personal

Task lifecycle: new-task (BA authoring + contradiction gate + Gherkin), requirements, plan-task, task-review, debug, qa skills + architect, debugger and requirements-analyst subagents.

8 skills · 3 agents

content-writer and fact-checker subagents + social-post, linkedin-post-writer, humanizer and remove-ai-marks skills: one idea into platform-native posts for LinkedIn, Threads, X, Instagram; EN/UK, owner's voice, fact-checked, humanized, and stripped of AI provenance marks.

4 skills · 2 agents

Selling and retention design: conversion-review, paywall-and-pricing, habit-loop, landing-builder and ux-copy skills + conversion-reviewer subagent. Honest by default (no dark patterns), every finding names the event that proves it.

5 skills · 1 agent

Per-stack reviewer subagents: Python/FastAPI, web (Vite/React/TS), SwiftUI, and ML pipeline (LORO gate, FEATURE_COLS sync, leakage).

4 agents

Apple-grade UX and the toy feel: delight-spec (spring, haptic and motion tokens with CSS and SwiftUI snippets), hig-review, and the design-first redesign orchestrator (5-6 directions, design system, screens, then plan) + hig-reviewer subagent.

3 skills · 1 agent

Business growth subagents: aso-optimizer (App Store), growth-analyst (funnel/conversion), outreach-writer (partnership and consulting pitches).

3 agents

Fly.io ops runbooks: deploy (with release_command gotcha), fly-logs, incident triage.

3 skills

Language servers: Python (pyright), TypeScript, Swift. Binaries installed per machine, see SETUP.md.

LSP

ML pipeline skills: feature-change (training/serving schema contract + leakage check), model-eval (multi-season leave-one-out regression gate), ship-model (snapshot, registry, artifact publish, cache flush, rollback). Pairs with the ml-reviewer subagent.

3 skills

Daily rhythm skills: morning (kickoff recap) and evening (wind-down with tomorrow's top 3, wellbeing and social suggestions).

2 skills

Blocking safety hooks: destructive Fly.io/prod-DB ops, force-push to main, AI attribution in commits, secrets/PII in staged and pushed diffs.

1 skill · hooks

report-builder subagent + weekly-report skill: business reports, decks, and consulting deliverables with charts.

1 skill · 1 agent

seo-strategist subagent + seo-audit skill: keyword research through technical, programmatic, and LLM SEO (AI Overviews, ChatGPT/Perplexity citability).

1 skill · 1 agent

Claude's own plumbing: gmail-sorter-setup (a daily cloud routine that triages the logged-in account's Gmail) and the /switch command for moving a session between claude.ai profiles.

1 skill · 1 command

app-factory skill: one spoken idea to a submitted App Store build. Requirements, architecture, Xcode scaffolding, implementation, review, simulator QA, screenshots, App Store Connect metadata, TestFlight and submission.

1 skill

Publication-safety review for personal-brand content: legal-reviewer subagent (contract / NDA / defamation / disclosure risk) + the employer-safety filter.

1 agent

Non-blocking coaching hooks: per-stack nudges on edit (Python/TS/Swift, FEATURE_COLS sync, no em-dashes in UI text), session banner, failure hints, uncommitted reminder.

hooks

Background monitors: live TypeScript build errors and local dev-server [ERROR]/[WARN], idle-safe outside matching repos.

1 skill

Fix-and-verify review that fixes code smells, security, scalability, and performance issues before any git push.

1 skill

researcher subagent: delegable multi-source research with claim verification and cited briefs.

1 agent

MCP server catalog (example): GitHub, Playwright, Postgres. Copy .mcp.json.example into a project and fill credentials.