 installs
▌
Cfo · cleanexpo
Daily financial visibility across the 11 Unite-Group businesses. Computes burn multiple, NRR, CAC payback, gross margin from Stripe + Xero feeds. Drafts a 1-page financial brief into the daily 6-pager. Gates spend approvals >$1K through draft_review HITL. Closes Wave 4.1 of the senior-agent slate (RA-1850).

9 installs
▌
Cto · cleanexpo
Daily platform-health visibility across the 11 portfolio repos. Computes the DORA quartet (deploy frequency, lead time, MTTR, change-failure rate) plus p99 latency, uptime, and cost-per-request from GitHub Actions + Vercel observability feeds. Drafts a 1-page CTO snippet into the daily 6-pager. Gates production PR merges through draft_review HITL. Closes Wave 4 A3 of the senior-agent slate (RA-1861).

10 installs
▌
Spm · cleanexpo bundle
Senior Project Manager command (/spm). Use before implementation to turn a rough task, feature, bug, idea, ticket, PR, or repo area into a decision-grade spec.md — via read-only project inspection, a self-leveling MOA specialist bench (0–8 seats sized to task complexity), judge-style challenge, verification + stress-test planning, and goal-ready acceptance criteria. Read-only — produces the spec, never the build.

6 installs
▌
Tao · cleanexpo
The Tao is the autonomous execution engine that ties self-direction with governance. It orchestrates /nexus (routing), /tao-loop (iterate-generate-deploy), /tao-judge (iterative-evaluator-calibrator), and /session-handoff (continuity/escrow) into a single cohesive autonomous mission-runner. The Tao handles autonomous overnight execution for complex projects.

8 installs
▌
Eeat · cleanexpo
E-E-A-T specialist — a first-class UPSTREAM consult lens that scores content for Google's Experience, Expertise, Authoritativeness, and Trust signals BEFORE it's finalized, and returns structured fixes. Use when producing or auditing any content, page, or claim that needs to rank / be cited / be trusted (blog, landing page, YMYL, client deliverable). Consumed by the specialist-council, marketing, seo, and geo-optimization; complements source-ingest (credibility of sources) and brand-guardian (terminal accuracy gate). Triggers on "E-E-A-T", "EEAT", "experience expertise authoritativeness trust", "trust signals", "author authority", "does this look credible/trustworthy".

7 installs
▌
Judge · cleanexpo
Mandatory pre-build challenge gate (/judge). Run before approving or building any feature, connector, automation, agent, hook, MCP server, UI change, database change, or architecture plan. Read-only — performs first-source evidence review, devil's advocate critique, existing-capability review, UX review, security/privacy review, test/stress review, and return-on-effort scoring out of 100.

10 installs
▌
Nexus · cleanexpo bundle
Master-orchestrator command. Type /nexus <goal> to have the estate's best minds work a goal end-to-end — frame it, research it to primary sources, deploy the right specialists, think past the obvious downstream, verify it adversarially, and hand back a decision a non-technical founder can act on. Default-lean; it does the minimum the goal actually needs.

8 installs
▌
Storm · cleanexpo
Use when the user wants a comprehensive, neutral, citation-grounded article, report, briefing, or explainer researched from scratch on a topic — invoked as /storm or by asking to "STORM" a topic. Reproduces the Stanford STORM method (perspective discovery + retrieval-grounded multi-perspective Q&A → outline → grounded long-form write-up). Not for quick factual lookups, opinion pieces, or topics that need private/internal data.

10 installs
▌
Claude · cleanexpo
Correct patterns for Claude SDK usage, subprocess vs API mode selection, MCP SDK imports, and streaming API call conventions in the Pi-Dev-Ops codebase.

9 installs
▌
Unlazy · cleanexpo bundle
Turn substantial delivery work into a dependency tree with owned files, rolling dispatch, executable gates, and exact completion evidence.

8 installs
▌
Verify · cleanexpo
Run the loop from `prove-the-failure` and confirm red goes green, then hold a cooldown before any further action is permitted. Use after `adversarial-review` returns PASS, before `immunise`.

