agentleFS
vcxcviivcxcvii/rainmaker/skills/what-to-target-next/SKILL.md

what-to-target-next

Skill0 starsChanged 4 months agoMITView on GitHub

Turn qualified clusters into a specific keyword plan, slotted as new, refresh, consolidate or kill, capped at the site's own authority budget.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 1 is distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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 20
  2. Very specific:

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

    line 28
  3. Very specific:

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

    line 30
  4. Very specific:

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

    line 36
  5. Distinctive:

    Only QUALIFY and CONDITIONAL verdicts enter the plan.

    line 69
  6. Very specific:

    Never assign priority_score by judgment.

    line 70
  7. Very specific:

    Every slot has a cluster id, a slot type and a CLI-sourced priority score, the plan respects the authority budget when one exists, and …

    line 86

≈ “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

what-to-target-next

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
data/strategy.json clusters, with SERP verdicts from can-i-actually-rankwhat to slotrun pick-my-battles then can-i-actually-rank first
data/snapshots/<latest>/gsc.jsonpositions and impressions per candidatecontinue at reduced confidence
data/snapshots/<latest>/crawl.jsonwhich URLs already exist, for slot classificationrun rainmaker audit
data/blueprint.jsonthe site's own authority budget, if a blueprint existscontinue without a cap, and say so

Produces

keyword_plan (owner). slot is shared with revive-old-pages.

Refuses when

A candidate has no SERP verdict at all (unchecked). Only QUALIFY and CONDITIONAL candidates from can-i-actually-rank may enter the plan; an unchecked or KILLed candidate is excluded, not silently downgraded.

Procedure

  1. For every cluster, take GSC queries whose text overlaps the head or support queries, plus any striking-distance queries from find-my-quick-wins mapped to that cluster.
  2. Assign a slot:
    • refresh when a tier-appropriate URL exists and ranks 4 to 20.
    • consolidate when 2 or more URLs compete on the query, per the same overlap rule find-my-quick-wins and revive-old-pages use.
    • new when no URL exists.
    • kill when a URL exists, ranks beyond 50, has zero clicks in two consecutive windows, and its tier is 3 or 4.
  3. priority_score comes from src/analyze/scoring.ts via the CLI; never invent it here.
  4. Cap the plan at the site's authority budget from data/blueprint.json if one exists. A plan nobody can execute is not a plan.
  5. State how many candidates were dropped for exceeding the cap, and the score of the highest dropped item, so the cutoff is visible rather than silent.

Decision rules

  • Only QUALIFY and CONDITIONAL verdicts enter the plan.
  • Never assign priority_score by judgment; it is always the score the CLI computed.
  • A kill slot always proposes a redirect target, matching revive-old-pages's rule that a kill without a redirect is a broken link.

Output

## Keyword plan

<query>: cluster <id>, slot <new|refresh|consolidate|kill>, score <x>
  target: <url or "none">

Capped at <n> slots (authority budget). Dropped <n>, highest dropped score <x>.

Done when

Every slot has a cluster id, a slot type and a CLI-sourced priority score, the plan respects the authority budget when one exists, and every kill slot names a redirect target.

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.