email-triage
Skill4 starsChanged 4 months agoMITView on GitHub
Use when the user asks for inbox-level email triage or processing. Do not use for ordinary email access, sending, or analysis of a single message.
13 other projects use a version of this.
Adopted by
Most recently taken up by
- selamy-labs/agent-skillstheir own version, first seen Nov 8, 2026
- 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
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
- megandmartin/agent-skills-repo★ 3same name
- juliasadler/muse-skills-cn★ 1same name
- leonardoaraujosantos/my_ai_skills★ 1same name
- huifeideyu-1121/email-triage★ 0same name
- Johnwang688/jarvis★ 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 repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- bib-auditSkill
- bootstrap-dispatcher-runtimeSkill
- ci-debugSkill
- cloud-filesSkill
- connect-googleSkill
- daily-planSkill
- distill-to-ruttersSkill
- email-clientSkill
- find-handoff-candidatesSkill
- formal-prose-reviewSkill
- get-weatherSkill
- git-workflowSkill
- hook-makerSkill
- initialize-tddSkill
- install-launchersSkill
- latex-workshopSkill
- list-managerSkill
- llm-wakeupSkill
- loose-modeSkill
- make-tex-docstringSkill
- math-dependency-graphSkill
- milestone-loggingSkill
- node-certifySkill
- node-driftSkill
- notation-reviewSkill
- online-calendarSkill
- pdf-to-markdownSkill
- prepare-handoffSkill
- proof-auditSkill
- recurring-tasksSkill
- refactor-nodeSkill
- regenerate-blueprintsSkill
- relocate-nodesSkill
- semantic-integrationSkill
- send-feedbackSkill
- setup-interface-managerSkill
- skill-makerSkill
- technical-flow-reviewSkill
- tight-modeSkill
- tool-applicabilitySkill
- update-standardsSkill
- using-compassSkill
- wrap-upSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 105
Use email-triage.interface.triage for every request within this skill's trigger scope.
“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
<!-- BEGIN BLUEPRINT INTERFACES -->Generated from
blueprint.yaml. Do not edit this block by hand.
Executable Interfaces:
Send the required caller (caller skill), interface, version, and arguments; optional dry_run defaults to false. Compact uses ordered positionals plus an option mapping; ordered raw argv uses positionals: [] plus every argv token in list options. Never mix forms.
email-triage._rtx.interface.fetch-filtered-envelopes— Fetch email envelopes for one account through email-client and emit only envelopes strictly after the triage watermark.- Caller:
email-triage - Version: 1
- Security level: 2
- Alternative:
short-accountArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--after": "YYYY-MM-DD", "--dedup-against": "todo|triage", "--rescan-after": "ISO_CUTOFF", "-a": "account"}, "positionals": [], "stdin": null} Required options: ["--after", "-a"]; positional arity: 0..0; stdin: forbidden - Alternative:
long-accountArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--account": "account", "--after": "YYYY-MM-DD", "--dedup-against": "todo|triage", "--rescan-after": "ISO_CUTOFF"}, "positionals": [], "stdin": null} Required options: ["--account", "--after"]; positional arity: 0..0; stdin: forbidden
- Caller:
email-triage._rtx.interface.scripts-clear-failure— Clear a latched triage failure after its cause is fixed, without advancing the watermark.- Caller:
email-triage - Version: 1
- Security level: 2
- Alternative:
ownerArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": ["reason"], "stdin": null} Required options: []; positional arity: 0..unbounded; stdin: forbidden
- Caller:
email-triage._rtx.interface.scripts-filter-envelopes— Filter JSON envelopes (from email-client's mail-list, piped via stdin) to those strictly after the triage watermark.- Caller:
email-triage - Version: 1
- Security level: 2
- Alternative:
ownerArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"-a": "account"}, "positionals": [], "stdin": null} Required options: ["-a"]; positional arity: 0..0; stdin: permitted
- Caller:
email-triage._rtx.interface.scripts-finalize-triage— Ordered, idempotent finalization of one triage run — writes metrics, then (only on success and only if no failure is latched) advances the watermark, recording the run id so a replayed call is a safe no-op.- Caller:
email-triage - Version: 1
- Security level: 2
- Alternative:
ownerArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--accounts": "a,b", "--added-todo": "N", "--added-triage": "N", "--deduped": "N", "--run-id": "id", "--skipped": "N", "--total-scanned": "N"}, "positionals": [], "stdin": null} Required options: ["--added-todo", "--added-triage", "--run-id", "--skipped", "--total-scanned"]; positional arity: 0..0; stdin: forbidden
- Caller:
email-triage._rtx.interface.scripts-get-cutoff— Return the cutoff date for the current triage run, with a fallback if no watermark exists.- Caller:
email-triage - Version: 1
- Security level: 2
- Alternative:
ownerArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": [], "stdin": null} Required options: []; positional arity: 0..unbounded; stdin: forbidden
- Caller:
email-triage._rtx.interface.scripts-log-decision— Append a triage classification decision for one email to triage.log.- Caller:
email-triage - Version: 1
- Security level: 2
- Alternative:
ownerArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": ["account", "id", "from", "subject", "DECISION", "reason"], "stdin": null} Required options: []; positional arity: 6..6; stdin: forbidden
- Caller:
email-triage._rtx.interface.scripts-mark-failure— Record that this triage run failed, so update-watermark refuses to advance and the scheduled health check reports it.- Caller:
email-triage - Version: 1
- Security level: 2
- Alternative:
ownerArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": ["reason"], "stdin": null} Required options: []; positional arity: 0..unbounded; stdin: forbidden
- Caller:
email-triage._rtx.interface.scripts-prune-log— Drop triage.log entries older than 30 days and print a one-line summary.- Caller:
email-triage - Version: 1
- Security level: 2
- Alternative:
ownerArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": [], "stdin": null} Required options: []; positional arity: 0..unbounded; stdin: forbidden
- Caller:
email-triage._rtx.interface.scripts-update-watermark— Advance the triage watermark to the current timestamp. Refuses if scripts-mark-failure was called earlier in this run.- Caller:
email-triage - Version: 1
- Security level: 2
- Alternative:
ownerArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": [], "stdin": null} Required options: []; positional arity: 0..unbounded; stdin: forbidden
- Caller:
email-triage._rtx.interface.scripts-write-metrics— Write metrics from a triage run (emails scanned, added to lists, skipped, deduped) to status.json for visibility and debugging.- Caller:
email-triage - Version: 1
- Security level: 2
- Alternative:
ownerArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--accounts": "TEXT", "--added-todo": "N", "--added-triage": "N", "--deduped": "N", "--skipped": "N", "--total-scanned": "N"}, "positionals": [], "stdin": null} Required options: ["--added-todo", "--added-triage", "--skipped", "--total-scanned"]; positional arity: 0..0; stdin: forbidden
- Caller:
Instruction Interfaces:
These are LLM-readable instruction surfaces. Read and follow them directly; do not invoke the MCP server for them.
email-triage.source.instructions-triage.interface.triage@2— Scans emails received since the last triage run and routes extracted action items to the right list.
<!-- END BLUEPRINT INTERFACES -->Email Triage
Use email-triage.interface.triage for every request within this skill's trigger
scope. Load that interface's detailed instructions and begin triage directly.
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.

