agentleFS
vcxcviivcxcvii/rainmaker/skills/revive-old-pages/SKILL.md

revive-old-pages

Skill0 starsChanged 4 months agoMITView on GitHub

Classify every URL with search history into refresh, rewrite, consolidate or kill, excluding anything still inside its own shipped verification window so a fix is never judged before it has had time to work.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 2 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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 22
  2. Very specific:

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

    line 30
  3. Very specific:

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

    line 32
  4. Very specific:

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

    line 38
  5. Very specific:

    Prefer refreshing a cluster below 80 percent completeness (per map-my-site) over starting a new one, when both are viable options for the …

    line 67
  6. Distinctive:

    Every URL gets exactly one classification.

    line 71
  7. Very specific:

    Never classify a page still inside its verification window.

    line 72
  8. Distinctive:

    Every URL with history has exactly one classification or sits in "pending", every kill names a redirect target, and nothing inside its own …

    line 98

≈ “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

revive-old-pages

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/snapshots/<latest>/gsc.json (2+ snapshots)position and impression history"Need at least two Search Console snapshots. Run rainmaker fetch --source gsc again after 28 days."
data/snapshots/<latest>/crawl.jsonword count, links, canonical statusrun rainmaker audit
data/ledger.jsonlwhat was already shipped and its verification windowrun rainmaker ledger --rebuild
data/blueprint.jsoncluster completeness, to prioritise refreshing under-covered clustersoptional

Produces

Classification report; keyword_plan[].slot (shared owner with what-to-target-next).

Refuses when

Fewer than two GSC snapshots exist. A single snapshot has no movement to classify against.

Procedure

  1. Classify every URL with GSC history into exactly one of:
    • refresh: position declined 3 or more places, impressions still above 100, tier 0 to 2, over 600 words.
    • rewrite: impressions fell 50 percent or more across two windows, cluster still validated.
    • consolidate: competes with another URL on a query, per the shared overlap detector, holding the smaller impression share.
    • kill: tier 3 or 4, zero clicks across two consecutive windows, no inbound links from tier 0 to 2, no proof cited on the page.
  2. Join to ledger.jsonl: exclude any page shipped inside its own verification window from src/ledger/types.ts VERIFICATION_WINDOWS. Judging a fix before its window closes manufactures noise, and this is the same rule the ledger itself enforces on shipped to verified.
  3. Rank by the score of the corresponding cluster.
  4. For every kill, state the proposed redirect target. A kill without a redirect target is a broken link, not a cleanup.
  5. Prefer refreshing a cluster below 80 percent completeness (per map-my-site) over starting a new one, when both are viable options for the same effort budget.

Decision rules

  • Every URL gets exactly one classification. A page that could plausibly be two things is resolved, not left ambiguous.
  • Never classify a page still inside its verification window; report it separately as "pending", matching the ledger's own pendingVerification.
  • A kill always names its redirect target.

Output

## Content decay report

refresh (<n>):
  <url>: position <before> to <after>, <impressions> impressions

rewrite (<n>):
  <url>: impressions down <n>%, cluster status <validated|hypothesis>

consolidate (<n>):
  <url>: competes with <url>, keep the larger impression share

kill (<n>):
  <url>: 0 clicks over 2 windows, redirect to <target>

pending verification (<n>, excluded from the above):
  <url>: shipped <date>, window closes <date>

Done when

Every URL with history has exactly one classification or sits in "pending", every kill names a redirect target, and nothing inside its own verification window was judged.

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.