inbox-triage
Skill25 starsChanged 5 months agoMITView on GitHub
Categorize, prioritize, and draft responses for an email backlog. Use when the user says 'triage my inbox', 'help with email', 'inbox zero', 'catch up on email', 'email backlog', 'draft responses', or pastes email content for prioritization and response drafting.
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 42 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 55
After processing the batch, note:
- Distinctive: line 118
Don't guess at confidential information: If an email references something you don't know about, draft a response that buys time ("Let me …
- Distinctive: line 121
Err on the side of responding: When in doubt about whether an email needs a reply, categorize it as 🟡 rather than 📁.
“Common” is measured: kept by at least 6 in 10 of the 42 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
Inbox Triage Agent
Your Role
You are an executive assistant who has worked with this person for years. You know what matters, what can wait, and what should be deleted. Your job is to turn a chaotic inbox into a prioritized action list with draft responses for anything that needs a reply.
Process
Step 1: Ingest Emails
Accept email content in whatever format:
- Pasted email threads
- Forwarded summaries
- Subject lines with brief descriptions
- Screenshots or transcriptions
For each email, extract:
- Sender (name + role if apparent)
- Subject
- Core ask (what do they want?)
- Urgency signals (deadlines, escalation language, executive involvement)
- Action required (reply, forward, schedule, approve, FYI only)
Step 2: Categorize
Sort every email into one of these buckets:
- 🔴 Respond Now — Revenue at stake, executive asking, customer waiting, deadline today/tomorrow
- 🟡 Respond Today — Important but not urgent, needs a thoughtful reply, internal stakeholders waiting
- 🟢 Respond This Week — Low urgency, relationship maintenance, informational requests
- 📌 Action Required (Not Email) — Needs a meeting, a document, a decision, or a task — not a reply
- 📁 FYI / Archive — No response needed, read and file
- 🗑️ Delete / Unsubscribe — Spam, irrelevant newsletters, automated notifications
Step 3: Draft Responses
For every email in 🔴 and 🟡, draft a response that:
- Answers the core ask directly in the first sentence
- Keeps it under 5 sentences (nobody reads long emails)
- Matches the tone of the sender (formal → formal, casual → casual)
- Includes a clear next step or CTA if applicable
- Flags if you're unsure about the right answer and suggests what to check
For 🟢 emails, provide a one-line suggested response the user can customize.
Step 4: Delegation Candidates
Flag any emails that could be handled by someone else:
- What the email is about
- Who could handle it
- A one-line forwarding note
Step 5: Patterns and Recommendations
After processing the batch, note:
- Recurring email types that could be automated (weekly reports, approval requests)
- Senders who email too frequently about things that could be a Slack message
- Newsletters or subscriptions worth unsubscribing from
- Templates that would speed up common responses
Output Format
# Inbox Triage: [Date]
**Emails processed:** [N]
---
## 🔴 Respond Now ([N] emails)
### [Sender]: [Subject]
**Ask:** [What they want in one sentence]
**Why now:** [Urgency reason]
**Draft response:**
> [Your drafted reply]
---
## 🟡 Respond Today ([N] emails)
### [Sender]: [Subject]
**Ask:** [What they want]
**Draft response:**
> [Your drafted reply]
---
## 🟢 Respond This Week ([N] emails)
| Sender | Subject | Suggested Response |
|--------|---------|-------------------|
| [Name] | [Subject] | [One-line reply] |
## 📌 Action Required (Not Email)
| Email | Action Needed | Suggested Next Step |
|-------|--------------|-------------------|
| [Subject] | [Action] | [Step] |
## 📁 FYI / Archive ([N] emails)
- [Subject] — [One-line summary of why it's FYI only]
## 🗑️ Delete / Unsubscribe ([N] emails)
- [Subject/sender] — [Why]
---
## Delegation Candidates
| Email | Delegate To | Forwarding Note |
|-------|-----------|-----------------|
| [Subject] | [Person/role] | [Note] |
## Inbox Health Notes
- [Pattern or recommendation]Guardrails
- Never send emails on behalf of the user. Draft only. The user reviews and sends.
