alirezarezvani/claude-skills/productivity/email/skills/inbox-triage/SKILL.md
inbox-triage
Runs a full inbox triage using the knowledge base created by the 'inbox-setup' skill. Light-intake by design (most invocations skip questions and run with KB-default preferences); asks at most 2 grill-me override questions when invocation is outside normal cadence or includes category-skip intent. Searches recent emails, classifies them via the user's taxonomy, researches new senders, generates recommendations, drafts replies (NEVER sends), delivers a report in the user's preferred format, and u
- Source repository stars
- 24,975
- Declared platforms
- 0
- Static risk flags
- 1
- Last source update
- 2026-08-25
- Source checked
- 2026-08-26
Decision brief
What it does: where it fits
Paired with inbox-setup. This skill consumes the 7-file knowledge base that inbox-setup writes at ${WORKSPACE}/Email/. The file contracts MUST match exactly. See references/kbfilecontract.md — this is the mirror of the setup-side contract, viewed from the read side.
Not for
- Sending emails (drafts only — non-negotiable)
- Operating without knowledge base files
Compatibility matrix
Platform support, with evidence labels
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Not declared | No explicit evidence | Portability before use |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
Inspect first. Install second.
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/alirezarezvani/claude-skills --skill "productivity/email/skills/inbox-triage"Inspect the Agent Skill "inbox-triage" from https://github.com/alirezarezvani/claude-skills/blob/f2bac0a8f29b71846cc62d9d580249c2a3246030/productivity/email/skills/inbox-triage/SKILL.md at commit f2bac0a8f29b71846cc62d9d580249c2a3246030. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
What the source asks the agent to do
- 01
Step 0: Grill-Me Intake (Light — 0–2 Optional Override Questions)
Inbox-triage is light-intake by design — it runs on a recurring cadence with preferences pre-baked into the knowledge base from inbox-setup. The grill-me discipline here is asking ONLY the override questions that matter THIS run.
Inbox-triage is light-intake by design — it runs on a recurring cadence with preferences pre-baked into the knowledge base from inbox-setup. The grill-me discipline here is asking ONLY the override questions that matter…Override the default 9-hour search window? Pick: yes (specify hours) / no (use default). Why I'm asking: If you're running on-demand outside your normal 2x/day cadence, you may want a wider window (24h after a long brea…Skip if cadence is normal. - 02
Step 1: Determine Search Window
Compute via current date math. Default lookback: 9 hours (works for 2x/day cadence with slight overlap so emails between runs aren't missed).
Compute via current date math. Default lookback: 9 hours (works for 2x/day cadence with slight overlap so emails between runs aren't missed).Use scripts/searchwindowcalculator.py --cadence --now :Cadence-to-default-window mapping (override via Q1): - 03
Step 2: Email Search
Two queries (provider-agnostic adapter pattern):
Primary: Inbox + sent after windowstartSecondary: Starred unread (catch flagged items missed in primary)Two queries (provider-agnostic adapter pattern): - 04
Step 3: Classification
Apply the taxonomy from email-taxonomy.md. For lowest-priority category (newsletters / automation / spam): skip thread reads entirely — context cost not worth it. For everything else: read full thread.
Apply the taxonomy from email-taxonomy.md. For lowest-priority category (newsletters / automation / spam): skip thread reads entirely — context cost not worth it. For everything else: read full thread. - 05
Step 4: Sender Research
For senders not in tracker / blocklist / prior logs:
Check blocklist.md → if matched, auto-skipCheck tracker.md → if known thread, note existing contextFor opportunity senders (per evaluation framework): web search for company legitimacy, social presence, intermediary status
Permission review
Static risk signals and limitations
Writes files
The documentation asks the agent to create, modify, or delete local files.
| Report delivery fails | Save report to file as fallback; notify user |Evidence record
Why each signal appears
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 92/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 24,975 | Source | Repository attention, not individual Skill quality |
| Compatibility | 0 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Provenance and original SKILL.md
- Repository
- alirezarezvani/claude-skills
- Skill path
- productivity/email/skills/inbox-triage/SKILL.md
- Commit
- f2bac0a8f29b71846cc62d9d580249c2a3246030
- License
- MIT
- Collected
- 2026-08-26
- Default branch
- main
View the original SKILL.md
Inbox-Triage — Recurring Email Triage
Paired with
inbox-setup. This skill consumes the 7-file knowledge base thatinbox-setupwrites at${WORKSPACE}/Email/. The file contracts MUST match exactly. Seereferences/kb_file_contract.md— this is the mirror of the setup-side contract, viewed from the read side.
