structure
$
npx mdskill add alirezarezvani/gaios/structureConverts fuzzy inputs into structured briefs for action.
- Fixes tasks lacking context, goals, or defined outcomes
- Depends on user prompts and unstructured task descriptions
- Decides framing by analyzing input vagueness and intent
- Delivers a standardized brief with clear next steps
SKILL.md
.github/skills/structureView on GitHub ↗
---
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`.
More from alirezarezvani/gaios
- draftUse when the user needs a written communication drafted in their voice — an email, a Slack/Teams message, a team update, an announcement, a reply to a thread, or a post. Produces a ready-to-review draft matching references/voice.md; never auto-sends external. Trigger on "/draft", "draft an email", "write a reply", "draft the update", "draft the announcement", "respond to this thread in my voice".
- exec-cockpitTemplate skill for a leadership-transition / executive cockpit — when someone steps into or covers a leadership role and needs to not drop anything. Produces a handoff doc + decision-rights map, an "open loops" tracker, a team-comms cadence, and a recurring report/update drafter. Trigger on "/exec-cockpit", "handoff doc", "decision-rights map", "open loops tracker", "cover for <role>", "interim <role>". Customize the placeholders to your situation.
- graphUse when the user wants to build, refresh, or visualize the repo's knowledge graph — code structure plus the committed wiki/ — via graphify. Produces an interactive graph + a GRAPH_REPORT.md of God Nodes, surprising connections, and suggested questions. Trigger on "/graph", "build the knowledge graph", "graph the repo", "map the codebase", "refresh the graph", "visualize the second brain".
- graph-ingestUse when the user brings an external source worth keeping — a URL, a paper, a tweet/thread, a blog post, a docs page — and wants it pulled into the second brain. Fetches the source into the git-ignored capture inbox, admits it to the committed wiki through the admission policy, then refreshes the knowledge graph so it joins the rest of your thinking. Trigger on "/graph-ingest", "ingest this url", "add this paper to my knowledge", "add this tweet/page to my knowledge", "capture this source".
- graph-queryUse when the user asks a question about how things in the codebase or wiki relate — what connects two things, how something works end to end, what depends on what, or what a concept means in this repo. Answers from the knowledge graph in graphify-out/graph.json, with source-location citations. Trigger on "/graph-query", "ask the graph", "what connects X to Y", "trace how X works", "explain <concept> from the graph", "shortest path between".
- level-upUse weekly to find and ship one new automation. Walks the 3Ms interview — Mindset (find the candidate) → Method (scope one) → Machine (build it). Trigger on "let's level up", "what should I automate next", "find me leverage this week", or as a Friday ritual. One run = one shipped artifact.
- prepUse when the user has a meeting, call, 1:1, a person to meet, or a decision coming up and needs to walk in prepared. Assembles a one-page brief from context/, wiki/, connections, open loops, and the knowledge graph — who · what · goal · history · open loops · the ask · risks. Trigger on "/prep", "prep me for", "brief me on <person/meeting>", "what do I need to know before", "get me ready for".