team-foundation
Team Workflow OS — shared clarc setup for engineering teams. Covers shared rules distribution, private skill packs, team sync patterns, onboarding, and multi-developer conventions.
Best use case
team-foundation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Team Workflow OS — shared clarc setup for engineering teams. Covers shared rules distribution, private skill packs, team sync patterns, onboarding, and multi-developer conventions.
Teams using team-foundation should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/team-foundation/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How team-foundation Compares
| Feature / Agent | team-foundation | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Team Workflow OS — shared clarc setup for engineering teams. Covers shared rules distribution, private skill packs, team sync patterns, onboarding, and multi-developer conventions.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Team Foundation
Patterns and workflows for running clarc as a shared engineering team OS — consistent rules, private skill packs, and synchronized conventions across all developers.
## When to Activate
- Setting up clarc for a team of 2+ engineers
- User runs `/team-sync`
- Onboarding a new developer to a team using clarc
- Distributing private rules or skills across a team
- Defining team-wide workflow conventions
- Creating a `company-clarc` private repository to house organization-specific rules and skills
- Troubleshooting why a team member's Claude session does not pick up the shared rules after an update
## Team Installation Model
### Standard Team Setup
```bash
# Team lead: create private rules + skills
mkdir -p ~/.company/private-rules ~/.company/private-skills
# Install for all team members via shared command
./install.sh --team-mode \
--company-prefix yourco \ # replace with your company/team prefix
--private-rules ~/.company/private-rules \
--private-skills ~/.company/private-skills \
typescript
# Each developer runs the same command
# → ~/.claude/rules/yourco/ (private rules)
# → ~/.claude/skills/yourco/ (private skills)
```
### Distribution via Git
**Recommended:** Store team config in a private git repo:
```
company-clarc/
├── install-team.sh # wrapper: calls clarc install.sh + team flags
├── private-rules/
│ ├── api-standards.md # company API conventions
│ ├── security-policy.md # internal security requirements
│ └── code-review.md # review checklist
├── private-skills/
│ ├── deploy-flow/SKILL.md # company-specific deploy workflow
│ └── pr-process/SKILL.md # internal PR process
└── README.md
```
`install-team.sh`:
```bash
#!/usr/bin/env bash
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
CLARC_DIR="${HOME}/.clarc"
if [[ ! -d "$CLARC_DIR" ]]; then
git clone https://github.com/marvinrichter/clarc.git "$CLARC_DIR"
fi
bash "$CLARC_DIR/install.sh" \
--team-mode \
--company-prefix yourco \
--private-rules "$SCRIPT_DIR/private-rules" \
--private-skills "$SCRIPT_DIR/private-skills" \
"$@"
```
New developer onboarding:
```bash
git clone git@github.com:yourco/company-clarc.git
cd company-clarc && ./install-team.sh typescript
```
## Private Rules Structure
Private rules follow the same format as clarc rules:
```
private-rules/
├── api-standards.md # REST/GraphQL API conventions
├── security-policy.md # Security requirements specific to company
├── code-review.md # Custom review checklist
├── deployment.md # Deployment process
└── incident-response.md # On-call and incident protocols
```
Each file is a plain Markdown file. Claude loads them from `~/.claude/rules/<prefix>/` automatically.