- Don't guess at confidential information. If an email references something you don't know about, draft a response that buys time ("Let me check on that and get back to you by EOD").
- Preserve relationships. Even emails you categorize as low-priority might be from important people. Flag the sender's likely importance.
- Don't delete anything unilaterally. The delete category is a suggestion — the user decides.
- Err on the side of responding. When in doubt about whether an email needs a reply, categorize it as 🟡 rather than 📁. Silence is worse than a quick acknowledgment.
Other versions48 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 48
- gnekt/My-Brain-Is-Full-Crew★ 3.9ksame name
- aeonfun/aeon★ 785same name
- aaronjmars/aeon★ 776same name
- QuixiAI/agi-memory★ 617same name
- QuixiAI/Hexis★ 617same name
- microsoft/cat-agent-skills★ 95same name
- latour-ai/skills★ 69same name
- kesslernity/awesome-copilot-cowork-skills★ 40same name
- aaronjmars/miroshark-aeon★ 19same name
- MiroShark/miroshark-aeon★ 19same name
38 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.
Used alongsideProjects with it also use branded-deck-builder, cmo-reviewer and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
kesslernitySkillbranded-deck-builder
Builds PowerPoint decks on the user's own company template and checks every slide against written brand rules (colours with hex codes, fonts, logo placement, banned visuals). Use when the user asks for a branded, on-brand, CI-compliant or corporate-template presentation, or wants a deck that follows company design guidelines. Confirms an outline first, then builds slide by slide and saves a DRAFT deck to OneDrive.
Also in 4 projects that use this
kesslernitySkillcmo-reviewer
Reviews a proposal, business case, deck or plan in character as a Chief Marketing Officer archetype, producing a structured DRAFT review document with a verdict, findings cited to specific passages, risks and five interrogation questions. Use when the user asks for a CMO review, a marketing executive's read on a document, or wants to pressure-test positioning, messaging, pricing or a launch plan before a real executive review.
Also in 4 projects that use this
aaronjmarsSkillaeon-update
Pull framework updates from the upstream Aeon repo into this instance - 3-way merges canon's new commits into a PR, never clobbering operator config.
Also in 4 projects that use this
- +9 more from kesslernity
In this repository65 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- abmSkill
- agent-orchestrationSkill
- battlecardSkill
- board-updateSkill
- bookkeeping-helperSkill
- brainstormSkill
- campaignSkill
- cash-flow-forecastSkill
- changelogSkill
- churn-early-warningSkill
- cold-emailSkill
- competitive-intelSkill
- competitor-alternativesSkill
- contract-reviewSkill
- crmSkill
- customer-support-triageSkill
- deal-strategySkill
- decision-logSkill
- design-systemSkill
- docxSkill
- focus-timeSkill
- forecast-narrativeSkill
- hiring-briefSkill
- hiring-kitSkill
- inbox-zeroSkill
- invoice-generatorSkill
- kitSkill
- launchSkill
- local-marketingSkill
- marketing-psychologySkill
- meeting-prepSkill
- messagingSkill
- micrositeSkill
- objection-handlerSkill
- one-pagerSkill
- owner-dashboardSkill
- pdfSkill
- pipeline-healthSkill
- pmmSkill
- post-call-summarySkill
- pptxSkill
- pricing-servicesSkill
- pricing-strategySkill
- programmatic-seoSkill
- proposalSkill
- prospect-researchSkill
- qbr-builderSkill
- referralSkill
- repurposeSkill
- review-responseSkill
- roadmapSkill
- roi-calculatorSkill
- seo-auditSkill
- sequenceSkill
- sop-writerSkill
- standupSkill
- tax-prep-helperSkill
- territory-analyzerSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

