setup-team
Configure SDLC team formation and SDLC method for this project.
Skill by SteveGJones
Chalk Labs
Need help deploying setup-team?
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/stevegjones-setup-team
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/setup-team
What's inside
- Skill name
setup-team- Description
- Configure SDLC team formation and SDLC method for this project. Asks the four-option SDLC method question (solo / single-team / programme / assured), then recommends and installs team plugins based on project type, language, tech stack, and support needs.
- License
- MIT
- Instructions
- 560 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- body: 560 lines (spec recommends under 500)
Files (1)
- SKILL.md
SKILL.md (first lines)
# SDLC Team Setup
Configure the right agent team for this project by selecting an SDLC method, a project type, and installing the matching team plugins.
## Steps
0. **Pre-check: inventory what's already installed**
Before making any recommendations, check what plugins, agents, and skills are already available — both globally and for this project.
**0a. Check installed plugins:**
- Read `~/.claude/settings.json` → `enabledPlugins` field (global installs)
- Read `.claude/settings.json` (project-level) → `enabledPlugins` field (if it exists)
- Merge both lists. For each `sdlc-*@ai-first-sdlc` entry: record as installed.
- Also check for `sdlc-knowledge-base@ai-first-sdlc`, `sdlc-programme@ai-first-sdlc`, and `sdlc-assured@ai-first-sdlc` specifically — these may be relevant to the SDLC method question in step 3.
**0b. Check available agents:**
- Glob `.claude/agents/**/*.md` (project-level agents)
- Note which come from installed plugins vs which are project-local
**0c. Check available skills:**
- List currently registered skills (the set Claude Code can see)
**0d. Present the pre-check results** to the user before any recommendations:
```
Current state:
Installed SDLC plugins:
✓ sdlc-core@ai-first-sdlc (global)
✓ sdlc-team-common@ai-first-sdlc (global)
✗ sdlc-team-fullstack@ai-first-sdlc
✗ sdlc-lang-python@ai-first-sdlc
✗ sdlc-knowledge-base@ai-first-sdlc
✗ sdlc-programme@ai-first-sdlc
✗ sdlc-assured@ai-first-sdlc
Available agents: N (from installed plugins)
Available skills: M
I'll only recommend what you don't already have.
```
**0e. Record the pre-check state** for use in later steps — the recommendation output (step 8) will mark already-installed plugins with `✓ (already installed)` instead of install commands, and the install command list (step 9) will exclude them.
1. **Check current team configuration**
Look for `.sdlc/team-config.json` in the project root (or `.claude/team-config.json` as a fallback). If it exists, display the current formation **and the recorded `sdlc_method`** (if present) and ask if the user wants to reconfigure.
2. **Ask the user what kind of project this is** (present as multiple choice):
- **A. Full-stack web application** — frontend + backend + API + DevOps
- **B. AI/ML system** — AI architects + prompt engineers + RAG designers
- **C. Cloud infrastructure** — cloud + containers + SRE + observability
- **D. API/microservices** — API + backend + integration + performance
- **E. Security-focused** — security + compliance + privacy
- **G. iOS app** — Apple HIG design + cross-platform mobile architecture & interaction UX
- **H. Android app** — Material Design 3 + cross-platform mobile architecture & interaction UX
- **I. Cross-platform mobile** — both iOS and Android design + shared mobile base
- **F. Custom** — pick individual team plugins
3. **Ask about SDLC method (delivery structure)**
The framework supports **four SDLC delivery structures**. This question is **orthogonal** to step 2 — step 2 picks team plugins (what kind of system); step 3 picks the SDLC method bundle (what kind of delivery discipline). A regulated medical-device system could be cloud-infrastructure (project type C) AND assured (SDLC method D); an AI/ML prototype could be project type B AND solo (SDLC method B).
Present as multiple choice:
- **A. Single-team (default)** — 3–10 contributors, organic delivery, no formal phase gates. Use the base SDLC (`/sdlc-core:new-feature` workflow) with team plugins from step 2. Most projects pick this.
- **B. Solo** — 1–2 contributors, fast iteration, lightweight constitution overlay. Use the base SDLC with `/sdlc-core:commission --option solo`.
- **C. Programme (Method 1)** — 11–50 contributors across 2–5 teams, formal phase gates (requirements → design → test → code) with mandatory cross-phase review. Adds the `sdlc-programme` bundle.
