Back to Skills

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 ca…

goai
By alirezarezvani
17k2.4kUpdated 3 days agoPythonMIT

Skill Content

# Inbox-Triage — Recurring Email Triage

> **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/kb_file_contract.md`](references/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`](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:

1. Check `blocklist.md` → if matched, auto-skip
2. Check `tracker.md` → if known thread, note existing context
3. 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`](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):**

1. **Overview** — 2–3 sentences. What happened? Anything urgent?
2. **Stats** — Counts: processed, drafts created, action needed, skipped.
3. **Action Needed** — Overdue items, decisions, drafts to review, deadlines.
4. **Quick Reference** — One line per email, alphabetical by sender. `**Sender** — one-sentence summary + recommendation`.
5. **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).
6. **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:

1. Check `tracker.md` for items due today or overdue
2. Generate minimal report: "No new actionable emails since last run"
3. Flag any overdue items
4. Escalate per tracker rules

Skip Steps 3–6 entirely on empty inbox.

## Critical Rules (Stated Multiple Times)

1. **DRAFTS ONLY — NEVER SEND.** Non-negotiable. Stated again here.
2. **Privacy.** No passwords / credentials in KB. Reference threads by ID for sensitive content.
3. **Accuracy over speed.** When unsure, flag for review. A wrong auto-draft is worse than no draft.
4. **Respect the KB.** Documented preferences are source of truth. Don't override with judgment.
5. **Transparency.** Note every KB change in the triage log.
6. **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`](references/kb_file_contract.md) — canonical 7-file contract (read perspective; mirrors `inbox-setup/references/kb_file_contract.md`)
- [`references/triage_decision_framework.md`](references/triage_decision_framework.md) — TAKE IT / WORTH / PASS / FLAG taxonomy
- [`references/drafts_only_safety.md`](references/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`](../../../../megaprompts/07-inbox-triage-megaprompt.md)
**Build pattern:** Path B (direct conversion). Paired with `inbox-setup`.

How to use

  1. Copy the skill content above
  2. Create a .claude/skills directory in your project
  3. Save as .claude/skills/claude-skills-inbox-triage.md
  4. Use /claude-skills-inbox-triage in Claude Code to invoke this skill

Claude Code Skills & Plugins — Agent Skills for Every Coding Tool

338 production-ready Claude Code skills, plugins, and agent skills for 13 AI coding tools.

The most comprehensive open-source library of Claude Code skills and agent plugins — also works with OpenAI Codex, Gemini CLI, Cursor, and 9 more coding agents. Reusable expertise packages covering engineering, DevOps, marketing (incl. AEO — Answer Engine Optimization for LLM citation), security (PreToolUse hooks), compliance, C-level advisory (incl. founder-mode CFO/CMO/CRO/CPO/COO/CHRO/CISO/GC/CDO/CAIO/CCO/VPE personas + 21 /cs:* slash commands), productivity (capture/email/reflect), an academic research stack (litreview/grants/dossier/patent/syllabus/pulse/notebooklm + hybrid router), and enterprise Research Operations (clinical-research/research-finance/market-research/product-research, v2.9.0).

Works with: Claude Code · OpenAI Codex · Gemini CLI · OpenClaw · Hermes Agent1 · Mistral Vibe2 · Cursor · Aider · Windsurf · Kilo Code · OpenCode · Augment · Antigravity

License: MIT Skills Agents Personas Commands Stars SkillCheck Validated

5,200+ GitHub stars — the most comprehensive open-source Claude Code skills & agent plugins library.


What Are Claude Code Skills & Agent Plugins?

Claude Code skills (also called agent skills or coding agent plugins) are modular instruction packages that give AI coding agents domain expertise they don't have out of the box. Each skill includes:

  • SKILL.md — structured instructions, workflows, and decision frameworks
  • Python tools — 533 CLI scripts (all stdlib-only, zero pip installs)
  • Reference docs — 676 templates, checklists, and domain-specific knowledge files

One repo, thirteen platforms. Works natively as Claude Code plugins, Codex agent skills, Gemini CLI skills, Hermes Agent skills, Mistral Vibe skills, and converts to more tools via scripts/convert.sh. All 533 Python tools run anywhere Python runs.