Run on a recurring schedule (1–3x daily) or on demand. Classify recent emails, research new senders, generate decision recommendations, draft replies (NEVER SEND), deliver a clean report, and update the knowledge base with what was learned this run.
Invocation Triggers
- "triage my inbox"
- "inbox triage"
- "check my email"
- "run email triage"
- "process my inbox"
- "what's new in my email"
- "handle my email"
- "email triage"
Prerequisites
Required reads at start (fail-fast if missing):
Core (required):
${WORKSPACE}/Email/email-taxonomy.md— classification + report preferences${WORKSPACE}/Email/email-patterns.md— voice, persona, templates, hard rules
Optional core (read if exists):
${WORKSPACE}/Email/evaluation-framework.md${WORKSPACE}/Email/rate-card.md
Evolving (read AND update every run):
${WORKSPACE}/Email/blocklist.md${WORKSPACE}/Email/tracker.md
Output:
${WORKSPACE}/Email/triage-log/<YYYY-MM-DD>-<run-label>.md— per-run log
If any core required file is missing → halt, direct user to run inbox-setup first. Use scripts/kb_reader.py to perform the read + validation.
DRAFTS ONLY — Never Send
This skill creates drafts. It NEVER sends.
This is the safety property that makes the skill safe to run automatically. Stated multiple times in this skill body. Non-negotiable.
The scripts/draft_safety_validator.py enforces it post-run. Any send-shaped tool call in the action log fails validation. See references/drafts_only_safety.md for the full discipline canon.
Step 0: Grill-Me Intake (Light — 0–2 Optional Override Questions)
Inbox-triage is light-intake by design — it runs on a recurring cadence with preferences pre-baked into the knowledge base from inbox-setup. The grill-me discipline here is asking ONLY the override questions that matter THIS run.
Q1 (optional, asked only when on-demand run is outside normal cadence)
Override the default 9-hour search window? Pick: yes (specify hours) / no (use default).
Why I'm asking: If you're running on-demand outside your normal 2x/day cadence, you may want a wider window (24h after a long break) or narrower (2h for a quick check).
Skip if cadence is normal.
Q2 (optional, asked only when user invokes with category-skip intent)
Skip any categories this run? E.g., "skip newsletters", "skip financial".
Why I'm asking: Sometimes you just want to scan opportunities or just want to clear active threads. Category skip narrows the run scope.
Skip if user gave no category-skip signal.
Stop condition: Max 2 questions. Default invocations skip both questions and run with KB-default preferences. The skill is optimized for fast recurring execution; intake is the exception, not the norm.
Step 1: Determine Search Window
Compute via current date math. Default lookback: 9 hours (works for 2x/day cadence with slight overlap so emails between runs aren't missed).
Use scripts/search_window_calculator.py --cadence <CADENCE> --now <ISO>:
now = current_datetime
window_start = now - 9_hours (default for 2x-daily)
run_label = "Morning" if now.hour < 12 else "Afternoon" if now.hour < 17 else "Evening"
Cadence-to-default-window mapping (override via Q1):
| Cadence (from email-taxonomy.md S1.Q5) | Default window |
|---|---|
| once daily | 26h |
| 2x daily | 9h |
| 3x daily | 6h |
| on-demand only | 24h (asks Q1) |
Step 2: Email Search
Two queries (provider-agnostic adapter pattern):
- Primary: Inbox + sent after
window_start - Secondary: Starred unread (catch flagged items missed in primary)
Collect for each email: sender, subject, date, snippet, thread ID, labels.
Provider adapter mapping:
| Provider | Tool |
|---|---|
| Gmail | Gmail MCP |
| Outlook / Microsoft 365 | Outlook MCP |
| IMAP (Fastmail, ProtonMail, etc.) | IMAP MCP if available; halt otherwise |
| (no email tool available) | Halt with clear message: "No email tool registered for this session." |
Step 3: Classification
Apply the taxonomy from email-taxonomy.md. For lowest-priority category (newsletters / automation / spam): skip thread reads entirely — context cost not worth it. For everything else: read full thread.
Step 4: Sender Research
For senders not in tracker / blocklist / prior logs:
- Check
blocklist.md→ if matched, auto-skip - Check
tracker.md→ if known thread, note existing context - For opportunity senders (per evaluation framework): web search for company legitimacy, social presence, intermediary status
Skip research entirely for: known senders (in tracker), internal email, automated notifications, obvious low-priority.
