This skill should be used when the user asks how to start an architecture project, which ArcKit commands to run and in what order, what workflow path to follow, how to onboard a project, or what comes next after a command. Common triggers: getting started with ArcKit, recommend a workflow, new project setup, guide me through, command sequence, next steps, arckit start.
npx claudepluginhub tractorjuice/arc-kitThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/ai-ml-path.mdreferences/data-path.mdreferences/defence-path.mdreferences/standard-path.mdreferences/uk-gov-path.mdGuides users through project onboarding using adaptive-depth questions and recommends a tailored command sequence.
<HARD-GATE> Do NOT run any `/arckit:*` commands during this process. Your only output is a recommended command plan. The user decides when and what to execute. This applies regardless of how simple the project seems. </HARD-GATE>Even experienced architects benefit from the triage. It catches blind spots — missing compliance requirements, forgotten dependencies, stakeholder gaps. The triage is fast (3-4 questions). Skip it and you risk generating artifacts in the wrong order or missing mandatory prerequisites.
A 30-command sequence helps nobody. The skill's job is to recommend the right commands for this project, in the right order. Every project is different — a compliance review needs 6 commands, not 30.
Follow these steps in order. Ask questions one at a time using AskUserQuestion. Prefer multiple-choice options.
Automatically check the project context (no questions needed):
projects/ directory exists and count projectsARC-000-PRIN-*)Based on findings, determine:
projects/ directory or empty — recommend starting from scratchDisplay a brief status summary before asking questions:
Project State: [1 project found, 4 artifacts, ~20% complete]
Or:
Project State: No project structure found. Starting fresh.
Ask these questions one at a time. Each uses AskUserQuestion with multiple-choice options.
Question 1 — Sector:
Question 2 — Project Type:
Question 3 — Current Stage:
Question 4 — Primary Goal:
Only ask these if the project triggers complexity:
Ask one at a time:
Q5 — Compliance Frameworks (multiple select):
Q6 — Procurement (if applicable):
Q7 — Strategic Analysis:
Q8 — Timeline Pressure:
Based on the answers, select the appropriate path and present the plan.
Base path selection:
| Sector Answer | Base Path |
|---|---|
| Private sector or Public sector (non-UK) | standard-path.md |
| UK Government | uk-gov-path.md |
| Defence | defence-path.md |
Modifiers (applied on top of base path):
| Condition | Modifier |
|---|---|
| Project type = AI/ML | Apply ai-ml-path.md |
| Project type = Data platform | Apply data-path.md |
| Both AI/ML and Data | Apply both modifiers |
Scope adjustments:
| Goal | Adjustment |
|---|---|
| Full governance lifecycle | Show full path from base + modifiers |
| Specific deliverable | Show only the relevant phase |
| Compliance check | Show only compliance phase from base path |
| Quick prototype documentation | Show minimum viable path from base path |
| Stage | Adjustment |
|---|---|
| Just starting | Show full path (or scoped path) |
| Have stakeholders/requirements | Skip Phases 1-2, start from Phase 3 |
| Have design artifacts | Skip to Phase 4 (Procurement) or Phase 5 (Design Reviews) |
| Need compliance review | Skip to compliance phase |
| Timeline | Adjustment |
|---|---|
| Weeks | Show minimum viable path only |
| Months | Show full path, note optional commands |
| Quarters | Show full path with all optional additions |
Present the plan as a numbered list grouped by phase:
Recommended Command Sequence
=============================
Based on: [UK Government] + [AI/ML] project, starting fresh, full lifecycle
Phase 1: Foundation
1. /arckit:principles — Governance foundation (GDS + TCoP aligned)
2. /arckit:stakeholders — Map DDaT roles, SROs, policy owners
3. /arckit:risk — HMG Orange Book risk methodology
Phase 2: Business Justification
4. /arckit:sobc — HM Treasury Green Book 5-case model
5. /arckit:requirements — Central artifact for all downstream work
Phase 3: Design & Analysis
6. /arckit:datascout — Discover UK Gov open data sources
7. /arckit:data-model — Data architecture with GDPR considerations
...
[Total: N commands across M phases]
[Estimated duration: X-Y months]
Run commands in order. Each command will guide you through its process.
After presenting the plan, ask if they want to adjust anything or if they're ready to begin.
This skill is invoked by the /arckit:start command, which delegates project onboarding to this skill. Users can also trigger it by asking about getting started, command sequences, or workflow recommendations.
For the detailed command dependency matrix, see DEPENDENCY-MATRIX.md in the user's project root (installed by arckit init). For visual workflow diagrams, see WORKFLOW-DIAGRAMS.md in the user's project root.
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.