Skills vs Agents vs Personas

SkillsAgentsPersonas
PurposeHow to execute a taskWhat task to doWho is thinking
ScopeSingle domainSingle domainCross-domain
VoiceNeutralProfessionalPersonality-driven
Example"Follow these steps for SEO""Run a security audit""Think like a startup CTO"

All three work together. See Orchestration for how to combine them.


Quick Install

Gemini CLI (New)

# Clone the repository
git clone https://github.com/alirezarezvani/claude-skills.git
cd claude-skills

# Run the setup script
./scripts/gemini-install.sh

# Start using skills
> activate_skill(name="senior-architect")

Claude Code (Recommended)

# Add the marketplace
/plugin marketplace add alirezarezvani/claude-skills

# Install by domain
/plugin install engineering-skills@claude-code-skills          # 24 core engineering
/plugin install engineering-advanced-skills@claude-code-skills  # 25 POWERFUL-tier
/plugin install product-skills@claude-code-skills               # 12 product skills
/plugin install marketing-skills@claude-code-skills             # 43 marketing skills
/plugin install ra-qm-skills@claude-code-skills                 # 12 regulatory/quality
/plugin install pm-skills@claude-code-skills                    # 6 project management
/plugin install c-level-skills@claude-code-skills               # 28 C-level advisory (full C-suite)
/plugin install business-growth-skills@claude-code-skills       # 4 business & growth
/plugin install finance-skills@claude-code-skills               # 2 finance (analyst + SaaS metrics)

# Or install individual skills
/plugin install skill-security-auditor@claude-code-skills       # Security scanner
/plugin install playwright-pro@claude-code-skills                  # Playwright testing toolkit
/plugin install self-improving-agent@claude-code-skills         # Auto-memory curation
/plugin install content-creator@claude-code-skills              # Single skill

OpenAI Codex

npx agent-skills-cli add alirezarezvani/claude-skills --agent codex
# Or: git clone + ./scripts/codex-install.sh

OpenClaw

bash <(curl -s https://raw.githubusercontent.com/alirezarezvani/claude-skills/main/scripts/openclaw-install.sh)

Manual Installation

git clone https://github.com/alirezarezvani/claude-skills.git
# Copy any skill folder to ~/.claude/skills/ (Claude Code) or ~/.codex/skills/ (Codex)

Multi-Tool Support (New)

Convert all 338 skills to 9 AI coding tools with a single script:

ToolFormatInstall
Cursor.mdc rules./scripts/install.sh --tool cursor --target .
AiderCONVENTIONS.md./scripts/install.sh --tool aider --target .
Kilo Code.kilocode/rules/./scripts/install.sh --tool kilocode --target .
Windsurf.windsurf/skills/./scripts/install.sh --tool windsurf --target .
OpenCode.opencode/skills/./scripts/install.sh --tool opencode --target .
Augment.augment/rules/./scripts/install.sh --tool augment --target .
Antigravity~/.gemini/antigravity/skills/./scripts/install.sh --tool antigravity
Hermes Agent~/.hermes/skills/python scripts/sync-hermes-skills.py --verbose
Mistral Vibe~/.vibe/skills/./scripts/vibe-install.sh

How it works:

# 1. Convert all skills to all tools (takes ~15 seconds)
./scripts/convert.sh --tool all

# 2. Install into your project (with confirmation)
./scripts/install.sh --tool cursor --target /path/to/project

# Or use --force to skip confirmation:
./scripts/install.sh --tool aider --target . --force

# 3. Verify
find .cursor/rules -name "*.mdc" | wc -l  # Should show 338

Each tool gets:

  • ✅ All 338 skills converted to native format
  • ✅ Per-tool README with install/verify/update steps
  • ✅ Support for scripts, references, templates where applicable
  • ✅ Zero manual conversion work

Run ./scripts/convert.sh --tool all to generate tool-specific outputs locally.


