email-triage
Skill0 starsChanged 6 days agoMITView on GitHub
Use when building or operating an agent email triage loop that turns recent inbox messages into prioritized, source-linked actions without duplicating project-specific rules across agents.
13 other projects use a version of this.
Adopted by
Most recently taken up by
- larchanka/skillstheir own version, first seen Nov 8, 2026
- juliasadler/muse-skills-cntheir own version, first seen Oct 17, 2026
- mariagorskikh/open-instincttheir own version, first seen Oct 14, 2026
- Johnwang688/jarvistheir own version, first seen Oct 13, 2026
- Magnus-Gille/claude-skillstheir own version, first seen Oct 11, 2026
- joelhooks/joelclawtheir own version, first seen Oct 8, 2026
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- gnekt/My-Brain-Is-Full-Crew★ 3.9ksame name
- mariagorskikh/open-instinct★ 428same name
- joelhooks/joelclaw★ 65same name
- larchanka/skills★ 50same name
- Magnus-Gille/claude-skills★ 5same name
- MoeenNehzati/famulus★ 4same name
- megandmartin/agent-skills-repo★ 3same name
- juliasadler/muse-skills-cn★ 1same name
- leonardoaraujosantos/my_ai_skills★ 1same name
- huifeideyu-1121/email-triage★ 0same name
3 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository108 other files it gives its agents.
- adaptive-estimationSkill
- adaptive-loop-budgetingSkill
- adopt-and-deleteSkill
- adversarial-reviewSkill
- agent-drives-uiSkill
- agentic-coding-loopSkill
- agent-otel-trajectorySkill
- agents-as-iac-modulesSkill
- ascii-ui-mockupsSkill
- authoring-html-emailSkill
- authoring-skills-vs-mcpSkill
- batched-ssh-enumerationSkill
- c4-architectureSkill
- challenge-the-premiseSkill
- codegraph-bootstrapSkill
- codegraph-worktree-startupSkill
- colocated-pod-tolerationsSkill
- command-creatorSkill
- complexity-budgetsSkill
- connector-readinessSkill
- context-anchored-patchingSkill
- continuous-issue-resolutionSkill
- credential-proxySkill
- criticality-tiered-reportingSkill
- data-connector-buildingSkill
- declarative-firstSkill
- disk-pressure-forensicsSkill
- early-return-over-elseSkill
- enums-codify-behaviorSkill
- ephemeral-workspace-lifecycleSkill
- event-sourcingSkill
- evidence-claim-boundariesSkill
- exhaustive-matchSkill
- feature-coverage-not-just-line-coverageSkill
- full-disk-forensicsSkill
- gate-before-pushSkill
- github-pr-shepherdingSkill
- graceful-shutdown-stateful-agentsSkill
- grounded-generationSkill
- iac-incident-responseSkill
- iac-not-ad-hocSkill
- instrumented-service-scaffoldSkill
- interface-over-conditionalsSkill
- knowledge-routingSkill
- lean-on-oss-standardsSkill
- live-money-disciplineSkill
- live-state-verificationSkill
- loop-governance-and-learningSkill
- low-level-executor-task-specSkill
- map-dispatch-over-conditionalsSkill
- merge-conflict-disciplineSkill
- mermaid-diagramsSkill
- oke-arc-runners-opentofuSkill
- orchestrate-agySkill
- orchestrate-claudeSkill
- orchestrate-codexSkill
- orchestrate-geminiSkill
- otel-emit-at-willSkill
- parameter-designSkill
- parse-dont-validateSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Read the canonical mail source with its supported API or local archive, using read-only access unless the task explicitly requires state …
- Distinctive: line 40
When a local script teaches you a better filter or category, promote the generic rule here and leave only the local values in configuration.
- Distinctive: line 47
Do not paste full private email bodies into logs, issues, or pull requests.
“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Email Triage
Email triage is a shared construct, not a per-agent script habit. Keep one audited workflow for how agents read mail, classify it, log what was seen, and promote reusable filters back into the shared source of truth.
Operating Contract
- Read the canonical mail source with its supported API or local archive, using read-only access unless the task explicitly requires state changes.
- Query a bounded recent window first. Prefer targeted queries by sender, subject, list identifier, labels, and age over scanning a full mailbox.
- Normalize each message into a small record: stable message id, date, sender, subject, labels/read state, source mailbox/archive, and a durable link or id.
- Deduplicate by stable message id before classification.
- Classify into action categories that match the agent's remit, such as failed automation, security alert, review request, team message, customer escalation, or informational update.
- Sort by severity first, then unread/actionable state, then recency.
- Fetch bodies only for the smallest actionable set, and extract concise evidence lines instead of copying whole emails.
- Append a triage summary to the durable log or wiki with counts, categories, message ids or links, and the next action for each actionable item.
Centralization Rule
- Reusable triage behavior belongs in this skill or a companion shared skill.
- Project-specific sender lists, labels, keywords, and escalation owners belong in configuration or memory, not hard-coded in each agent script.
- Long-lived architecture notes belong in the wiki or docs and should point to this skill for behavior.
- Config files should contain only a thin pointer to this skill, not a copied triage procedure.
When a local script teaches you a better filter or category, promote the generic rule here and leave only the local values in configuration.
Evidence Discipline
- Preserve message ids and source locations so another operator can re-check the same email.
- Do not paste full private email bodies into logs, issues, or pull requests.
- Redact personal data unless it is required for the task and allowed by the destination.
- Log negative runs too: the absence of actionable mail is operational evidence when it includes the query window and source.
Failure Handling
- Authentication failure: report the credential or consent surface that failed, then stop before changing mail state.
- Query failure: record the query, status code, and first diagnostic clue.
- Parser failure: keep the raw message id and headers, then quarantine the body handling bug for a focused fix.
- Ambiguous relevance: classify as informational and capture why it was not escalated.
Done Standard
An email triage run is done only when the durable log names the source, query window, counts by category, highest-priority actionable items, and either the next owner/action or a clear "no actionable mail" 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.