- **D. Assured (Method 2)** — regulated industries (DO-178C, IEC 62304, ISO 26262, FDA 21 CFR Part 820). Bidirectional traceability, positional namespace IDs, DDD decomposition, typed evidence statuses, standard-specific exports. Adds the `sdlc-assured` bundle (v0.2.0 audit-ready at the tooling layer).
- **E. Decide later** — proceed with single-team default; user can run `/sdlc-core:commission` at any time to switch.
Default to **A** if the user presses Enter without selecting.
**Map the answer:**
| Selection | `sdlc_method` value | Bundle plugin to recommend | Post-install commission command |
|-----------|---------------------|---------------------------|--------------------------------|
| A. Single-team | `single-team` | (none — sdlc-core is sufficient) | (none — default behaviour) |
| B. Solo | `solo` | (none — sdlc-core is sufficient) | `/sdlc-core:commission --option solo` |
| C. Programme | `programme` | `sdlc-programme@ai-first-sdlc` | `/sdlc-core:commission --option programme --level production` (or `/sdlc-programme:commission-programme`) |
| D. Assured | `assured` | `sdlc-assured@ai-first-sdlc` | `/sdlc-core:commission --option assured --level production` (or `/sdlc-assured:commission-assured`) |
| E. Decide later | `undecided` | (none — defer) | (none — user runs `/sdlc-core:commission` later) |
**What to record:**
- Add `sdlc_method` to the team-config.json fields written in step 11 (e.g., `"sdlc_method": "assured"`).
- For C / D: add the bundle plugin to the install recommendation list shown in step 8. If the bundle appears in the pre-check (step 0) list as already installed, mark it `✓ (already installed)` and skip re-recommending — but **do** surface the post-install commission command in the recommendation output, since commissioning is a separate step from plugin install.
- For B / C / D: add a **"Post-install action"** line in the step 8 recommendation output advising the user to run the appropriate `/sdlc-core:commission` command after the plugin is installed (or, for B, even if no extra plugin is installed). Without this surfacing, the bundle would ship installed but uncommissioned, and the user would get validation errors with no clear diagnosis path.
- For E: record `"sdlc_method": "undecided"` so the post-check (step 13) can surface a one-line reminder that commissioning is still pending.
**If unsure, point to `docs/METHODS-GUIDE.md`** for a fuller decision tree, comparison table, trade-offs, and migration notes between methods.
4. **Map step 2 selection to recommended team plugins:**
| Selection | Plugins |
|-----------|---------|
| A. Full-stack | `sdlc-team-common`, `sdlc-team-fullstack` |
| B. AI/ML | `sdlc-team-common`, `sdlc-team-ai`, `sdlc-lang-python` |
| C. Cloud | `sdlc-team-common`, `sdlc-team-cloud` |
| D. API | `sdlc-team-common`, `sdlc-team-fullstack`, `sdlc-team-cloud` |
| E. Security | `sdlc-team-common`, `sdlc-team-security` |
| G. iOS app | `sdlc-team-common`, `sdlc-team-ios`, `sdlc-team-mobile`, `sdlc-lang-swift` |
| H. Android app | `sdlc-team-common`, `sdlc-team-android`, `sdlc-team-mobile`, `sdlc-lang-kotlin` |
| I. Cross-platform mobile | `sdlc-team-common`, `sdlc-team-ios`, `sdlc-team-android`, `sdlc-team-mobile`, `sdlc-lang-swift`, `sdlc-lang-kotlin` |
| F. Custom | `sdlc-team-common` (pre-selected) + user picks additional team plugins |
**Mobile plugins pair with the shared base.** `sdlc-team-ios` (Apple HIG) and `sdlc-team-android` (Material Design 3) each carry only their platform's design specialist; the cross-platform agents (`mobile-architect`, `mobile-ux-architect`) live once in `sdlc-team-mobile`. Always recommend the platform plugin **and** `sdlc-team-mobile` together — the marketplace has no hard dependency resolution, so this recommendation is the pairing mechanism. A cross-platform team installs both platform plugins + the single shared base (agents are never duplicated).
**`sdlc-team-common` is a near-universal default.** It contains the research-and-agent-creation pipeline (`pipeline-orchestrator`, `deep-research-agent`, `agent-builder`, `repo-knowledge-distiller`) plus cross-cutting specialists (`solution-architect`, `database-architect`, `performance-engineer`, `observability-specialist`). Every project type above includes it because:
- Discovery during setup relies on `pipeline-orchestrator` for the research → synthesis → agent-builder workflow
- Any Section C coverage gap identified during discovery requires these agents to act on
- Cross-cutting architecture decisions benefit from `solution-architect` regardless of project type
For option F (Custom), `sdlc-team-common` is pre-selected. If the user wants to deselect it, present this warning:
> ⚠️ You are deselecting `sdlc-team-common`. This plugin provides the agents required for custom agent creation (`pipeline-orchestrator`, `deep-research-agent`, `agent-builder`). Without it:From SteveGJones/ai-first-sdlc-practices, MIT.
