Unite-Hub

Apply this skill for Unite-Hub Supabase migrations, PostgREST/Data API visibility, founder-scoped Playwright journeys, or errors such as PGRST205, access=denied, stale Supabase linked refs, or migration history drift. Prevents repeating the SQL/cache/auth loop by enforcing the exact verification sequence for core journeys.

The compass for Unite-Hub's road to /shipit. Defines the single NorthStar (a real, comprehensive, working founder CRM in production, every section GREEN), the binding definition of GREEN, and the No-Invaders Manifest that keeps the build honest and surgical. Consult BEFORE deciding what to build/skip/finish — it resolves "200 ≠ real" temptations and scope-creep pressure. P1, auto-loaded.

Apply this skill WHEN scaffolding a new cron "pull" route that syncs external/derived data into Supabase on a schedule (Vercel cron). Encodes the Unite-Hub cron invariants: CRON_SECRET auth, FOUNDER_USER_ID actor, overlap safety, idempotent upsert, last-sync timestamp, and failure surfacing. Generic `cron-scheduler` covers scheduling; this covers the PULL handler body. P3.

Apply this skill WHEN verifying that a route, page, or integration serves REAL data and not silent mock/placeholder data. Detects the "false-green" failure mode: an endpoint returns 200 (or a page renders) while the underlying data is fabricated because a provider is unconnected. Trigger WHENEVER classifying a section's readiness, reviewing integration wrappers, or before marking anything GREEN. P2 — load on audit/verify tasks.

Manifest-first context isolation — each subagent receives only its scope, never the full codebase

Apply this skill for ANY decision with non-obvious tradeoffs: architectural choices, debugging without a clear root cause, performance strategies, security decisions, feature design with competing constraints, refactoring scope decisions. Forces multi-perspective analysis before committing to a solution. P1 auto-load — always active on complex reasoning tasks.

Apply this skill before executing ANY irreversible action: bash commands that delete, reset, or overwrite; database migrations; git destructive operations (push --force, reset --hard, branch -D); environment variable changes; deployment triggers. Apply before proposing solutions when requirements are ambiguous. Blocks unsafe execution defaults. P1 auto-load — always active.

Autonomous task completion loop with PRD tracking and persistent progress memory

Apply this skill for ALL UI work in Unite-Group: components, pages, layouts, Tailwind classes, design decisions, CSS, visual styling, colour choices, spacing, typography. Also apply when reviewing or auditing existing UI, suggesting improvements, or building anything that will be rendered in a browser. If there is any visual or interactive element involved, this skill applies.

Apply this skill before creating new files, new abstractions, new dependencies, new API routes, new database tables, or new components. Detects architectural drift, complexity accumulation, and pattern violations before they get committed. Also applies when reviewing existing code for structural issues. P1 auto-load — always active when the system structure changes.

[REQUIRED — This is what Claude reads to decide whether to apply the skill] Apply this skill for ANY [exhaustive list of scenarios where this applies]. Trigger verbs: ANY, BEFORE, WHEN, AFTER. Be specific — vague descriptions cause missed triggers. End with: "[Priority context]. [Auto-load statement if P1]."

Hard verification gate — no task is complete without proof it works (Next.js/Supabase stack)

Route complex requests to the right specialist agent or chain of agents. Central brain of the agent swarm — analyses what the user needs, determines which specialist domain(s) are required, and coordinates parallel or sequential agent execution. Use when a request spans multiple domains, when deciding which specialist should handle an ambiguous request, or when a task requires a multi-step pipeline across different skills. Triggers on: multi-step requests, cross-domain tasks, "coordinate", "plan this out", "I need help with multiple things", or any complex request that touches more than one specialist area.

Type-safe fetch wrapper with interceptors, retry, and error normalisation for Next.js API clients

Typed API contract patterns enforcing consistency between Next.js API routes (Zod request/response schemas) and frontend consumers. Covers schema location conventions, error response contracts, and versioning strategy.

