agentleFS
MetalLegBobMetalLegBob/solana-vibes-kit/svk-setup/SKILL.md

SVK-setup

Skill19 starsChanged 9 months agoMITView on GitHub

SVK Setup: Guided onboarding skill that interviews users about their experience and project scope, recommends tools from a tiered catalog (MCPs, plugins, skills), walks through installation of third-party tools and SVK core skills (SOS, GL, DB, BOK), and generates a personalized reference document. The first thing a new SVK user runs. Run /SVK-setup for the full guided flow, or /SVK-setup:interview to begin.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Look for .claude/svk-meta.json in the current project.

    line 25
  2. Very specific:

    Read the svk_repo path and installed_version from the metadata file.

    line 26
  3. Very specific:

    Run: git -C <svk_repo> tag --sort=-v:refname | head -1 to get the latest tag.

    line 28
  4. Distinctive:

    If they match, skip — the user is up to date.

    line 30
  5. Distinctive:

    If the latest tag is newer, show this message ONCE (never repeat in this session):

    line 31
  6. Distinctive:

    If the git commands fail (offline, repo moved, etc.), skip silently.

    line 37
  7. Distinctive:

    Important: Do NOT block or delay the user's actual command.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- SVK Version Check — runs once per session on first skill invocation --><svk-version-check> **On first invocation this session**, silently perform a version check:
  1. Look for .claude/svk-meta.json in the current project. If it doesn't exist, skip this check entirely.
  2. Read the svk_repo path and installed_version from the metadata file.
  3. Run: git -C <svk_repo> fetch --tags --quiet 2>/dev/null
  4. Run: git -C <svk_repo> tag --sort=-v:refname | head -1 to get the latest tag.
  5. Compare the installed version against the latest tag (strip the leading v).
  6. If they match, skip — the user is up to date.
  7. If the latest tag is newer, show this message ONCE (never repeat in this session):

SVK Update Available: v{latest} is available (you're on v{installed}).

  • Update now: I can pull and reinstall the changed skills in this session
  • Update later: Start a new chat and run /SVK:update
  1. If the git commands fail (offline, repo moved, etc.), skip silently. Never show errors from version checking.

Important: Do NOT block or delay the user's actual command. Perform this check, show the notification if needed, then proceed with the command they invoked. </svk-version-check>

SVK Setup

A guided onboarding skill that sets up your entire Solana development environment — not just SVK, but the full ecosystem of plugins, MCPs, and skills needed for productive Solana development.

"The first 30 minutes determine whether someone stays or bounces. Make them count."


Getting Started

SVK Setup runs as a 4-phase guided flow. The full command runs all phases in sequence; sub-commands let you re-run individual phases.

Quick Start

/SVK-setup

This begins with a short interview about your experience and project, then recommends tools, walks through installation, and generates a reference doc. Follow the prompts.

Full Pipeline

┌─────────────────────────────────────────────────────────────────────┐
│                         SVK SETUP v1.0                              │
├─────────────────────────────────────────────────────────────────────┤
│                                                                     │
│  /SVK-setup:interview    Phase 1 — User Interview                  │
│  ═══════════════════     5-7 questions, one at a time               │
│  Experience gauging: git, Solana, Claude Code                       │
│  Project scoping: new/existing, type, frontend/backend, team       │
│  Output: .svk/SETUP_PROFILE.json                                    │
│                          │                                          │
│                          ▼                                          │
│  /SVK-setup:recommend    Phase 2 — Tiered Recommendations          │
│  ═══════════════════     Three tiers based on profile               │
│  Essential: always recommended (GSD, Superpowers, Safety Net, etc) │
│  Recommended: profile-dependent (Trail of Bits, Context7, etc)     │
│  Optional: shown but not pushed (Figma, Vercel, Docker, etc)       │
│  Output: .svk/SETUP_RECOMMENDATIONS.json                           │
│                          │                                          │
│                          ▼                                          │
│  /SVK-setup:install      Phase 3 — Installation Walkthrough        │
│  ═══════════════════     One category at a time                     │
│  Explain → choose → install → verify per tool                      │
│  Category order: Workflow → Safety → Solana → Search → Memory →    │
│    Security → Frontend → Backend → DevOps → Utility                │
│  Output: .svk/SETUP_INSTALLED.json                                  │
│                          │                                          │
│                          ▼                                          │
│  /SVK-setup:reference    Phase 4 — Reference Document              │
│  ═══════════════════     Personalized setup reference               │
│  Getting started, installed tools, skipped tools, quick reference  │
│  Output: docs/svk-setup-reference.md                                │
│                                                                     │
└─────────────────────────────────────────────────────────────────────┘

Typical Workflow

For first-time users, just run /SVK-setup and follow the prompts. The full flow takes 10-20 minutes depending on how many tools you install.

To re-run individual phases later:

  • /SVK-setup:interview — Re-do the interview (resets profile)
  • /SVK-setup:recommend — Re-generate recommendations from existing profile
  • /SVK-setup:install — Install additional tools
  • /SVK-setup:reference — Re-generate the reference document

Foundation Patterns

PatternHow SVK Setup Uses It
Progressive DisclosureTool catalog indexed by category, loaded per-category during walkthrough
Signal-Based IndexingInterview answers drive which catalog entries are surfaced

Output Structure

SVK Setup writes state to .svk/ in the project root and the reference doc to docs/:

.svk/
├── SETUP_PROFILE.json          # User profile from interview
├── SETUP_RECOMMENDATIONS.json  # Tiered tool recommendations
└── SETUP_INSTALLED.json        # What was installed/skipped

docs/
└── svk-setup-reference.md      # Personalized reference document

User Profiles

The interview produces one of three profiles that tune all subsequent behavior:

ProfileGitSolanaClaude CodeBehavior
BeginnerNone/BasicNo/LearningNewExtra explanations, guardrails emphasized, learning resources
IntermediateComfortableLearning/ShippedSomeStandard explanations, full recommended tier
AdvancedComfortableShippedPower userMinimal hand-holding, full catalog available, cherry-pick

Tool Tiers

TierSelection Logic
EssentialAlways recommended regardless of profile
RecommendedShown based on project type and experience
OptionalListed for awareness, not pushed

See resources/tool-catalog.md for the complete registry.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.