8 installs
▌
Analyst · cleanexpo
Research and intelligence doctrine — the directing analysis layer for growth and sustainability data collection. Frames questions, tasks collector skills, grades evidence (NATO/Admiralty), runs ACH/premortem/gap-scan, and delivers defensible evaluations with kill-switches. Use before any non-trivial research, market sizing, strategic bet, or when synthesising collector output into a decision.

8 installs
▌
Contain · cleanexpo
Reach a safe state before diagnosing. Halt the affected job, revert to last known good, or stop the loop — containment, never a fix. Records what was contained and what was deliberately left alone. Use immediately after `prove-the-failure`, or any time a failure is actively recurring and the bleeding must stop first.

8 installs
▌
Ship It · cleanexpo
A launch-readiness PRE-FLIGHT that runs before the existing ship-chain — load the charter, audit build-state, run the aggregated launch-review, propose enhancements, sync findings to Linear via the existing pi-dev-linear-contract, then STOP for a human go. On go it hands the approved, build-ready issues to the existing ship-chain / tao-loop, never re-implementing build/test/ship. Use on "ship it" / "run the launch crew".

9 installs
▌
Ceo Mode · cleanexpo
CEO-level strategic analysis and executive communication. Direct, evidence-based, no filler.

8 installs
▌
Classify · cleanexpo
The gate in the self-healing chain. Decides whether a diagnosed failure may proceed to an automated fix, by asking two questions — is this a known pattern in incident memory, and how wide is the blast radius. Known and low-radius may proceed; novel or high-radius stops and reports with the diagnosis attached. Also holds the chain's circuit breaker. Use after `diagnose`, before any repair is designed.

8 installs
▌
Cs Tier1 · cleanexpo
Tier-1 customer support across the 11 portfolio brands. Computes NPS, First Contact Resolution (FCR), Gross Retention Rate (GRR), and avg first-response time. Drafts replies through telegram-draft-for-review. Approves refunds up to $100; routes anything larger through draft_review HITL. Closes Wave 4 A4 of the senior-agent slate (RA-1862).

6 installs
▌
Diagnose · cleanexpo
Find root cause by running the red loop from `prove-the-failure` and changing one variable at a time — never by reading the code and reasoning about it. Outputs a written cause with file and line evidence. Use after containment, before any repair is designed.

8 installs
▌
Grill Me · cleanexpo
Run a relentless one-question-at-a-time interview on a sketch or plan until every branch of the decision tree resolves into either a decision, a rabbit hole, or an explicit no-go. Use when the user wants to stress-test a fat-marker sketch before any code is written, or asks to be "grilled", "interviewed", or to "stress-test" a plan. Adapted from Matt Pocock's /grill-me (mattpocock/skills) and combined with Shape Up's appetite + fidelity discipline.

9 installs
▌
Immunise · cleanexpo
Add the check, test, or workflow guard that stops this failure recurring. May propose a fence change; may never apply one. Use after `verify` passes and its cooldown has elapsed.

7 installs
▌
Brand Strategist · cleanexpo
Senior Brand Strategist (15+ yr calibration). Voice register strategic owner. Maintains per-brand voice tag system (Q2.5.5) + Phase 4 voice amendments + verification-gated category claims + portfolio taboo discipline + L9 cross-client carve-out. Approves voice register decisions before brand-voice-enforce mechanically gates drafts. Closes every decision with the specific voice-tag locked, amendments cited, and the brand-voice-enforce directive that downstream skills consume. Reads ceo-foundation.md + verification-gates.md at every invocation.

9 installs
▌
Campaign Planner · cleanexpo bundle
Synthex campaign planning enforcer. NEVER produce generic Mon-announcement, Wed-educational, Fri-promotional calendar arcs, or fill slots with placeholder content types without brand-specific reasoning. ALWAYS derive the content arc from the brand's DNA and campaign goal, vary cadence by platform, and name the specific hook angle for every calendar slot. Activate on ANY request to plan a campaign, build a content calendar, schedule posts, or map out a 30/60/90-day content strategy.

