list-hygiene-judge
Skill97 starsChanged 35 days agoApache-2.0View on GitHub
Decide and record conservative contact-consent transitions from bounded engagement, bounce, and consent evidence before any send.
In this repository94 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- runxSkill
- adopt-skillSkill
- agencySkill
- answer-from-docsSkill
- attention-reviewSkill
- audit-receiptSkill
- brand-voiceSkill
- business-opsSkill
- chargeSkill
- chief-of-staffSkill
- cold-outreachSkill
- content-pipelineSkill
- contract-drafterSkill
- conversation-replySkill
- conversation-reviewSkill
- crm-cleanupSkill
- cve-auditSkill
- data-storeSkill
- data-subject-requestSkill
- deep-researchSkill
- diagnose-skill-runSkill
- dispute-respondSkill
- ecosystem-briefSkill
- extractSkill
- ghostwriteSkill
- github-pr-commentSkill
- github-pr-reviewSkill
- github-syncSkill
- google-analyticsSkill
- google-calendarSkill
- google-search-consoleSkill
- governed-outboundSkill
- helpdeskSkill
- incident-commanderSkill
- issue-intakeSkill
- issue-to-prSkill
- issue-triageSkill
- knowledge-routerSkill
- lead-enrichmentSkill
- lead-qualifySkill
- least-privilegeSkill
- ledgerSkill
- marketplace-invokeSkill
- meeting-followupSkill
- mock-chargeSkill
- mock-paySkill
- mock-refundSkill
- moltbookSkill
- n8n-handoffSkill
- nitrosendSkill
- nws-weather-forecastSkill
- open-meteo-weather-forecastSkill
- operator-inboxSkill
- ops-deskSkill
- organic-growthSkill
- policy-authorSkill
- postmortem-makerSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill after collecting current contact evidence and before preparing a campaign.
- Very specific: line 44
Only re_permission and suppress can create transitions.
- Very specific: line 60
Every result therefore keeps downstream_send.status at not_run and names send-as as the separate delivery boundary.
- Distinctive: line 73
If the ledger version changes before the decision, run again with a fresh read and fresh evidence.
- Distinctive: line 92
Never invent engagement, bounce, consent, or version evidence.
- Distinctive: line 93
Never relax suppression from contact age alone.
- Distinctive: line 94
Never re-permission an unsubscribed contact automatically.
- Distinctive: line 95
Never describe an internal ledger append as a provider update.
- Distinctive: line 96
Never dispatch, send, or claim delivery from this result.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
List Hygiene Judge
Use this skill after collecting current contact evidence and before preparing a campaign. It decides whether a contact remains eligible, needs re-permission, must be suppressed, or needs human review. When policy justifies a state transition, it records that decision in the operator's consent ledger with optimistic concurrency and verifies the exact event through a second read.
This skill never sends a message and never mutates a mailing provider. A later
send-as run must read the current consent state again at delivery time. The
ledger records the operator's policy decision; it does not replace provider
unsubscribe or bounce data.
Composes
<!-- Generated from the native execution closure; run pnpm core-skills:composes:generate. -->data-store#append_eventdata-store#read_projection
Operating model
The caller supplies one bounded engagement observation, the current consent
observation, and the policy threshold that applies to the contact. The evidence
must be marked read and versioned to the same ledger head that the runner
reads through data-store's read_projection runner. Missing, stale, ambiguous, or conflicting
evidence produces human_review without a write.
The deterministic decision order is conservative:
- An unsubscribe marker stops automation.
- An existing suppression is preserved; age alone can never relax it.
- Verified hard-bounce evidence suppresses when policy permits that automatic action, otherwise it stops for review.
- A subscribed contact whose last engagement exceeds the decay threshold is
moved to
re_permission. - A clean, recent subscribed contact returns
verifywithout writing.
Only re_permission and suppress can create transitions. The append uses the
observed ledger version and the caller's stable idempotency key. Readback must
match the append status, source identity, new version, event reference, event
digest, and projection digest before the result reports a recorded transition.
No-write decisions also perform a second read and require the projection to
remain unchanged.
Authority and finality
The runner requests runx:data:read and, only for an admitted transition,
runx:data:append. These scopes authorize a bounded consent-ledger operation;
they do not authorize delivery or changes to a CRM or mailing provider. The
data-source binding owns storage and credentials.
A sealed result proves the ledger reads and any exact recorded transition. It
does not prove provider state, re-subscription, campaign approval, or delivery.
Every result therefore keeps downstream_send.status at not_run and names
send-as as the separate delivery boundary.
Decisions and recovery
verify: current evidence supports no transition. Nothing is appended.re_permission: engagement has decayed past policy and a subscribed contact must regain permission before sending. The transition is recorded once.suppress: hard-bounce evidence requires suppression, or an existing suppression is preserved. A write occurs only when state actually changes.human_review: evidence or policy cannot safely support automation. Nothing is appended.
If the ledger version changes before the decision, run again with a fresh read and fresh evidence. Reuse an idempotency key only for the identical transition. The runner deliberately makes no claim that a post-commit retry can recover from the old expected version; inspect the receipt and current ledger before deciding whether another operation is needed.
Inputs and result
Provide the logical data source, consent-ledger resource, contact aggregate, observed version, stable transition key, bounded engagement counts and recency, bounce policy, and current consent evidence. Counts must be non-negative and the policy threshold must be between 1 and 3,650 days.
The result preserves the decision and reason, the observed consent state, the readback-bound transition identity when one was written, a human escalation only when review is required, and the untouched downstream send boundary.
Agent rules
- Never invent engagement, bounce, consent, or version evidence.
- Never relax suppression from contact age alone.
- Never re-permission an unsubscribed contact automatically.
- Never describe an internal ledger append as a provider update.
- Never dispatch, send, or claim delivery from this result.
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
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.

