Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Triage

ASecurity

Use when the user dumps a batch of inputs at once — a pile of emails, a backlog of Slack/Teams messages, a list of asks, meeting action items, a notes brain-dump — and needs it sorted into action. Classifies each item, assigns owner + next step + priority, and flags which need a full /structure brief or a /decide call. Trigger on "/triage", "triage this", "process my inbox", "sort these asks", "clear my backlog", "what do I do with all this".

37 stars
0 votes
0 copies
2 views
Added 6/9/2026
ai-agentsrails

Security Analysis

A100/100

Scanned 6/9/2026

$npx -y skills add alirezarezvani/gaios --skill triage --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Triage?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Triage
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/alirezarezvani-triage/badge)](https://www.skillsdirectory.com/skills/alirezarezvani-triage)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: triage
description: Use when the user dumps a batch of inputs at once — a pile of emails, a backlog of Slack/Teams messages, a list of asks, meeting action items, a notes brain-dump — and needs it sorted into action. Classifies each item, assigns owner + next step + priority, and flags which need a full /structure brief or a /decide call. Trigger on "/triage", "triage this", "process my inbox", "sort these asks", "clear my backlog", "what do I do with all this".
---

# Triage

Batch intake for the Chief of Staff: turn a chaotic pile into a sorted, owned, prioritized list —
the front-door `/structure` does for *one* fuzzy input, `/triage` does for *many*.

## When to run
- An inbox / backlog / message pile needs to become action.
- After a meeting, to process a batch of action items at once.
- Feeding `/daily` — fold the triaged items into today.

## The output (always this shape)
```
## Triage — <date> (<N> items)
| # | Item (1 line) | Type | Owner | Next step | Priority | Route |
|---|---------------|------|-------|-----------|----------|-------|
| 1 | … | ask/FYI/decision/task | <who> | <action> | P1/P2/P3 | /structure · /decide · /draft · done |

**Needs your decision** — the short list only the user can resolve (with the framed choice).
**Delegated** — items routed to the team (with owner + next step).
**Drop / FYI** — no action needed (so they're off the list).
```

## Process
1. **Split the batch into discrete items.** One row per real ask; merge duplicates.
2. **Classify each:** ask · FYI · decision · task. Be ruthless — most "FYIs" are drops.
3. **Assign owner + next step + priority.** Default owner to the right teammate (don't pool on the user). Priority by leverage/urgency.
4. **Route, don't solve inline:** mark complex items `/structure` (needs framing), `/decide` (needs a call), `/draft` (needs a reply). Simple ones get a one-line next step.
5. **Surface the decision shortlist.** Pull every `decision`-type item into "Needs your decision" with the choice framed for a fast yes/no.
6. **Offer next moves:** run `/structure` on the flagged items, `/draft` the replies (internal may send; external = draft), and/or feed the result into `/daily`.

## Autonomy
**L2 — sorts and routes; the human decides and sends.** Triage never auto-replies.

## Guardrails (from CLAUDE.md)
- **Eliminate first** (3Ms): if nobody would notice an item disappearing, drop it.
- No confidential data persisted to the repo; reference live sources.
- External replies are **drafts** in `references/voice.md` register; internal-to-team may send.

Attribution

alirezarezvanialirezarezvani
View sourceSee grades on GitHubMore from alirezarezvani →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →