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/teaglebuilt-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
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
- universal architecture
- License
- MIT
- Instructions
- 475 lines in SKILL.md · view on GitHub
Files (7)
- SKILL.md
- analysis-procedure.md · references/
- diagram-guide.md · references/
- patterns.md · references/
- quality-attributes.md · references/
- adr-template.md · templates/
- tradeoff-matrix.md · templates/
SKILL.md (first lines)
# Software Architecture Skill
> Use this skill when making architectural decisions, reviewing system design, analyzing codebase structure, generating architecture diagrams, or evaluating pattern fitness for a project.
KNOWLEDGE_PATH: $HOME/github/teaglebuilt/knowledge
## Procedures
This skill provides five core capabilities. Load the relevant resource before executing.
### 1. Analyze Codebase Architecture
When asked to assess or understand an existing codebase's architecture:
1. Read `references/analysis-procedure.md` for the full analysis playbook
2. Map the project structure, entry points, and dependency graph
3. Identify the dominant patterns in use (layered, hexagonal, vertical slice, etc.)
4. Measure coupling and cohesion indicators
5. Produce a structured assessment with findings and recommendations
**Key commands to run:**
```bash
# Dependency/import analysis (JS/TS)
grep -rn "^import\|^from\|require(" --include="*.ts" --include="*.tsx" --include="*.js" | head -200
# Package dependency graph (monorepo)
cat package.json | jq '.dependencies, .devDependencies'
find . -name "package.json" -not -path "*/node_modules/*" -exec jq '{name: .name, deps: .dependencies}' {} \;
# Module boundary detection
find . -name "index.ts" -o -name "index.js" | grep -v node_modules | sort
# Circular dependency check (if tool available)
npx madge --circular --extensions ts,tsx src/
# Python projects
grep -rn "^import\|^from" --include="*.py" | head -200
cat requirements.txt 2>/dev/null || cat pyproject.toml 2>/dev/null
# Go projects
grep -rn "^import" --include="*.go" | head -200
cat go.mod
```
### 2. Evaluate Architecture Options
When comparing patterns or making a structural decision:
1. Read `references/patterns.md` for the pattern decision matrices
2. Read `references/quality-attributes.md` for the scoring framework
3. Identify the top 3-5 quality attributes that matter most for this project
4. Score 2-3 candidate architectures against those attributes
5. Produce a tradeoff analysis using `templates/tradeoff-matrix.md`
### 3. Generate Architecture Decision Record (ADR)
When a decision needs to be documented:
1. Read `templates/adr-template.md`
2. Read any documentation in `docs/` folder that applies to the input.
3. Fill in all sections: context, decision drivers, considered options, decision outcome, consequences
4. Save to the project's ADR directory (typically `docs/adr/` or `.docs/architecture/decisions/`)
5. Name with sequential numbering: `NNNN-short-description.md`
### 4. Generate Architecture Diagrams
When visualizing architecture:
1. Read `references/diagram-guide.md` for C4, sequence, and deployment diagram patterns
2. Use Mermaid syntax for all diagrams
3. Start at the appropriate C4 level:
- **Context** — System and its external actors/systems
- **Container** — High-level technical building blocks
- **Component** — Internal structure of a container
- **Code** — Class/module level (rarely needed)
4. Include a legend and brief description with each diagram
### 5. Design New Architecture
When designing from scratch or planning a migration:
1. Read `references/patterns.md` for pattern options
2. Read `references/quality-attributes.md` for prioritization
3. Read `references/analysis-procedure.md` section on migration strategies (if migrating)
4. Load any relevant **domain references** (see below)
5. Follow this sequence:
- Clarify requirements and constraints (ask if not provided)
- Identify bounded contexts / domain boundaries
- Select structural pattern(s)
- Select communication pattern(s)
- Select data pattern(s)
- Define deployment strategy
- Document with ADR + diagrams
- Define fitness functions to protect architectural intent
---
## Resource Routing
Always log to the console which resources are being used.
### Universal Frameworks
| Task | Resource to Read |
|------|-----------------|
| Analyzing existing code | `references/analysis-procedure.md` |
| Comparing patterns | `references/patterns.md` |
| Scoring options | `references/quality-attributes.md` |
| Creating diagrams | `references/diagram-guide.md` |
| Documenting decisions | `templates/adr-template.md` |
| Comparing options side-by-side | `templates/tradeoff-matrix.md` |
### Skill Reference
Always consider using skills that are relevant any way and always show which skills are being used.
### Domain ReferencesFrom teaglebuilt/skillz, MIT.
More from teaglebuilt/skillz
- 0.524score
github-repo-explore
teaglebuilt
Guide for searching and exploring external GitHub repositories using the gh CLI.
SkillBFreshness: BClaude Code +9 - 0.520score
youtube-to-markdown
teaglebuilt
Use when user asks YouTube video extraction, get, fetch, transcripts, subtitles, or captions.
SkillBFreshness: BClaude Code +9 - 0.278score
n8n-workflow
teaglebuilt
No description from the publisher yet.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 20, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/teaglebuilt/skillz
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from teaglebuilt
- 0.524score
github-repo-explore
teaglebuilt
Guide for searching and exploring external GitHub repositories using the gh CLI.
SkillBFreshness: BClaude Code +9 - 0.520score
youtube-to-markdown
teaglebuilt
Use when user asks YouTube video extraction, get, fetch, transcripts, subtitles, or captions.
SkillBFreshness: BClaude 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/teaglebuilt-architect (last updated 2026-10-24)