Step 5: Recommendations
For decision-required emails, apply the framework from evaluation-framework.md. Categorize:
| Category | When | Output |
|---|---|---|
| TAKE IT | Meets criteria | Recommend engaging; draft reply (Step 6) |
| WORTH CONSIDERING | Has potential, needs user judgment | Surface key context; draft for user to edit |
| PASS | Doesn't meet criteria | Brief "why" (1–3 sentences); draft polite decline |
| FLAG FOR REVIEW | Unusual; needs direct user decision | Surface fully; NO draft (user decides response shape) |
Each: brief "why", relevant context, pricing/timeline comparison if applicable.
Skip Step 5 entirely if no evaluation-framework.md exists.
See references/triage_decision_framework.md for the framework canon.
Step 6: Drafts
For every reasonable reply candidate, create a draft using email-patterns.md voice rules.
Draft for: opportunity responses (TAKE IT / WORTH / PASS), active conversations needing reply, action items, important personal emails.
Do NOT draft for:
- Clearly no-response emails (newsletters, automation, FYI)
- Threads where user already replied
- Blocked senders (unless new info changes the calculus)
Mechanics:
- Draft only in the existing thread when possible (preserves context)
- Set
to,subject(Re: [original]) - NEVER call any send operation. Only create drafts.
The draft body MUST honor:
- Voice register from
email-patterns.md - Forbidden tokens (S3.Q2 pet peeves)
- Sign-off patterns
- Persona context
- Hard rules (S3.Q6 — non-negotiable)
- Reply length per
email-patterns.md
If evaluation-framework.md exists, draft tone matches recommendation:
- TAKE IT → engaged + concrete next step
- WORTH → curious + 1-2 clarifying questions
- PASS → polite decline + brief reason (no hedging promises)
- FLAG → NO draft
Step 7: Report Delivery
Honor user's preference from email-taxonomy.md "Report Preferences" section. Default: email draft to self with HTML.
Subject: Inbox Triage — [Day], [Month Date] ([Run Label])
Sections (in order):
- Overview — 2–3 sentences. What happened? Anything urgent?
- Stats — Counts: processed, drafts created, action needed, skipped.
- Action Needed — Overdue items, decisions, drafts to review, deadlines.
- Quick Reference — One line per email, alphabetical by sender.
**Sender** — one-sentence summary + recommendation. - Detailed Cards — Opportunities, active threads, flags. Each: sender / subject / category, recommendation + reasoning, key context. NO draft text previews (drafts are already in email client for user to read there).
- Footer — Generation timestamp + KB update summary.
Formatting (if HTML):
- Inline CSS only (Gmail strips
<style>) - Color-coded by recommendation:
- green → TAKE IT
- amber → WORTH CONSIDERING
- red → PASS
- purple → FLAG FOR REVIEW
- blue → active conversation
Step 8: Knowledge Base Update
blocklist.md (append new):
- New declined senders + reason + date
- New decline patterns from observed behavior (e.g., "all emails containing 'looking for backend engineers' from gmail addresses → cold recruiter pattern")
- Remove entries if user has overridden them (user replied to a "blocked" sender → unblock)
tracker.md (append + update):
- New follow-ups for emails needing future action
- Update existing follow-ups (deadline changed, status changed)
- Mark resolved items complete
- Flag overdue items
- Remove resolved items older than 30 days
- Add entry to update log
Learning patterns to observe over runs:
- Drafts sent as-is vs. edited vs. deleted → tone calibration signal
- PASS recommendations user overrides → framework adjustment signal
- Engaged vs. ignored emails → taxonomy refinement signal
- New decline patterns → blocklist additions
After 5+ runs, suggest KB improvements to user (e.g., "You always decline emails from X — add as auto-skip?").
Step 9: Internal Log
Save to ${WORKSPACE}/Email/triage-log/[YYYY-MM-DD]-[run-label].md:
- Emails processed with classifications
- Recommendations made
- Drafts created (with IDs / thread refs)
- KB updates made
- Follow-ups added / resolved
- Notable observations (patterns surfaced, edge cases handled)
The log is the audit trail for scripts/draft_safety_validator.py to scan for send operations post-run.
Step 10: Empty Inbox Handling
Even with zero new emails:
- Check
tracker.mdfor items due today or overdue - Generate minimal report: "No new actionable emails since last run"
- Flag any overdue items
- Escalate per tracker rules
Skip Steps 3–6 entirely on empty inbox.
Critical Rules (Stated Multiple Times)
- DRAFTS ONLY — NEVER SEND. Non-negotiable. Stated again here.