8 installs
▌
Client Retention · cleanexpo
Senior Client Retention + Customer Success Lead (15+ yr calibration · cohort analysis · churn modelling · intervention design · expansion-revenue framing). Owns user-engagement monitoring, churn-risk identification, and retention-strategy design across the 4 Nexus brands and CCW carve-out (Phase 3.4 boundary mechanical). Produces cohort-retention reports, at-risk-user lists with verified-vs-hypothesised churn-probability scores, intervention proposals routed through brand-voice-enforce and frequency-cap (Q3.2.4 hard rule 8 source-of-truth job ID + cross-brand cap pooling). Reads ceo-foundation.md + verification-gates.md at every invocation.

13 installs
▌
Content Pipeline · cleanexpo bundle
AI content generation pipeline guide for SYNTHEX. Documents the model registry, provider abstraction, BYOK key injection, content scoring, and repurposing flow. Use when working on AI-powered content features or debugging model selection issues.

9 installs
▌
Email Specialist · cleanexpo
Senior Email Marketing Specialist (15+ yr calibration). Owns email lifecycle for the 8 active cross-sell triggers (T1, T2, T3, T4, T5, T7, T8, T10) plus deferred P2 triggers (T6, T9). Enforces foundation rules at every draft: Q2.5.3 cadence map, frequency cap, quiet hours, compliance-deadline override, cross-client boundary. Closes every sequence with a falsifiable open/click/conversion target, a kill threshold, and a sender-reputation guard. Reads ceo-foundation.md + verification-gates.md at every invocation.

8 installs
▌
Grounded Visuals · cleanexpo
THE way to produce any image or video in Synthex — grounded on the founder's owned real-photo library with the industry LoRA auto-applied. Use for every visual asset request (brand, campaign, social, video seed, training material). Never call an image provider directly.

9 installs
▌
Ship Loop Master · cleanexpo
24/7 ~1.5-day autonomous shipping orchestrator for Synthex. Drives 7 child loops (build, test, sanity, watch, smoke, pr, merge) on differentiated cadences. Reads state from .claude/scratchpad/ship-loop-state.json on every tick, dispatches the next eligible child loop, and exits cleanly after 36 hours OR when state.completion === 'merged'. Use when the CEO says "/loop ship-loop-master" to start an autonomous shipping run.

7 installs
▌
Ship Loop Sanity · cleanexpo
Security/quality gate child loop. Runs auth ratchet test, npm audit, parallel auth-coverage script, and a secret-leak diff-scan. Updates ship-loop-state.json with per-gate state. On failure applies one recovery recipe (typically auth ratchet triage or audit fix), retries once, escalates. Use standalone via /loop ship-loop-sanity or wired into the master orchestrator.

9 installs
▌
Foundation Keeper · cleanexpo
Senior Foundation Keeper (15+ yr governance calibration). Discipline-enforcement meta-skill. Maintains canonical foundation files (ceo-foundation.md · verification-gates.md · skill-orchestration-spec.md · reporting-templates.md · tier-b-engineering-specs.md · gap-audit-playbooks.md). Updates verification-gate state ONLY when source documentation arrives + filed in registry. Refuses unsupported flips. Logs every amendment + every refusal with audit trail · zero silent updates. Read-write authority on canonical files; all other skills consume them read-only. The mechanism that prevents hallucination at production time. Closes every action with audit_log_entry, downstream-skill notifications, and brand-voice-enforce directive.

7 installs
▌
Platform Showcase · cleanexpo bundle
Synthex platform showcase enforcer. NEVER describe features with generic marketing language ("powerful AI", "seamless integration") or produce wall-of-bullets capability lists. ALWAYS lead with a specific client outcome, use concrete numbers, and write in Australian English. Activate on ANY request to showcase a platform, explain a feature, demonstrate capability, or create platform presentation content.

7 installs
▌
Security Hardener · cleanexpo
Synthex security posture enforcer. NEVER apply generic OWASP checklists without grounding in Synthex's specific threat model. NEVER suggest any auth system other than Supabase. ALWAYS audit: SSRF via validateExternalUrl, JWT tier elevation via resolveVerifiedTier, CORS via CORS_ORIGIN exact-match, org-scope bypass in Prisma. Activate on ANY request to harden security, audit vulnerabilities, review auth patterns, check for injection risks, or assess an attack surface.

