architect
Given a PRD, produces an implementation architecture: file tree, component breakdown, data model, and a phased build plan with end conditions that a campaign…
Skill by special-place-administrator
Chalk Labs
Need help deploying architect?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/special-place-administrator-architect
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: frontend, data, marketing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/architect
What's inside
- Skill name
architect- Description
- Given a PRD, produces an implementation architecture: file tree, component breakdown, data model, and a phased build plan with end conditions that a campaign orchestrator can execute directly. Multi-candidate evaluation for key decisions.
- License
- MIT
- Instructions
- 139 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Identity
Architect skill converts a PRD into a buildable plan. It decides HOW to implement
what the PRD describes. Its output is a campaign-ready architecture document.
# When to Use
- After a PRD is approved (greenfield or feature mode)
- When the user has a clear direction + existing codebase
- When the user has a spec and wants a build plan
# Inputs
One of:
1. A PRD file path — preferred, contains structured requirements
2. A user-provided spec + existing codebase — sufficient
3. Neither — suggest creating a PRD first, but don't hard-gate
# Mode Detection
**Greenfield mode**: PRD with `Mode: greenfield`, or no existing source files.
Produces a complete architecture from scratch.
**Feature mode**: PRD with `Mode: feature`, OR the user describes a feature
and the project has existing source files.
In feature mode:
- Read the existing file tree FIRST
- File Tree section shows ONLY new and modified files
- Phases include a Phase 0: "Baseline" that records current typecheck/test state
- Every phase's end conditions include "no new typecheck errors" and "existing tests pass"
# Protocol
## Step 1: READ
**If PRD exists**, read it. Extract core features, technical decisions, end conditions, out of scope, integration points.
**If no PRD**, read the codebase. Scan file tree, read package.json/equivalent, read main entry points. Use the user's description as the feature spec.
## Step 2: EVALUATE OPTIONS
For any architectural decision where multiple valid approaches exist:
1. Generate 2-3 candidate approaches
2. For each candidate, assess: complexity, risk, maintainability, LLM-friendliness
3. Pick the winner. Document why.
Key decisions warranting multi-candidate evaluation:
- State management approach
- API structure
- Auth implementation pattern
- Database schema design
- Routing strategy
## Step 3: PRODUCE
Write to `.citadel/research/architecture-{slug}.md`:
```markdown
# Architecture: {App Name}
> PRD: .citadel/research/prd-{slug}.md
> Date: {ISO date}
## File Tree
{Greenfield: complete file tree. Feature mode: ONLY new and modified files.}
## Component Breakdown
### Feature: {name}
- Files: {list}
- Dependencies: {what must exist first}
- Complexity: {low/medium/high}
## Data Model
### {Entity name}
- Fields: {name: type}
- Relationships: {connections}
## Key Decisions
### {Decision}: {What was chosen}
- **Chosen**: {approach} — because {reasoning}
- **Rejected**: {alternative} — because {why not}
## Build Phases
### Phase 1: {name}
- **Goal**: {one sentence}
- **Files**: {files created or modified}
- **Dependencies**: {what must exist first, or "none"}
- **End Conditions**:
- [ ] {machine-verifiable condition}
## Phase Dependency Graph
Phase 1 → Phase 2 → Phase 3
## Risk Register
1. {risk}: {mitigation}
2. {risk}: {mitigation}
3. {risk}: {mitigation}
```
## Step 4: CONNECT TO CAMPAIGN
Convert the architecture into a campaign-ready format:
1. Each build phase becomes a campaign phase
2. End conditions become Phase End Conditions
3. Dependency graph determines phase ordering
4. Parallel-safe phases get flagged for potential fleet execution
Present the summary to the user and ask for approval.
## Step 5: HANDOFF
```
---HANDOFF---
- Architecture: {app name}
- Document: .citadel/research/architecture-{slug}.md
- Phases: {count}
- Estimated complexity: {low/medium/high}
- Next: Campaign ready to executeFrom special-place-administrator/citadel_codex, MIT.
More from special-place-administrator/citadel_codex
- 0.409score
create-skill
special-place-administrator
Creates new skills from the user's repeating patterns.
SkillDFreshness: DClaude Code +9 - 0.406score
autopilot
special-place-administrator
Intake-to-delivery pipeline.
SkillDFreshness: DClaude Code +9 - 0.406score
do
special-place-administrator
Unified router that auto-routes user intent to the right orchestrator or skill.
SkillDFreshness: DClaude Code +9 - 0.406score
fleet
special-place-administrator
Parallel campaign coordinator.
SkillDFreshness: DClaude Code +9 - 0.406score
live-preview
special-place-administrator
Mid-build visual verification loop.
SkillDFreshness: DClaude Code +9 - 0.406score
marshal
special-place-administrator
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work.
SkillDFreshness: DClaude Code +9 - 0.406score
postmortem
special-place-administrator
Auto-generates a structured postmortem from a completed campaign.
SkillDFreshness: DClaude Code +9 - 0.406score
prd
special-place-administrator
Generates a Product Requirements Document from a natural language app description.
SkillDFreshness: DClaude Code +9 - 0.406score
qa
special-place-administrator
Browser-based QA verification.
SkillDFreshness: DClaude Code +9 - 0.406score
refactor
special-place-administrator
Safe multi-file refactoring with automatic rollback.
SkillDFreshness: DClaude Code +9 - 0.406score
research
special-place-administrator
Focused research investigations.
SkillDFreshness: DClaude Code +9 - 0.406score
research-fleet
special-place-administrator
Parallel research using Fleet wave mechanics.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 27, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from special-place-administrator
- 0.409score
create-skill
special-place-administrator
Creates new skills from the user's repeating patterns.
SkillDFreshness: DClaude Code +9 - 0.406score
live-preview
special-place-administrator
Mid-build visual verification loop.
SkillDFreshness: DClaude Code +9 - 0.406score
do
special-place-administrator
Unified router that auto-routes user intent to the right orchestrator or skill.
SkillDFreshness: DClaude Code +9 - 0.406score
fleet
special-place-administrator
Parallel campaign coordinator.
SkillDFreshness: DClaude Code +9 - 0.406score
autopilot
special-place-administrator
Intake-to-delivery pipeline.
SkillDFreshness: DClaude Code +9 - 0.406score
archon
special-place-administrator
Multi-session campaign orchestrator.
SkillDFreshness: DClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get architect running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
architect skill. Agent Mart. https://agentmart.dev/skills/special-place-administrator-architect (last updated 2026-10-24)