AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Concept

skill-gaia-computer-technologies-architecture-skills-concept · by gaia-computer-technologies

Route a concept-phase task to the right skill, and show the toolkit menu. Use when an architect says "help me with a concept", "where do I start", "what can this do", or describes a project without naming a skill. Maps the request to the right concept-design skill (design-brief, site-context, programme-schedule, material-palette, space-feel, concept-parti, concept-narrative, render-prompt, preced…

No reviews yet
0 installs
31 views
0.0% view→install

Install

$ agentstack add skill-gaia-computer-technologies-architecture-skills-concept

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-gaia-computer-technologies-architecture-skills-concept)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Concept? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Concept (router + menu)

The front door to the concept-design toolkit. Point a request at the right skill, or show what's available. For open-ended, multi-step work, prefer the concept-architect agent, which runs the whole arc; use this skill for a quick "which one do I want?"

When to use

  • The architect describes a project or task but hasn't named a skill.
  • Someone asks "what can this do?" or "where do I start?"
  • You need to hand off to a single specific skill.

How to route

Read the request, name the one or two skills that fit, say why in a line, and hand off. If the work spans several, suggest the sequence (or the agent).

| The architect wants to… | Skill | |---|---| | Turn notes / a client meeting into a structured brief | design-brief | | Read a site's opportunities and constraints from its facts | site-context | | Build or check an area schedule / schedule of accommodation | programme-schedule | | Find the organising idea / concept options for a blank page | concept-parti | | Choose a cohesive, specifiable material palette | material-palette | | Describe how a space feels (light, threshold, atmosphere) | space-feel | | Write the design rationale / project statement for an audience | concept-narrative | | Craft a prompt for an AI render | render-prompt | | Gather verifiable precedents / case studies | precedent-study | | Pressure-test a scheme before a pin-up | design-critique |

A natural order (adapt — most projects use a subset)

design-briefsite-contextprogramme-scheduleconcept-partimaterial-palette → (space-feel) → concept-narrativerender-prompt, with precedent-study feeding in wherever references help and design-critique as the checkpoint before presenting.

The house rules (apply to every skill here)

  • Concept phase only — upstream of BIM, code, and specification.
  • Never fabricate a precedent, citation, code, benchmark, or number. Flag what needs verifying.
  • Show the basis of any figure. Say "appears consistent with," never "complies."
  • One strong direction beats five weak ones.

What you don't do

  • Don't do the downstream work yourself — route to the skill, don't reinvent it inline.
  • Don't route to more than two skills at once. If it's genuinely multi-step, name the sequence or hand to the agent.

Source & license

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

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

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.