8 installs
▌
Senior Copywriter · cleanexpo bundle
Senior Copywriter (15+ yr calibration). Drafts client-facing content (LinkedIn posts · Hub articles · email sequences · landing-page copy · ad copy · Remotion scripts · founder thought leadership) per the surface's locked foundation structure. Reads ceo-foundation.md + verification-gates.md at every drafting task. Closes every draft with a falsifiable engagement/conversion hypothesis, a kill threshold, and a pre-gate self-audit against the junior-failure-mode NEVER list before routing to brand-voice-enforce.

5 installs
▌
Senior Strategist · cleanexpo
Senior Strategist (15+ yr calibration). Cross-skill orchestrator and final-gate before the CEO batched-review queue. Calibrates strategy to locked foundation, sequences skill handoffs against `skill-orchestration-spec.md`, audits drafts against verification-gates.md before forward, surfaces decisions that genuinely require CEO attention. Consumes structured outputs from analytics-lead · cro-specialist · email-specialist · creative-director · senior-copywriter and routes them via H-1 through H-4 protocols. Never writes client-facing copy directly. Reads ceo-foundation.md + verification-gates.md + skill-orchestration-spec.md at every invocation.

9 installs
▌
Synthex Standards · cleanexpo bundle
Synthex Capability Uplift master reference. Contains the authoritative anti-patterns and replacement standards that override LLM defaults across ALL Synthex skills. ALWAYS read the relevant reference file before producing UI, content, chart, or code output. Activate on any visual, content, code, campaign, brand, analytics, or design task.

10 installs
▌
Build Orchestrator · cleanexpo
5-phase deployment orchestrator for Synthex production releases. Manages the full lifecycle from preflight validation through post-deploy monitoring. Use when deploying to production, running build pipelines, or diagnosing deployment failures. Phases: PREFLIGHT, BUILD, DEPLOY, VERIFY, MONITOR.

10 installs
▌
Codex Agent Loader · cleanexpo
On-demand loader for VoltAgent/awesome-codex-subagents. Install any of the 136 specialist Codex agents into Claude Code on demand. Covers backend, frontend, infra, security, data, DevEx, and meta-orchestration domains.

8 installs
▌
Brand Voice Enforce · cleanexpo
Mechanical gate that checks senior-skill output against the brand rules locked in `.claude/memory/ceo-foundation.md` and the gate state in `.claude/memory/verification-gates.md`. Reads both at every invocation. Pass/fail decision per draft. Forwards passing drafts to senior-strategist for final review before CEO batched-review queue.

10 installs
▌
Social Integrations · cleanexpo
Social media platform integration guide for SYNTHEX. Documents the 9-platform architecture, OAuth connection flow, webhook signature verification, token encryption, and the base service contract. Use when adding platform support, debugging OAuth issues, or working on webhook handlers.

9 installs
▌
Vercel Build Doctor · cleanexpo
Diagnose Synthex Vercel production build failures from the actual build logs, not guesses. Pulls the failed deployment's logs via the Vercel REST API, classifies the failure against a known-error table (OOM/exit 137, type-check, schema drift, module-not-found, function-size, timeout), and applies the proven fix. Use whenever a Vercel deploy shows "failure"/ERROR, the GitHub "Vercel – synthex" check is red, or someone says "we're still getting Vercel errors".

8 installs
▌
Cursor Hooks Windows · cleanexpo
Fix Cursor beforeShellExecution hooks on Windows when stdout is invalid JSON or empty. Use for hooks-allow.bat, validate-mounted-env-files.sh, 1Password plugin, or "blocked for safety" agent terminal errors on Synthex (Windows 11).

8 installs
▌
Visual Content Brief · cleanexpo bundle
Synthex visual content enforcer. NEVER produce generic stock-photo prompts, "professional woman at a desk" imagery without brand colour injection, or AI image prompts that could belong to any brand. ALWAYS inject the brand's primary hex, lighting that matches brand tone, and a negative prompt banning competitor colours and stock-photo feel. Activate on ANY request to create visuals, image prompts, design briefs, social graphics, product photography, or brand imagery — including "what should my images look like".

9 installs
▌
Architecture Enforcer · cleanexpo
Synthex architecture pattern enforcer. NEVER suggest Redux, Zustand, tRPC, GraphQL, Server Actions for mutations, or any pattern absent from this codebase. NEVER allow cross-layer imports (page importing from lib/ directly). ALWAYS enforce: Pages → Components → Hooks → lib/ → Database. All mutations go through API routes. Activate on ANY request to design architecture, review patterns, plan a new system, refactor, or assess structural decisions.

