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

Structure

ASecurity

Use when the user brings any fuzzy, half-formed, or interrupt-driven input — an order from a boss, a forwarded email thread, a ticket, a chat message, a "can you look into X", a raw idea — and it needs framing before work starts. Turns the input into a structured brief (Context · Desired outcome · Goal · Owner · Next step · Decision needed). This is the AIOS's front door; run most things through it first. Trigger on "/structure", "frame this", "what's the actual ask here", "structure this", o...

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

Works with

cli

Security Analysis

A100/100

Scanned 6/9/2026

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

Installs into .claude/skills of the current project.

Are you the author of Structure?

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

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

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: structure
description: Use when the user brings any fuzzy, half-formed, or interrupt-driven input — an order from a boss, a forwarded email thread, a ticket, a chat message, a "can you look into X", a raw idea — and it needs framing before work starts. Turns the input into a structured brief (Context · Desired outcome · Goal · Owner · Next step · Decision needed). This is the AIOS's front door; run most things through it first. Trigger on "/structure", "frame this", "what's the actual ask here", "structure this", or any vague task that lacks a defined outcome.
---

# Structuring Engine

A common leverage point: inputs arrive **without structured context, defined outcomes, or clear goals.** This skill fixes that before any work begins. Frame first, then act (or delegate).

## When to run
- A new task lands fuzzy ("the boss wants the draft checked", "look into the X thing").
- A long email/chat thread needs to become an action.
- The user is about to do something the old way → apply the **Default Shift** ("to what extent could AI be leveraged here?").

## The output (always this shape)
```
## <short title>
**Context** — what's going on, in 2-4 plain sentences. The why behind the ask.
**Desired outcome** — the end state. What does "done" look like, concretely?
**Goal** — the measurable/observable target (a date, a number, a deliverable). One line.
**Owner** — who should own this (route to the team; don't pool on the user by default).
**Next step** — the single next physical action, and by when.
**Decision needed** — the specific call the user must make, framed as a fast choice.
```
When a decision is involved, present it as a **fast checklist** they can answer in seconds:
```
- Send to the client now (yes/no)?
- Loop in <reviewer> first (yes/no)?
- Target date: <propose one>
```

## Process
1. **Read everything given.** If it references a ticket, doc, or thread and a connection exists, pull it rather than guessing.
2. **Strip to the real ask.** Separate noise from the actual decision/outcome. Name what's missing.
3. **Fill the template.** Be concrete. If a field is genuinely unknown, write `❓ <the open question> → <who can answer>` instead of inventing.
4. **Route the owner.** Default to delegating to the right teammate; only put the user as owner when it's truly theirs (a decision, an external sign-off).
5. **Offer the next move.** After the brief, offer to: create the artifact (ticket / note / plan — allowed without approval), draft the reply in the user's voice (internal may send to team; never external without approval), and/or log a decision to `decisions/log.md`.

## Guardrails (from CLAUDE.md)
- No confidential figures or sensitive/regulated data persisted to the repo. Pull live, don't store.
- **Cite, don't invent** — any regulatory/financial/legal claim cites a source or is flagged as a gap.
- **Draft, never send external.** Internal to the team may be OK; external needs approval.
- Match `references/voice.md`.

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 →