Skills Overview

338 skills across 16 domains:

DomainSkillsHighlightsDetails
🔧 Engineering — Core51Architecture, frontend, backend, fullstack, QA, DevOps, SecOps, AI/ML, data, Playwright Pro (test gen, flaky fix, migrations), self-improving agent (auto-memory curation), security suite, a11y auditengineering-team/
⚡ Engineering — POWERFUL78Agent designer, RAG architect, database designer, CI/CD builder, security auditor, MCP builder, AgentHub, Helm charts, Terraform, self-eval, llm-wiki, tc-tracker, autoresearch-agent, reliability portfolio (feature-flags-architect, kubernetes-operator, chaos-engineering, slo-architect), ship-gate, security-guidance PreToolUse hook, Matt Pocock skills (write-a-skill, caveman, grill-me, handoff, grill-with-docs)engineering/
🎯 Product17Product manager, agile PO, strategist, UX researcher, UI design, landing pages, SaaS scaffolder, analytics, experiment designer, discovery, roadmap communicator, code-to-prd, apple-hig-expertproduct-team/
📣 Marketing468 pods: Content, SEO + AEO (aeo — E-E-A-T audit, citation tracking across 5 LLMs), CRO, Channels, Growth, Intelligence, Sales + context foundation + orchestration routermarketing-skill/
🚀 Productivity6capture (brain-dump-to-action), email pair (inbox-setup + inbox-triage), reflect (journal), handoff (Matt Pocock-inspired), andreessen (market-first decision mode)productivity/
🎨 Marketing (top-level)1landing — single-file HTML landing-page generator (4 design styles, GSAP patterns, brand palette validator)marketing/
🔬 Research (academic)8research orchestrator (hybrid router + fallback) + 7 specialists: pulse, litreview, grants (NIH), dossier, patent, syllabus, notebooklmresearch/
🧪 Research Operations ✨v2.9.05Enterprise/cross-functional research: orchestrator + clinical-research (study design), research-finance (R&D program finance), market-research (sizing/survey/segmentation), product-research (user research) — each with onboarding + customization + opt-in autoresearch bridgeresearch-ops/
📋 Project Management9Senior PM, scrum master, Jira, Confluence, Atlassian admin, templates + bundled Atlassian Remote MCPproject-management/
🏥 Regulatory & QM18ISO 13485, MDR 2017/745, FDA, ISO 27001, GDPR, SOC 2, CAPA, risk managementra-qm-team/
🛡️ Compliance OS9Compliance operating system — controls, evidence, audit-readiness workflowscompliance-os/
💼 C-Level Advisory66Full C-suite (CEO/CTO/CFO/CMO/CRO/CPO/COO/CHRO/CISO/GC/CDO/CAIO/CCO/VPE) + founder-mode agents + orchestration + board meetings + culture & collaborationc-level-advisor/
📈 Business & Growth5Customer success, sales engineer, revenue ops, contracts & proposals, BizDev toolkitbusiness-growth/
🏭 Business Operations7Orchestrator + process-mapper, vendor-management, capacity-planner, internal-comms, knowledge-ops, procurement-optimizerbusiness-operations/
🤝 Commercial8Orchestrator + pricing-strategist, deal-desk, partnerships-architect, channel-economics, commercial-policy, rfp-responder, commercial-forecastercommercial/
💰 Finance4Financial analyst (DCF, budgeting, forecasting), SaaS metrics coach, business investment advisorfinance/

Personas

Pre-configured agent identities with curated skill loadouts, workflows, and distinct communication styles. Personas go beyond "use these skills" — they define how an agent thinks, prioritizes, and communicates.

PersonaDomainBest For
Startup CTOEngineering + StrategyArchitecture decisions, tech stack selection, team building, technical due diligence
Growth MarketerMarketing + GrowthContent-led growth, launch strategy, channel optimization, bootstrapped marketing
Solo FounderCross-domainOne-person s

Footnotes

  1. Hermes Agent is BYO-sync tier: the repo ships a pre-generated .hermes/skills/claude-skills/ tree, but you run python scripts/sync-hermes-skills.py once locally to install into ~/.hermes/skills/. Uses the same agentskills.io SKILL.md standard — no format conversion.

  2. Mistral Vibe is also BYO-sync tier: the repo ships a pre-generated .vibe/skills/claude-skills/ tree, run ./scripts/vibe-install.sh once locally to install into ~/.vibe/skills/. Same agentskills.io SKILL.md standard — no format conversion. Docs: https://docs.mistral.ai/mistral-vibe/agents-skills.

View source on GitHub