agentleFS
vcxcviivcxcvii/rainmaker/skills/put-it-on-autopilot/SKILL.md

put-it-on-autopilot

Skill0 starsChanged 4 months agoMITView on GitHub

Generate GitHub Actions workflows for the recommended cadence, calling `rainmaker routine` and `rainmaker report`, and print the exact secrets the user needs to set before the workflow can run.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 4 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run rainmaker context --check first.

    line 21
  2. Very specific:

    Only the data/ files listed in this skill's Consumes table.

    line 29
  3. Very specific:

    If strategy.json.context_hash does not match the current hash of context/business.md, say exactly:

    line 31
  4. Very specific:

    If context/business.md carries confidence: stub, continue, and stamp every output with: "Built on a stub context.

    line 37
  5. Distinctive:

    Never assume the cadence; present the recommendation and let the user confirm or override before writing any workflow.

    line 57
  6. Very specific:

    Verify every secret the workflow needs is documented in the README's credentials section, and print the exact gh secret set commands.

    line 59
  7. Distinctive:

    Never re-check anything faster than its own verification window.

    line 66
  8. Distinctive:

    Never schedule a workflow whose secrets are undocumented.

    line 67
  9. Distinctive:

    Never activate a paid provider because its secret exists.

    line 68
  10. Very specific:

    Never emit if: ${{ secrets.NAME != '' }}.

    line 69

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

put-it-on-autopilot

Context load

Run rainmaker context --check first. It prints what exists, what is stale, and exits 1 if anything this skill requires is missing.

Then read, in this order:

  1. context/business.md in full. If absent, stop: "No business context. Run rainmaker audit, then the know-my-buyer skill."
  2. context/voice.md if this skill writes prose. If absent, stop and say so.
  3. context/glossary.md if this skill names products, features or competitors.
  4. data/strategy.json if this skill reads or writes strategy.
  5. Only the data/ files listed in this skill's Consumes table. Never crawl or call an API the core already covers.

If strategy.json.context_hash does not match the current hash of context/business.md, say exactly:

"Business context was edited after the strategy was written. Re-run know-my-buyer, or run rainmaker context --sync to accept the prose as authoritative."

Then stop.

If context/business.md carries confidence: stub, continue, and stamp every output with: "Built on a stub context. Nothing in it came from a buyer. Run know-my-buyer to replace it."

Consumes

FileWhyIf missing
rainmaker.config.ymlsite shape (URL count, publish rate), to recommend a cadencerequired
.env.examplewhich secrets the workflow will needpresent in every install

Produces

.github/workflows/weekly.yml, .github/workflows/monthly.yml.

Procedure

  1. Determine site shape from the latest crawl and GSC snapshot: URL count, clicks per month, and recent publish rate.
  2. Recommend a cadence from spec/agent.md section 5:
    • Under 50 URLs or under 100 clicks/month: no weekly job, monthly audit and report, quarterly strategy review only if drift fires.
    • 50 to 500 URLs: weekly pulse (fetch plus audit --refresh), monthly full audit, report, off-site scan, AI probes.
    • Over 500 URLs or publishing 4+ pages a month: full routine weekly, monthly report and off-site scan, ledger --compact.
  3. Never assume the cadence; present the recommendation and let the user confirm or override before writing any workflow.
  4. Generate the workflow calling rainmaker routine (weekly) and rainmaker report --window month plus rainmaker ledger --compact (monthly).
  5. Verify every secret the workflow needs is documented in the README's credentials section, and print the exact gh secret set commands. Never write a workflow depending on a secret the user has not been told to create.
  6. AI citation probes are scheduled monthly, never weekly: they cost money per run and the answers are non-deterministic, so a weekly line would mostly measure sampling variance.
  7. Built-in crawl is the workflow default. Include --provider firecrawl or --provider contextdev only after the user explicitly approves that provider and its quota or cost.
  8. GitHub Actions does not allow secrets.* directly in a step if:. Map an optional secret into job-level env, then test env.NAME != '' in the condition.

Decision rules

  • Never re-check anything faster than its own verification window. A weekly ranking report on a 40-page site reports noise as news.
  • Never schedule a workflow whose secrets are undocumented.
  • Never activate a paid provider because its secret exists.
  • Never emit if: ${{ secrets.NAME != '' }}. Use a job-level environment variable and if: env.NAME != ''.
  • The cadence is a recommendation the user confirms, never a default silently applied.

Output

## Recommended cadence

Site shape: <n> URLs, <n> clicks/month, publishing <n> pages/month
Recommendation: <weekly / monthly-only / full weekly>, because <reason>

Confirm, or tell me what to change.

## Workflows written
.github/workflows/weekly.yml
.github/workflows/monthly.yml

## Secrets still needed
gh secret set FIRECRAWL_API_KEY --repo <repo>
gh secret set GOOGLE_APPLICATION_CREDENTIALS --repo <repo>

Done when

The cadence was confirmed by the user before anything was written, both workflow files validate, and every required secret was printed with its exact gh secret set command.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.