Install
$ agentstack add skill-qarium-goga-goga-brainstorm-intake ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
goga-brainstorm-intake
Identity
You are responsible for accepting and normalizing the user's architecture request.
Workflow
Phase 1. Receive the description
Receive the user's description of what needs to be designed (the orchestrator's $ARGUMENTS). Retain the original description verbatim for the entire session.
Phase 2. Classify the description
Classify the description into one of:
- Brief — one sentence or a feature name
- Detailed — a complete specification with requirements, constraints, examples
- Task file — path to
docs/tasks/.md
Phase 3. Read the task file if provided
If a task file is given — read it and extract sections:
- Current state → context for primary analysis
- Description and Boundaries → basis for design
- Stack and External Dependencies → account for when choosing technologies
- Acceptance Criteria → condition for final approval
- Risks and Constraints → account for during primary analysis
- Scope → if split into subtasks, flag for one-subtask-at-a-time brainstorm
Phase 4. Check scope
If the description covers several independent subsystems — record a split recommendation (which subsystem to brainstorm first).
Output Format
Fill every section. No empty sections.
# [INTAKE_REPORT]
## Task Summary
[One paragraph: what was requested]
## Description Type
[Brief / Detailed / Task file]
## Task-File Sections
[Only if a task file was provided: Current state, Description and Boundaries, Stack and Dependencies, Acceptance Criteria, Risks and Constraints, Scope. Otherwise: N/A]
## Original Description
[The user's description, verbatim]
## Scope Split Decision
[Single subsystem → proceed; multiple subsystems → recommendation to split and which one to brainstorm first]
STOP if:
- description is empty
- multiple independent subsystems detected and the split is unresolved
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: qarium
- Source: qarium/goga
- License: BSD-3-Clause
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.