Local Service Spotlight Content Factory

Local Service Spotlight Task Library

Use these guides to save time on work that helps your business grow. Pick one job, give AI the right facts, and check what it makes. Start with one draft you can review.

1. Pick a job Find its guide 2. Give it facts Use the firstprompt 3. Check the work Save proofand next steps
A guide gives the steps. You choose the job and check the result.

New here? See how to start one job. The ZIP includes START-HERE.md.

Library counts and other downloads

SOPs. Their article mappings resolve to hubs: catalog-ready and in progress. A Definitive marker also requires review of the actual page.

Last updated:
Reported guide status

Start one job

  1. Pick the result you need. Search the tasks above. Open a guide and choose “Copy first-run prompt.” Paste it into the AI app you use, then add your business facts.
  2. Give it what the job needs. Add the files named in the guide. Connect an account only if the task needs it. Ask the AI to name any missing file or access before it starts.
  3. Try once and check the result. Start with a draft. Use the guide’s checklist, open the output, and save the proof and next step. A downloaded file has not done the job.
  4. Set repeats only if needed. After one run works, agree on a time, time zone, where it will run, and who gets the result. Check that the first timed run really happened. See setup and access steps.

A skill is a written recipe; a pack groups recipes. A plugin is a package an app can load. An agent is the AI worker that uses them. This ZIP is a set of guides. Use the install guide for a supported app package.

What do the status labels mean?

“Reported complete” is the contributor’s saved label. It does not prove that we checked every part of the guide. It also does not mean a skill is installed, an account is connected, a job has run, or a business result was reached. Each needs its own evidence. Missing evidence stays unknown.

Every real run gets a meta article: a record of the work and its proof. Run records link to the recipe so we can improve it. Rechecking or editing the same run does not add a new run.

The line, not a list

Content Factory — four phases

The Content Factory turns real stories into content that can help your business. Produce: gather the source. Process: shape it. Post: publish it. Promote: share what works. Setup and support tasks help these stages. Click a stage to find its tasks; read each guide for the actual inputs and next step.

⭐ The engine

Use each run to improve the guide

Use each real run to check the recipe. Record what happened, including failed or blocked work, then review any lesson before changing the shared instructions. Writing the run record is required; public release needs its own authority.

Dorun the task 📝Checkactual result Writerun record 📰Linktask + run ID 🔁Reviewrecipe change learn from evidence

DoCheck the resultWrite the run recordLink the taskReview the lesson

One maintained recipe explains a repeatable task. Each actual execution gets a meta article: a written account of its steps, evidence, result, and next handoff. Keep the same execution ID across revisions and retries. A written draft is a valid record while public release is pending.

If a run reveals a useful lesson, propose a change to the recipe and review the evidence. The next execution tests an accepted change. A failed run, an unresolved gap, or no justified recipe change can be the honest result.

  • One maintained recipe — the task records link their current instructions. Keep missing inputs, checks, and evidence visible as gaps.
  • Check the actual outcome — compare the observed result with the recipe’s acceptance checks. Record completed, partial, failed, or blocked work honestly.
  • Write every execution — save the factual meta article and link its task and execution ID, including failed or blocked work. Publication is a separate step.
  • Review each lesson — change the shared recipe only when evidence supports the change and review accepts it.