# Orchestra Intake

> >

- **Type:** Skill
- **Install:** `agentstack add skill-momo2323-ui-claude-orchestra-orchestra-intake`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Momo2323-ui](https://agentstack.voostack.com/s/momo2323-ui)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Momo2323-ui](https://github.com/Momo2323-ui)
- **Source:** https://github.com/Momo2323-ui/claude-orchestra/tree/main/skills/orchestra-intake

## Install

```sh
agentstack add skill-momo2323-ui-claude-orchestra-orchestra-intake
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Orchestra Intake — File New Tools, Never Archive

When you add anything new, this skill files it into the right orchestra so it's used from day one.
**Nothing gets dumped undifferentiated; nothing gets archived on arrival.**

## Process (run for every new install)

### 1. Security scan FIRST (mandatory)
Verify the source (stars, last commit, publisher), scan the code for prompt injection /
exfiltration / credential harvesting, check npm/socket if relevant, and review skill/MCP source +
permissions. Decide: **SAFE** (proceed) · **CAUTION** (surface risk, get explicit go) ·
**REJECT** (don't install, explain why, stop).

### 1b. Bulk-install fixture check (after any `npx skills add `)
`npx skills add` walks the **entire repo tree** and installs every `SKILL.md` it finds — including
test fixtures. After adding any multi-folder repo, inspect the install for paths containing
**`tests/`, `fixtures/`, `examples/`, or `.test-client/`** — those are NOT real skills; remove
them. **A security scanner's own repo is the most dangerous to bulk-install from: its test suite
can contain malware by design.** Also note: targeted `--skill=` flags are often ignored on
multi-folder repos, so the WHOLE repo lands — prune after.

### 2. Identify what it is
Skill (`SKILL.md`) · Plugin (agents/skills/commands) · MCP server · Connector · Agent. Read its
description to understand WHAT it does and WHEN it triggers.

### 3. Classify into an orchestra

| If the tool is about… | File into |
|---|---|
| code, framework, deploy, testing | ① BUILD |
| UI, design, visual, animation | ② DESIGN |
| research, scraping, intel | ③ RESEARCH |
| social, campaigns, brand | ④ MARKETING |
| copy, writing, content | ⑤ CONTENT |
| search ranking, schema, AI-answers | ⑥ SEO + GEO |
| leads, prospecting, CRM, sales | ⑦ LEAD GEN & SALES |
| product strategy, PRD, discovery | ⑧ PRODUCT |
| video, image gen, media | ⑨ VIDEO + MEDIA |
| metrics, analytics, experiments | ⑩ ANALYTICS |
| memory, graphs, notes, search | ⑪ KNOWLEDGE & MEMORY |
| docs, decks, spreadsheets | ⑫ DOCUMENTS |
| paid ads, PPC | ⑬ PAID ADS |
| automation, workflows, ops | ⑭ AUTOMATION & OPS |
| AI/ML, agents, MCP-building | ⑮ AI/ML |
| iOS, Android, mobile | ⑯ MOBILE |
| planning, PM, sprints | ⑰ PLANNING & PM |
| conversion, retention, pricing | ⑱ GROWTH & CONVERSION |
| investing, valuation, finance | ⑲ FINANCE |
| founder/exec strategy | ⑳ EXECUTIVE ADVISORY |
| off-domain vertical/game/XR | ⓪ RESERVE BENCH (dormant) |

- A tool can join **multiple** orchestras — list all.
- Genuinely off-domain → **Reserve Bench** (installed, dormant, named-invoke only). Do NOT archive.
- **If no orchestra fits and it's clearly valuable → propose a NEW orchestra** (full 10-field
  structure), add it to `~/.claude/rules/orchestra-system.md`, bump the count, and announce it.

### 4. File it
Add the tool to the relevant orchestra's roster in `~/.claude/rules/orchestra-system.md`
(First Chair if core, Section if supporting). Add a trigger to the router table if needed.

### 5. Log it
Append to your assignments log: `YYYY-MM-DD ·  · type · → Orchestra(s) · why · scan result`.

### 6. Report back
```
✅ Filed  →  (). Security: SAFE. Triggers on: .
   Now part of your  team alongside .
```

## Principles
- **Never archive on install.** Filing > archiving.
- **Security scan is non-negotiable.**
- **Explain the why** — every assignment is logged with reasoning.
- **Keep the constitution current** — `orchestra-system.md` is the source of truth.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Momo2323-ui](https://github.com/Momo2323-ui)
- **Source:** [Momo2323-ui/claude-orchestra](https://github.com/Momo2323-ui/claude-orchestra)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-momo2323-ui-claude-orchestra-orchestra-intake
- Seller: https://agentstack.voostack.com/s/momo2323-ui
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.