architect
Given a PRD, produces an implementation architecture: file tree, component breakdown, data model, and a phased build plan with end conditions that Archon can…
Skill by mayankjain1815-commits
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/mayankjain1815-commits-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
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 Archon can execute directly. Multi-candidate evaluation for key decisions.
- License
- MIT
- Instructions
- 164 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- no-prd.md · __benchmarks__/
- with-direction.md · __benchmarks__/
SKILL.md (first lines)
# /architect — Implementation Architecture from PRD
## When to Use
**Don't use when:** you already have an architecture and want to implement it (use /marshal or /archon); you need a PRD first (use /prd before /architect).
- After /prd produces an approved PRD (greenfield or feature mode)
- When the user has a clear direction + existing codebase (no PRD needed)
- When /do routes a build request
- When the user has a spec and wants a build plan
## Inputs
One of:
1. A PRD file path (from /prd) — preferred, contains structured requirements
2. A user-provided spec or description + an existing codebase — sufficient
3. Neither — suggest /prd first, but don't hard-gate. If the user has a clear
direction ("add auth to my app"), that + the existing code IS the input.
## Mode Detection
**Greenfield mode**: PRD exists with `Mode: greenfield`, or no existing source files.
Produces a complete architecture from scratch.
**Feature mode**: PRD exists with `Mode: feature`, OR the user describes a feature
and the project has existing source files. The architecture describes changes to
existing code, not a standalone system.
In feature mode:
- Read the existing file tree FIRST — understand the current architecture before planning changes
- Read key files (package.json, tsconfig, main entry points, existing patterns)
- The File Tree section shows ONLY new and modified files, not the entire project
- 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"
- The Risk Register includes "regression in existing functionality" as a default risk
## Protocol
### Step 1: READ
**If PRD exists**, read it. Extract:
- Core features (the numbered list)
- Technical decisions (stack choices)
- End conditions (what "done" looks like)
- Out of scope (what NOT to build)
- Integration points (feature mode)
**If no PRD**, read the codebase instead:
- Scan the file tree for structure and conventions
- Read package.json / equivalent for dependencies and scripts
- Read the main entry point(s) to understand the architecture
- Use the user's description as the feature spec
- Infer end conditions from the description ("add auth" → "protected routes return 401 without token")
### Step 2: EVALUATE OPTIONS (for non-trivial decisions)
For decisions with multiple valid approaches — state management, API structure, auth pattern, DB schema, routing — generate 2-3 candidates. Assess each on complexity, risk, maintainability, and LLM-friendliness. Pick the winner and document why. Reject alternatives with reasoning.
Simple decisions (file naming, folder structure, CSS) don't need this — use the PRD's stack choices and move on.
### Step 3: PRODUCE
Write to `.planning/architecture-{slug}.md`:
```markdown
# Architecture: {App Name}
> PRD: .planning/prd-{slug}.md | Date: {ISO date}
## File Tree
{Greenfield: complete file tree for v1, every file listed.
Feature mode: ONLY new (+) and modified (~) files.}
## Component Breakdown
### Feature: {name}
- Files: | Dependencies: | Complexity: {low/medium/high}
## Data Model
### {Entity name}
- Fields: {name: type} | Relationships: {connections}
{Omit section if no database.}
## Key Decisions
### {Decision}: {chosen approach}
- **Chosen**: {approach} — {reasoning}
- **Rejected**: {alternative} — {why not}
## Build Phases
### Phase N: {name}
- **Goal**: {one sentence}
- **Files**: | **Dependencies**: {or "none"}
- **End Conditions**: [ ] {machine-verifiable}
## Phase Dependency Graph
{Text format: Phase 1 → Phase 2 → Phase 3 / Phase 3 + 4 → Phase 5}
## Risk Register
1. {risk}: {mitigation}
2. {risk}: {mitigation}
3. {risk}: {mitigation}
## Deployment Strategy
{Skip if "deploy later" or static-only.}
- **Platform**: | **Method**: | **Environment variables**: | **Pre-deploy checks**:
{Final phase is "Deploy" when a platform is specified. A failed deploy does NOT fail the campaign.}
```
### Step 4: CONNECT TO CAMPAIGN
Each build phase becomes a campaign phase; end conditions carry over; the dependency graph determines ordering; parallel-safe phases flagged for Fleet.
Present summary to user (file count, phase count, key decisions, estimated complexity) and ask: "Ready to build? This will create an Archon campaign." If approved, write the campaign file.
### Step 5: HANDOFF
```
---HANDOFF---
- Architecture: {app name}
- Document: .planning/architecture-{slug}.md
- Phases: {count}From mayankjain1815-commits/CITADEL, MIT.
More from mayankjain1815-commits/CITADEL
- 0.519score
daemon
mayankjain1815-commits
Continuous autonomous operation mode.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
grill
mayankjain1815-commits
Relentless one-question-at-a-time interview that sharpens a vague plan or design into shared understanding before any build.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
decision-map
mayankjain1815-commits
Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
evolve
mayankjain1815-commits
Research-driven multi-cycle improvement director.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
create-skill
mayankjain1815-commits
Creates new skills from the user's repeating patterns.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
fleet
mayankjain1815-commits
Parallel campaign orchestrator.
SkillCFreshness: C★ 4Claude Code +9 - 0.516score
design
mayankjain1815-commits
Generates and maintains a design manifest for visual consistency.
SkillCFreshness: C★ 4Claude Code +9 - 0.516score
do
mayankjain1815-commits
Unified router that auto-routes user intent to the right orchestrator or skill.
SkillCFreshness: C★ 4Claude Code +9 - 0.516score
doc-gen
mayankjain1815-commits
Documentation generator with three modes: function-level (JSDoc/docstrings), module-level (directory READMEs), and API reference (endpoints/exports).
SkillCFreshness: C★ 4Claude Code +9 - 0.516score
experiment
mayankjain1815-commits
Automated optimization loop with scalar fitness function.
SkillCFreshness: C★ 4Claude Code +9 - 0.516score
archon
mayankjain1815-commits
Autonomous multi-session campaign agent.
SkillCFreshness: C★ 4Claude Code +9 - 0.516score
ascii-diagram
mayankjain1815-commits
Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow.
SkillCFreshness: C★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 11, 2026 (4 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 mayankjain1815-commits
- 0.519score
evolve
mayankjain1815-commits
Research-driven multi-cycle improvement director.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
fleet
mayankjain1815-commits
Parallel campaign orchestrator.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
daemon
mayankjain1815-commits
Continuous autonomous operation mode.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
decision-map
mayankjain1815-commits
Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
create-skill
mayankjain1815-commits
Creates new skills from the user's repeating patterns.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
grill
mayankjain1815-commits
Relentless one-question-at-a-time interview that sharpens a vague plan or design into shared understanding before any build.
SkillCFreshness: C★ 4Claude Code +9
Cite this page
architect skill. Agent Mart. https://agentmart.dev/skills/mayankjain1815-commits-architect (last updated 2026-10-24)