10 installs
▌
Client Content Studio · cleanexpo bundle
Autonomous per-client avatar+voice content engine (HeyGen + ElevenLabs) that turns a paying client's project activity into constant client-focused updates, published and measured per client through the Synthex dashboard. NEVER publish client-facing content without the human-approval gate. NEVER generate a HeyGen avatar without a recorded consent record. NEVER report fabricated client metrics (views/engagement) — only real or DATA_REQUIRED. ALWAYS scope per client and one-source→many-surfaces. Activate on ANY request to generate client video/voice updates, onboard a client to the studio, build the autonomous content loop, or work on the HeyGen/ElevenLabs pipeline.

9 installs
▌
Dependency Discipline · cleanexpo
The "no invaders" gate for Synthex. The ship already carries everything it needs. NEVER add a new npm dependency, external SaaS, framework, datastore, or auth system to solve a problem an existing system already solves — adding one is a CEO-gated decision. ALWAYS prove the capability isn't already present (grep package.json, lib/, the skills list, Vercel env) before integrating anything new. Activate on ANY request to "add a package / install / npm i / integrate X / we need a tool / use library Y / add a provider / new database".

7 installs
▌
Google Search Console · cleanexpo bundle
GSC data interpretation, indexing triage, coverage analysis, sitemap strategy, and diagnostic decision trees for search performance issues. Use when working with Search Console data, debugging indexing problems, or analysing search analytics trends.

3 installs
▌
Local SEO Geo Veteran · cleanexpo
Senior Local SEO + GEO Veteran (15+ yr calibration · GBP rank-and-rent · service-area-business compliance · schema discipline · AI-search realism). Owns DR's Google Maps + GBP work (the only portfolio brand with genuine local-services GBP relevance per L7 carve-out) and schema markup audits across the portfolio. Enforces foundation Q3.2.3 amendments at every action — GBP compliance rule (no artificial profiles), AI-search realism (directional snapshot not KPI), schema discipline (matches visible content), 30/30/30 sequencing. Reads ceo-foundation.md + verification-gates.md at every invocation.

9 installs
▌
Customer Insights Lead · cleanexpo
Senior Customer Insights Lead (16+ yr calibration · JTBD · ethnography · audience-evidence base custodian). Owns the locked audience profiles for the portfolio (foundation Phase 3.1.2 RA · Phase 3.2.2 DR + NRPG · Phase 3.3.2 CARSI · Phase 3.4.2 CCW + Bridge) and the verified-vs-hypothesised state of every JTBD claim senior-copywriter consumes. Surfaces audience-match · drift · trigger-alignment opportunity to invoking skill with explicit verification-state tagging. Reads ceo-foundation.md + verification-gates.md at every invocation.

9 installs
▌
Pr Communications Lead · cleanexpo
Senior PR + Communications Lead (15+ yr calibration · earned media · crisis comms · executive thought leadership · industry-association positioning). Owns external-facing communications across the 4 Nexus brands (DR · NRPG · RestoreAssist · CARSI) and the CCW carve-out (Phase 3.4 boundary mechanical). Produces press-release drafts, journalist-pitch packages, crisis-response statements, executive thought-leadership briefs, and brand-reputation snapshots — every output passes the brand-voice-enforce gate, the Aid Rule (no AI-as-actor framing), the verification-gate state for any category claim, and the Phase 3.4 cross-portfolio carve-out. Reads ceo-foundation.md + verification-gates.md at every invocation.

16 installs
▌
Dx Review · cleanexpo
DX Review Specialist

5 installs
▌
Google Business Profile · cleanexpo bundle
Listing optimisation, review response strategy, Google Posts, local pack ranking factors, NAP consistency, and category selection for Google Business Profile. Use when optimising GBP listings, managing reviews, or improving local search visibility.

6 installs
▌
Google Updates Sentinel · cleanexpo bundle
Algorithm update types, diagnosis workflows, recovery strategies, and proactive hardening for Google algorithm changes. Use when diagnosing traffic drops, responding to algorithm updates, or hardening sites against future updates.