## Private Skills Structure
Private skills use the standard clarc SKILL.md format:
```
private-skills/
├── deploy-flow/
│ └── SKILL.md # "How to deploy at Acme"
├── feature-flags/
│ └── SKILL.md # "Company feature flag process"
└── data-access/
└── SKILL.md # "Internal data access patterns"
```
## Team Sync Workflow
Run `/team-sync` to:
1. **Pull latest clarc** — `cd ~/.clarc && git pull`
2. **Pull team config** — `cd ~/company-clarc && git pull`
3. **Re-run team install** — apply any new private rules or skills
4. **Report diff** — what changed since last sync
## Team Conventions
### Shared CLAUDE.md
Add to the project `CLAUDE.md`:
```markdown
## Team clarc Setup
This project uses company-clarc. Install with:
cd ~/company-clarc && ./install-team.sh typescript
Team rules are in `~/.claude/rules/yourco/`:
- api-standards.md — REST API conventions
- security-policy.md — security requirements
Private skills available: /deploy-flow, /pr-process
```
### Preventing Rule Conflicts
- Company prefix isolates private rules: `~/.claude/rules/yourco/`
- Private rules never overwrite clarc common rules
- Developers can still override any rule with their own version
## Onboarding Checklist
```
[ ] Clone company-clarc
[ ] Run ./install-team.sh <language>
[ ] Verify: ls ~/.claude/rules/yourco/
[ ] Verify: ls ~/.claude/agents/ (should list 50+ agents)
[ ] Read CLAUDE.md in the project repository
[ ] Enable Memory Bank: mkdir .clarc (in project root)
[ ] Test: open Claude Code, run /doctor
```Related Skills
team-process
Engineering team process patterns: OKR definition and scoring, sprint planning and retros, roadmap structuring (now/next/later), feature breakdown into user stories with acceptance criteria, and engineering metrics (DORA, velocity). For product lifecycle see product-lifecycle skill.
foundation-models-on-device
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.
zero-trust-patterns
Zero-Trust security patterns — mTLS between microservices (Istio/SPIFFE), SPIRE workload identity, OPA/Envoy authorization, NetworkPolicy default-deny-all, short-lived credentials, service mesh security, and Kubernetes RBAC hardening.
wireframing
Wireframing and prototyping workflow: fidelity levels (lo-fi sketch → mid-fi wireframe → hi-fi prototype), tool selection (Figma, Excalidraw, Balsamiq), user flow diagrams, wireframe annotation standards, information architecture (IA) mapping, and the handoff from wireframe to visual design. For developers who need to communicate UI structure before writing code.
webrtc-patterns
WebRTC patterns — peer connection setup, ICE/STUN/TURN configuration, signaling server design, SFU vs mesh topology, screen sharing, media track management, and reconnect/ICE restart handling.
webhook-patterns
Webhook patterns for receiving, verifying (HMAC), and idempotently processing third-party events. Covers Stripe, GitHub, and generic webhook patterns, delivery guarantees, retry handling, and testing.
web-performance
Web performance optimization: Core Web Vitals (LCP, CLS, INP), Lighthouse CI with budget configuration, bundle analysis (webpack-bundle-analyzer, vite-bundle-visualizer), hydration performance, network waterfall reading, image optimization (WebP/AVIF, srcset), and font performance.
wasm-performance
WebAssembly performance: wasm-opt binary optimization, size reduction (panic=abort, LTO, strip), profiling WASM in Chrome DevTools, memory management (linear memory, avoiding GC pressure), SIMD, and multi-threading with SharedArrayBuffer.
wasm-patterns
WebAssembly patterns: wasm-pack, wasm-bindgen (JS↔Wasm interop), WASI, Component Model, wasm-opt, Rust-to-WASM compilation, JS integration (web workers, streaming instantiation), and production deployment (CDN, Content-Type headers).
visual-testing
Visual Regression Testing: tool comparison (Chromatic/Percy/Playwright screenshots/BackstopJS), pixel-diff vs AI-based comparison, baseline management, flakiness strategies (masks, tolerances, waitForLoadState), CI integration with GitHub Actions, and Storybook integration.
visual-identity
Brand identity development: color palette construction (primary/secondary/semantic/neutral), logo concept brief writing, typeface pairings, brand voice definition, mood board direction, and Brand Guidelines document structure. Use when establishing or evolving a visual brand — not for implementing existing tokens.
ux-micro-patterns
UX micro-patterns for every product state: Empty States, Loading States (skeleton screens, spinners, optimistic UI), Error States, Success States, Confirmation Dialogs, Onboarding Flows, and Progressive Disclosure. These patterns apply to every feature — done wrong, they're the biggest source of user confusion.