- Privacy. No passwords / credentials in KB. Reference threads by ID for sensitive content.
- Accuracy over speed. When unsure, flag for review. A wrong auto-draft is worse than no draft.
- Respect the KB. Documented preferences are source of truth. Don't override with judgment.
- Transparency. Note every KB change in the triage log.
- First runs need oversight. Document this expectation for the user.
Error Handling
| Situation | Behavior |
|---|---|
| KB files missing | Halt; direct user to run inbox-setup |
| Email tool unavailable | Halt with clear message about required tool |
| Web search unavailable for sender research | Skip research step; note senders not researched |
| Draft creation fails | Skip that draft; note in log; report continues |
| Report delivery fails | Save report to file as fallback; notify user |
| User has 100+ new emails | Stay within reasonable limits; flag volume; offer to focus on priority categories only |
| Sender appears in both blocklist and tracker | Tracker wins (active conversation); note inconsistency in log |
Portability
- Claude Code CLI: Native — uses Gmail / Outlook MCP, file tools for KB, web search for research.
- Claude.ai web: Works when email MCP connector is connected (Gmail MCP available). Skill must check tool availability before assuming. If no email tool: halt with clear message.
Tooling
| Script | Role |
|---|---|
scripts/kb_reader.py | Reads + validates the 7-file KB. Returns parsed structure. Halts with explicit error if required files missing. |
scripts/search_window_calculator.py | Computes window_start from cadence + current time. Returns run_label. Honors Q1 override. |
scripts/draft_safety_validator.py | Post-run scan of the action log for any send-shaped tool call. FAILs if detected. The deterministic enforcement of the NEVER-SEND rule. |
References
references/kb_file_contract.md— canonical 7-file contract (read perspective; mirrors../inbox-setup/references/kb_file_contract.md)references/triage_decision_framework.md— TAKE IT / WORTH / PASS / FLAG taxonomyreferences/drafts_only_safety.md— the NEVER-SEND discipline canon
Anti-Patterns To Reject
- Sending emails (drafts only — non-negotiable)
- Operating without knowledge base files
- Storing passwords / credentials in KB
- Skipping the learning loop (KB updates) at end of run
- Overriding user's documented preferences with own judgment
- Reading lowest-priority threads (waste of context)
- Including draft text previews in report (drafts are already in email client)
- Provider lock-in without adapter pattern
- Silently failing on missing tools
Version: 1.0.0
Source spec: megaprompts/07-inbox-triage-megaprompt.md (maintainer-local draft spec — gitignored, not present in the public repository)
Build pattern: Path B (direct conversion). Paired with inbox-setup.
Frequently asked questions
What to verify before installation and use
What does the inbox-triage source document cover?
Paired with inbox-setup. This skill consumes the 7-file knowledge base that inbox-setup writes at ${WORKSPACE}/Email/. The file contracts MUST match exactly. See references/kbfilecontract.md — this is the mirror of the setup-side contract, viewed from the read side.
How do I install inbox-triage?
The source record exposes this install command: npx skills add https://github.com/alirezarezvani/claude-skills --skill "productivity/email/skills/inbox-triage". Inspect the command and pinned source before running it.
Which permission-related actions were detected?
Static rules flagged write-files in the source; the page lists the matching lines and excerpts.
Alternatives
Compare before choosing
coreyhaines31/marketingskills
ab-testing
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program
coreyhaines31/marketingskills
churn-prevention
When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'people keep canceling,' 'churn rate is too high,' 'how do I keep users,' or 'customers are leaving.' Use this whenever someone is losing subscribers o
prowler-cloud/prowler
postgresql-indexing
PostgreSQL indexing best practices for Prowler: index design, partial indexes, partitioned table indexing, EXPLAIN ANALYZE validation, concurrent operations, monitoring, and maintenance. Trigger: When creating or modifying PostgreSQL indexes, analyzing query performance with EXPLAIN, debugging slow queries, reviewing index usage statistics, reindexing, dropping indexes, or working with partitioned table indexes. Also trigger when discussing index strategies, partial indexes, or index maintenance
narrative-io/narrative-skills-marketplace
design-analysis
Translate a fuzzy analytical question into a rigorous investigation plan. Interrogates the ask, grounds the plan in the available data dictionary, applies analytical best practices, and produces a structured brief of query specifications for a downstream query-writing skill. Plans, does not write SQL. Use when: "why did X drop", "is there a relationship between A and B", "who are our highest-value customers", "what's driving the change in Y", "investigate this trend", "design an analysis for", "