The plumbing under Stage 3: list, publish, audit and configure schema across hundreds of personal brand sites. The two-credential model, the Elementor trap, and the stale-cache failure that hid 18 live sites.
The Meta Ad Agent — One Skill, Many Clients
A plumber, a roofer, a course creator and a coach get the same agent, parameterized by a client profile. The prime directive, the low-volume design, the money guardrails, and the runnable skill file.
Fleet Uptime Monitor — A Green Result Is Only Trustworthy If the List Was Current
150 sites returned 500 and nothing noticed. Then the monitor built to catch it passed 18/18 while a 111-day-stale roster hid 18 live sites. Both incidents, the probe design, and the runnable skill file.
The Positioning Strategist — Name It Before You Build It
Buy box, passion, and the one sentence only you can sign. Step 1 of the personal-brand method, the swap test that validates it, four worked examples, and the runnable skill file.
The Repurposer — The Daily Channel Watchdog
Someone records on YouTube and their websites never find out. The daily watch loop, the SKIP/LIGHT/MODERATE/STRONG triage, the A− publish bar, and the runnable skill file.
The Publisher — Every Skill Has a Webpage
A skill that exists only as a file is invisible. The rule, the three artifacts, the definitive-article pattern, and the runnable skill file.
The RACI Enforcer — Dennis Is Never R or A
Every project at Local Service Spotlight gets a young adult as its owner. Dennis is Consulted or Informed — never Responsible, never Accountable. The skill file that enforces it, plus the repair pass for projects that already drifted.
The Definitive Guide to Claude Scheduled Jobs: The Agents That Work While You Sleep
Skills are books. Scheduled jobs are employees. SKILLS the documented method ACCESS connectors & passwords GOALS your GCT brief SCHEDULE cadence & trigger ONE WORKING AGENT — YOUR NEW HIRE runs unattended · reports back · never forgets a week HIRE SIX OF THEM = YOUR AI OPERATING TEAM chief of staff · publicist · security guard · analyst · …
Every Place to Inventory Your Podcast So LLMs Cite You (and Why the Ahrefs Numbers Lie)
The Podcast Citation Flywheel 1. APPEARguest on shows 2. INVENTORY5+ platforms 3. CLAIMverify via X 4. PUBLISHappearances page 5. SYNDICATEWikidata · panels LLM CITATIONSChatGPT · Grok/Grokipedia · Gemini · AI Overviews · Perplexity more citations →more authority →more bookings →the loop compounds Every platform that states the same facts about youis one more consistent source an LLM can retrieve and …
Content Factory AI Capability Index
Content Factory • Methodology v0.1 A task’s “AI vulnerability” is not one number. We need to know what AI can execute, what still requires a human owner, how much of the workflow is exposed to automation, and whether the task is documented well enough to test. The Content Factory AI Capability Index turns the Task Library into a living evaluation …
The changelog that proved nothing
Our Task Library dashboard promised that every run appends an entry to its changelog. On August 1, 2026 the monthly refresh found the panel held exactly one record, dated June 10 — with a correct daily date stamped directly above it.
How to Set Up a Basecamp Project for a New Client
Every client we take on gets a Basecamp project, and it exists before they ever talk to us again. The reason is simple. Whatever isn’t written down in a shared place lives in somebody’s head or somebody’s inbox, and that’s where work goes to die. Six months later nobody can tell what was promised, what was delivered, or who dropped …