More from SteveGJones/ai-first-sdlc-practices
- 0.643score
kb-ingest-bulk
SteveGJones
Parallel map-reduce bulk ingest for large source sets.
SkillAFreshness: A★ 41Claude Code +9 - 0.640score
kb-rebuild-indexes
SteveGJones
Rebuild the knowledge base shelf-index with hash-based change detection.
SkillAFreshness: A★ 41Claude Code +9 - 0.640score
kb-ingest-batch
SteveGJones
Drive agent-knowledge-updater over a batch of staged files in library/raw/.
SkillAFreshness: A★ 41Claude Code +9 - 0.640score
kb-query
SteveGJones
Query the project knowledge base.
SkillAFreshness: A★ 41Claude Code +9 - 0.555score
android-scaffold
SteveGJones
Scaffold a new Android app with SDLC and Play-safe defaults — Kotlin/Compose Gradle project with version catalog, convention plugins, module layout, a…
SkillCFreshness: C★ 41Claude Code +9 - 0.555score
android-signing-setup
SteveGJones
Set up Android app signing safely — generate an upload keystore, enroll in Play App Signing, and wire a Gradle release signingConfig that reads secrets from a…
SkillCFreshness: C★ 41Claude Code +9 - 0.555score
ios-ci
SteveGJones
Generate a GitHub Actions workflow for iOS — macOS runner, SPM/DerivedData caching, build, test on a simulator matrix, run the iOS pre-flight checks, and…
SkillCFreshness: C★ 41Claude Code +9 - 0.555score
android-ci
SteveGJones
Generate a GitHub Actions workflow for Android — JDK + Gradle caching, build, unit + instrumented tests, Android Lint, run the Android pre-flight checks, and…
SkillCFreshness: C★ 41Claude Code +9 - 0.555score
kb-lint
SteveGJones
Health-check the project knowledge base.
SkillCFreshness: C★ 41Claude Code +9 - 0.555score
android-play-release
SteveGJones
Validated Google Play release — runs the pre-flight checks and clears the Play policy gates, builds a signed app bundle with a git-stamped versionCode…
SkillCFreshness: C★ 41Claude Code +9 - 0.555score
council-policy
SteveGJones
Policy for the cross-model council: when to hand off to an installed sibling plugin's own slash command (`/codex:*`) versus dispatching our…
SkillCFreshness: C★ 41Claude Code +9 - 0.555score
ios-scaffold
SteveGJones
Scaffold a new iOS app with SDLC and submission-safe defaults — diffable project files, app + test targets, deployment-target policy, a git-stamped build…
SkillCFreshness: C★ 41Claude Code +9
Signals
- Stars
- 41
- Forks
- 6
- Open issues
- 37
- Last commit (this folder)
- Jul 24, 2026 (3 months ago)
- Last release
- Aug 10, 2025 (1 year 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 SteveGJones
- 0.643score
kb-ingest-bulk
SteveGJones
Parallel map-reduce bulk ingest for large source sets.
SkillAFreshness: A★ 41Claude Code +9 - 0.640score
kb-query
SteveGJones
Query the project knowledge base.
SkillAFreshness: A★ 41Claude Code +9 - 0.640score
kb-ingest-batch
SteveGJones
Drive agent-knowledge-updater over a batch of staged files in library/raw/.
SkillAFreshness: A★ 41Claude Code +9 - 0.640score
kb-rebuild-indexes
SteveGJones
Rebuild the knowledge base shelf-index with hash-based change detection.
SkillAFreshness: A★ 41Claude Code +9 - 0.555score
council-policy
SteveGJones
Policy for the cross-model council: when to hand off to an installed sibling plugin's own slash command (`/codex:*`) versus dispatching our…
SkillCFreshness: C★ 41Claude Code +9 - 0.555score
kb-lint
SteveGJones
Health-check the project knowledge base.
SkillCFreshness: C★ 41Claude 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 setup-team 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
setup-team skill. Agent Mart. https://agentmart.dev/skills/stevegjones-setup-team (last updated 2026-10-24)