5 installs
▌
Algorithm Knowledge Base · cleanexpo bundle
Algorithm Intelligence Layer for Synthex. Loads curated platform algorithm knowledge to inform content strategy recommendations. Auto-invokes when generating content recommendations, explaining reach drops, reviewing posts for platform fit, or building advisor briefs. Contains signal data for Google Search, Instagram, and LinkedIn with confidence ratings.

8 installs
▌
Brand Campaign Generator · cleanexpo bundle
Synthex campaign content enforcer. NEVER open posts with "Excited to announce", use "leverage", "game-changing", or "revolutionary", produce platform-agnostic copy, or generate content that scores below 80. ALWAYS write platform-distinct hooks, use specific numbers over superlatives, and enforce exactly one CTA per piece. Activate on ANY request to create a campaign, generate posts, write social content, or launch content for a product, offer, or event.

7 installs
▌
Platform Content Adaptor · cleanexpo
Senior Platform Content Adaptor (15+ yr calibration · multi-platform native voice · algorithm-aligned formatting · brand-DNA preservation across resize). Takes one source piece (post · article · video script · announcement) and produces correctly-formatted versions for every active platform — never the same copy across platforms · LinkedIn hooks never start with "I" · Instagram hooks land in 125 chars · TikTok opens with a challenge or question. Every adaptation passes the brand-voice-enforce gate, the platform-distinct-voice rule, and the hashtag-tier discipline (broad/medium/niche mix). Reads ceo-foundation.md + verification-gates.md at every invocation.

8 installs
▌
Performance · cleanexpo
Review PR for bundle size regressions, N+1 queries, serverless function size, and render performance

9 installs
▌
Brand Consistency Checker · cleanexpo bundle
Synthex brand consistency enforcer. NEVER produce vague feedback ("sounds on-brand", "good feel", "consistent with your voice"). ALWAYS score against specific criteria: vocabulary match percentage, anti-pattern phrase count, and CTA quality. Every feedback item must be specific enough to act on immediately. Activate on ANY request to check brand consistency, audit content against brand guidelines, review voice alignment, or validate that content matches a Business DNA profile.

9 installs
▌
Test Quality · cleanexpo
Test Quality Review Specialist

7 installs
▌
Competitive Local Strategy · cleanexpo bundle
Competitor gap analysis, displacement tactics, benchmarking, citation gaps, and quarterly strategy reviews for local businesses. Use when analysing competitors, planning market positioning, or building competitive advantage in local search.

7 installs
▌
Platform Content Optimiser · cleanexpo
Senior Platform Content Optimiser (15+ yr calibration · algorithm-signal scoring · plain-English client translation · falsifiable lift framing). Scores content 0-100 against platform algorithm signals and outputs prioritised, plain-English recommendations. Uses algorithm-knowledge-base as the signal intelligence layer. Every signal name in client-facing output uses the plain-English translation from `algorithm-knowledge-base/references/signal-translations.json` — never exposes raw signal names (NavBoost · sends_per_reach etc.) to clients. Reads ceo-foundation.md + verification-gates.md at every invocation.

8 installs
▌
Accessibility · cleanexpo
Accessibility Review Specialist

8 installs
▌
Commit Hygiene · cleanexpo
Commit Hygiene Review Specialist

9 installs
▌
React Patterns · cleanexpo
Enforce React hooks rules, key prop usage, stale closure detection, effect cleanup, and render performance

10 installs
▌
Review Metrics · cleanexpo
Review Board Metrics Analyzer

5 installs
▌
Performance Attribution Lead · cleanexpo
Senior Performance Attribution Lead (15+ yr calibration). Monitors portfolio metrics across the 4-tier reporting cadence (Hyper-Care daily · Tier 1 weekly · Tier 2 monthly · Tier 3 quarterly). Renders reports from `.claude/memory/reporting-templates.md` against verification-gate state. Surfaces canary signals + threshold breaches + same-day incidents. Closes every report with explicit gate-state tags per metric, cross-funnel separation enforced, and same-day-incident bypass routing. Feeds structured metric blocks to analytics-lead via `PerformanceAttributionOutput` contract. Reads ceo-foundation.md + verification-gates.md + reporting-templates.md at every invocation.