Structured audit event logging for compliance, forensics, and activity tracking — 7-year retention per Privacy Act 1988

Act as a brand ambassador — create authentic, platform-specific social media content that embodies a brand's identity and connects with audiences. Use when asked to "create social media content for a brand", "act as a brand ambassador", "write ambassador posts", "promote [brand] on social media", "create influencer-style content", "write authentic brand content", or any request involving representing a brand through social content. Triggers on: ambassador voice, brand promotion posts, UGC-style content, or when someone wants social media content that sounds like a real person recommending a brand rather than corporate marketing copy. Especially relevant for Synthex AI social content pipeline and the 7 businesses in the Unite-Group network.

Orchestrates 9-persona CEO Board deliberation for strategic business decisions, with persistent agent expertise files

">"

">"

Use when facing 2+ independent failures or tasks that can be worked on concurrently without shared state. Groups independent failures by component (frontend/backend/database), launches concurrent agents, integrates results, then runs full test suite. Triggers on multiple independent test failures, multi-component CI failures, or parallel feature work.

">"

">"

End-of-feature workflow for development branches. Verifies tests pass, generates PR description, chooses merge strategy, cleans up worktrees, and manages branch lifecycle. Triggers on "create PR", "merge", "finishing", "branch cleanup", "ready to merge", or at end of feature work.

Creates isolated git worktrees for feature development with automatic dependency installation, baseline test verification, and .gitignore safety checks. Extends the /minion isolation model with a formal worktree workflow. Triggers on "new feature", "isolate", "worktree", multi-session work, or when parallel development is needed.

Plain-English pipeline from idea to production — routes user requests to the right phase and agent

">"

Notebook First retrieval policy — query NotebookLM notebooks before web search or context dumping

OAuth 2.0 and OIDC integration with PKCE, Supabase Auth providers, and redirect URI validation

">"

Act as a Senior Project Manager with 15 years of SaaS delivery experience — advising, creating deliverables, and managing the full lifecycle from discovery through renewal. Triggers on: project plan, implementation plan, sprint planning, risk register, stakeholder update, SOW, resource plan, go-live, project charter, retrospective, change request, escalation, budget tracking, RACI, governance, release plan, data migration, QA strategy, UAT, cutover, capacity planning, velocity, burndown, kickoff, lessons learned, or any request involving running a SaaS project. Also triggers on "we're behind schedule", "the client is unhappy", or "how should I run this project?"

Use when encountering any bug, test failure, or unexpected behaviour, before proposing any fixes. Four-phase root-cause protocol with hard 3-attempt circuit breaker. Enhances the bug-hunter agent with structured investigation. Triggers on "bug", "error", "failing", "crash", "debug", "broken", "why isn't", "not working".

Use when implementing any feature or bug fix. Hard gate — no production code without a failing test first. Applies to vitest (apps/web/) and pytest (apps/backend/). Triggers on "implement", "add feature", "fix bug", "new component", "new endpoint", or any code-writing task.

">"

Hybrid DAG execution primitive combining deterministic and agentic nodes with hard iteration caps

Claude Chrome extension tools for personal browser automation in the user's actual browser. Use for logged-in sessions, form filling, and interactive tasks.

Mathematical first principles validation for code quality. Triggers on "optimise", "algorithm", "performance", "complexity", "O(n)", or when reviewing code for efficiency. Enforces Turing (algorithmic), Von Neumann (architecture), Bezier (animation), and Shannon (compression) principles.

Scheduled task management patterns for Vercel cron jobs, Next.js API route handlers, and backend periodic tasks. Covers cron expression conventions, CRON_SECRET authentication, overlap protection, timezone handling (AEST/AEDT), and failure alerting.

Streaming CSV parse and generate patterns for large file support across Next.js frontend and FastAPI backend. Covers row-by-row streaming, Zod row validation, Pydantic export models, Australian locale formatting (DD/MM/YYYY dates, AUD currency), and memory-safe chunked processing.

Real-time dashboard patterns codifying the project's Status Command Centre component library, timeline/orbital layout, Supabase Realtime integration, and Scientific Luxury design enforcement for all data visualisation surfaces.