8 installs
▌
Database Review · cleanexpo
Review queries for optimisation, missing indexes, RLS, SQL injection, and migration safety

6 installs
▌
Marketing Operations Director · cleanexpo
Senior Marketing Operations Director (19+ yr calibration). Owns operational infrastructure layer — identity resolution (L1) · ESP setup (L2) · analytics + attribution (L3) · trigger orchestration · workflow automation. Pairs with engineering on Tier B build (per `tier-b-engineering-specs.md`). Enforces cross-client boundary at the data layer · enforces privacy P-rules mechanically · enforces source-of-truth job ID at every cross-funnel touchpoint. Closes every infrastructure change with a leading-indicator threshold, a rollback procedure, and a privacy-compliance verification step. Reads ceo-foundation.md + verification-gates.md + tier-b-engineering-specs.md at every invocation.

6 installs
▌
Breaking Changes · cleanexpo
Detect API contract changes, Prisma schema breaks, component prop changes, and removed exports

9 installs
▌
Dependency Audit · cleanexpo
Audit new dependencies for CVEs, licence compliance, bundle size impact, and supply chain risk

5 installs
▌
Supabase Patterns · cleanexpo
Supabase Patterns Specialist

8 installs
▌
Typescript Strictness · cleanexpo
Enforce type safety — no unsafe casts, proper generics, strict null checks, no untracked suppressions

6 installs
▌
Synthex Orchestrator · cleanexpo
Orchestrate the brand intelligence pipeline — load clients, spawn agents, track costs, write summaries

8 installs
▌
Ceo Board Pipeline Integration · cleanexpo
CEO Board integration layer — convene 9 personas for strategic decisions within the brand intelligence pipeline

9 installs
▌
Scout · cleanexpo bundle
AI provider and model monitoring for Synthex. Detects approaching model retirements, alerts on model errors, and recommends fallback models. Use when a model call fails, a retirement is imminent, or any feature hardcodes a model name.

7 installs
▌
UI UX · cleanexpo bundle
Synthex UX enforcer. NEVER produce generic bullet-list audit reports, recite WCAG rules without grounding them in Synthex's dark glassmorphic interface, or reference pnpm (this project uses npm). ALWAYS ground findings in Synthex's #0f172a dark background, Radix UI primitive semantics, and 4px spacing scale. Activate on ANY request to audit UX, review accessibility, optimise flows, check interactions, or validate usability.

7 installs
▌
Design · cleanexpo bundle
Synthex design system enforcer. NEVER use Inter as a heading font, purple (#8B5CF6) gradients on white, or generic glassmorphism without Synthex tokens. ALWAYS use Space Grotesk headings, #FF6B35 brand orange, #0f172a slate background, and the Synthex glass token set. Activate on ANY request involving UI, components, styling, layout, visual design, colour, typography, spacing, shadows, animations, or anything a user will see on screen.

7 installs
▌
UI Review · cleanexpo bundle
Synthex UI validation agent. NEVER run generic Lighthouse audits without grounding findings in Synthex's dark glassmorphic interface. NEVER reference pnpm. ALWAYS check backdrop-filter fallbacks, focus rings against the dark background (#0f172a), and Radix UI interaction semantics. Activate on ANY request to review UI, validate a page, check a component, run a visual audit, or test a user story.

8 installs
▌
Brandprint · cleanexpo bundle
Multi-brand branding enforcer for every client-facing or branded output — invoices, reports, proposals, documents, PDFs, dashboards, canvases, decks, emails, letterheads, web pages — even when the request never says the word "brand". Resolves WHICH brand applies (synthex, dr, nrpg, ra, carsi, unite, john-coutis, or an onboarded client) and applies that brand's colours, typography, logos, voice, and layout rules from packages/brand-config. NEVER invent hex codes, fonts, or logos; never blend two brands in one output — co-branding is an explicit, separately configured mode with one owning brand.

8 installs
▌
North Star · cleanexpo
The engineering navigation layer for Synthex — holds the mission, the current course, the rules of the ship, and routes work to the right existing specialist. Load at the START of any planning, prioritisation, "what's next", roadmap, scope, or new-feature decision. NEVER let work drift off the critical path or add capabilities the ship already carries (see dependency-discipline). NEVER claim done without the verification gate. NEVER merge to production or change prod data without a human gate. ALWAYS trace a task to the NorthStar, the live Linear epic, and an existing system before writing code.

9 installs
▌
Senior Cmo · cleanexpo
Senior CMO (18+ yr multi-business operator calibration). Cross-portfolio CMO oversight role. Operates above the senior-strategist layer at the cross-portfolio P&L narrative level. Owns marketing P&L · channel mix justification · quarterly portfolio strategic review · foundation-amendment proposals. Closes every recommendation with a flywheel-position citation, a 90-day measurable target, leading + lagging indicators, a kill threshold, and a cross-portfolio re-allocation criterion. Reads ceo-foundation.md + verification-gates.md at every invocation.

9 installs
▌
API Testing · cleanexpo
Synthex API testing enforcer. NEVER mock the database in integration tests — use real Supabase. NEVER skip the 401 (unauthenticated) or 403 (wrong org) test cases. NEVER use pnpm. ALWAYS structure tests as: 401 → 403 → 400 → 200/201 happy path. Activate on ANY request to write API tests, validate endpoints, add test coverage, or check test quality.

9 installs
▌
Brand Video · cleanexpo bundle
Produce one or many consistent, on-brand faceless marketing videos end-to-end from a topic — script → ElevenLabs voiceover (with timestamps) → one styled illustration per beat via the grounded pipeline (generateImage(), auto-detect + auto-LoRA) → ffmpeg stitch to 1080p, optionally uploaded to YouTube as Unlisted. The visual LOOK is a selectable style from styles.md (flat-line, hand-doodle, bold-kinetic, cinematic-photoreal, minimal-corporate, retro-print) so the same command yields different aesthetics for different audiences. Use when the user says "/brand-video", "make a styled marketing video/reel", "another video in the <style> look", "batch of videos for <brand>", or wants consistent repeatable video output across brands (RestoreAssist, Synthex, DR, NRPG, CARSI, CCW, Unite). This is the proven, fully-automated pipeline (distinct from faceless-video's Artlist/FACT-STORY flow and video-director's motion edit).

5 installs
▌
Code Review · cleanexpo bundle
Synthex code quality enforcer. NEVER flag Synthex conventions as bugs (Australian English, Supabase-only auth, SWR with credentials:'include', selective error boundaries). NEVER suggest Redux, Zustand, tRPC, or any pattern absent from this codebase. ALWAYS enforce: useRouter from next/navigation, no window.location.href, SWR for client data fetching, { error: string } response shape. Activate on ANY request to review code, audit a PR, check a component, or validate an implementation.

9 installs
▌
Codex Local · cleanexpo
Wrapper around the Codex CLI bound to a cheap backend (DeepSeek V4 Flash via OpenRouter, or local Gemma 4 via Ollama) for code-specific tasks with diff-based UX.

10 installs
▌
Agentic Marketing Intelligence · cleanexpo bundle
Research → verify → score → plan → improve loop for SEO / AEO / GEO across the Unite-Group portfolio. Ingests Obsidian source data and (when supplied) YouTube channels, cross-verifies every claim against ≥4 sources, scores ranking opportunity / decay / freshness / GEO visibility with confidence-adjusted prioritisation, and produces human-gated site-improvement tickets. Never fabricates metrics. Orchestrates — does not duplicate — the existing google-search-console, google-business-profile, local-seo-agent, google-updates-sentinel, competitive-local-strategy and algorithm-knowledge-base skills.

10 installs
▌
Anti AI Slop · cleanexpo
Removes AI-slop from any writing before it ships — the tells that make text read as machine-generated: filler openers, hedge-everything qualifiers, rule-of-three padding, "it's not just X, it's Y" antithesis, em-dash abuse, empty transitions, and self-congratulatory adjectives. Two modes — Quick Scan (flag + score, no rewrite) and Deep Rewrite (voice-first reconstruction). Activate on ANY writing or editing task: drafting copy, emails, docs, posts, PR descriptions, marketing content, summaries, or when asked to "make this sound human", "de-slop", "tighten", or "cut the fluff".

15 installs

430 published skills · page 4 of 5