build-with-claude
Skill178 starsChanged 4 months agoMITView on GitHub
Guide a developer through building their Solana MVP step by step using Claude Code. Use when a user says "help me build this", "start the MVP", "guide me through implementation", "what should I build first", or "walk me through the code". Reads build-context.md from a prior scaffold phase if available.
- Sends data out
In this repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- animation-reverse-engineeringSkill
- brand-designSkill
- build-data-pipelineSkill
- build-defi-protocolSkill
- build-mobileSkill
- csoSkill
- debug-programSkill
- design-tasteSkill
- frontend-design-guidelinesSkill
- launch-tokenSkill
- navigate-skillsSkill
- number-formattingSkill
- page-load-animationsSkill
- product-reviewSkill
- review-and-iterateSkill
- roast-my-productSkill
- scaffold-projectSkill
- verify-humanity-pohSkill
- virtual-solana-incubatorSkill
- colosseum-copilotSkill
- competitive-landscapeSkill
- defillama-researchSkill
- find-next-crypto-ideaSkill
- learnSkill
- solana-beginnerSkill
- validate-ideaSkill
- apply-grantSkill
- create-pitch-deckSkill
- deploy-to-mainnetSkill
- marketing-videoSkill
- submit-to-hackathonSkill
- video-craftSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
23 rules. About 0 are common, 17 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈17
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
If TEL_PROMPTED is no: Before starting the skill workflow, ask the user about telemetry.
- Distinctive: line 36
If A: run this bash:
- Distinctive: line 43
If B: run this bash:
- Very specific: line 62
Check for .superstack/build-context.md.
- Distinctive: line 63
Read references/skill-mcp-usage-guide.md to understand what tools are available BEFORE building.
- Distinctive: line 64
Read references/dev-environment-setup.md to ensure the dev environment is ready.
- Distinctive: line 65
Read references/solana-dev-patterns.md for implementation patterns.
- Distinctive: line 72
When stuck, consult references/error-recovery-guide.md.
- Distinctive: line 73
After MVP is complete, run through references/testing-checklist.md.
- Very specific: line 77
If .superstack/build-context.md exists, use the stack and architecture decisions.
- Distinctive: line 81
Never block on missing context files: Always proceed by asking the user directly.
- Distinctive: line 82
Never write more than 1 milestone of code before testing.
- Distinctive: line 83
Always test on devnet before suggesting mainnet.
- Distinctive: line 84
If the user is stuck for more than 2 attempts at the same problem, step back and try a different approach.
- Distinctive: line 85
Use the installed skills and MCPs — they exist to help.
- Distinctive: line 86
Keep explanations short. The user is here to build, not read essays.
- Distinctive: line 101
When MVP is complete and tests pass, tell the user to proceed to review-and-iterate for security audit and production readiness check.
- Very specific: line 103
When updating build-context.md, deep-merge with existing content — don't overwrite fields from prior phases.
- Distinctive: line 127
Which RPC for development?: Use devnet public or Helius free.
- Very specific: line 128
Which wallet for testing?: Use file keypair: solana-keygen new --outfile test-wallet.json
- Distinctive: line 129
When to move from local to devnet?: After all unit tests pass locally.
- Distinctive: line 130
Surfpool vs solana-test-validator?: Use Surfpool when you need real mainnet account state (DeFi, existing programs).
- Very specific: line 145
After the skill workflow completes (success, error, or abort), log the telemetry event.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.
Files
Preamble (run first)
_TEL_TIER=$(cat ~/.superstack/config.json 2>/dev/null | grep -o '"telemetryTier": *"[^"]*"' | head -1 | sed 's/.*"telemetryTier": *"//;s/"$//' || echo "anonymous")
_TEL_TIER="${_TEL_TIER:-anonymous}"
_TEL_PROMPTED=$([ -f ~/.superstack/.telemetry-prompted ] && echo "yes" || echo "no")
_TEL_START=$(date +%s)
_SESSION_ID="$$-$(date +%s)"
mkdir -p ~/.superstack
echo "TELEMETRY: $_TEL_TIER"
echo "TEL_PROMPTED: $_TEL_PROMPTED"
if [ "$_TEL_TIER" != "off" ]; then
_TEL_EVENT='{"skill":"build-with-claude","phase":"build","event":"started","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}'
echo "$_TEL_EVENT" >> ~/.superstack/telemetry.jsonl 2>/dev/null || true
_CONVEX_URL=$(cat ~/.superstack/config.json 2>/dev/null | grep -o '"convexUrl":"[^"]*"' | head -1 | cut -d'"' -f4 || echo "")
[ -n "$_CONVEX_URL" ] && curl -s -X POST "$_CONVEX_URL/api/mutation" -H "Content-Type: application/json" -d '{"path":"telemetry:track","args":{"skill":"build-with-claude","phase":"build","status":"success","version":"0.2.0","platform":"'$(uname -s)-$(uname -m)'","timestamp":'$(date +%s)000'}}' >/dev/null 2>&1 &
true
fiIf TEL_PROMPTED is no: Before starting the skill workflow, ask the user about telemetry.
Use AskUserQuestion:
Help superstack get better! We track which skills get used and how long they take — no code, no file paths, no PII. Change anytime in
~/.superstack/config.json.
Options:
- A) Sure, help superstack improve (anonymous)
- B) No thanks
If A: run this bash:
echo '{"telemetryTier":"anonymous"}' > ~/.superstack/config.json
_TEL_TIER="anonymous"
touch ~/.superstack/.telemetry-promptedIf B: run this bash:
echo '{"telemetryTier":"off"}' > ~/.superstack/config.json
_TEL_TIER="off"
touch ~/.superstack/.telemetry-promptedThis only happens once. If TEL_PROMPTED is yes, skip this entirely and proceed to the skill workflow.
Wrong skill? See SKILL_ROUTER.md for all available skills.
Build with Claude
Overview
Guide the user through implementing their Solana MVP feature by feature. Break the work into small, testable increments. Use installed skills and MCPs to accelerate development. Keep the user shipping, not stuck.
Workflow
- Check for
.superstack/build-context.md. If found, use the stack and architecture decisions. If not, ask what they've set up and what they want to build. Write.superstack/build-context.mdwith the context gathered so future skills can use it. - Read references/skill-mcp-usage-guide.md to understand what tools are available BEFORE building.
- Read references/dev-environment-setup.md to ensure the dev environment is ready.
- Read references/solana-dev-patterns.md for implementation patterns.
- Break the MVP into 3-5 milestones, each shippable in 1-2 hours.
- For each milestone: a. Explain what we're building and why b. Write the code (use installed skills for domain guidance) c. Test it (devnet first, always) d. Verify it works before moving on
- When stuck, consult references/error-recovery-guide.md.
- After MVP is complete, run through references/testing-checklist.md.
Prior Context (Optional — never block on this)
If .superstack/build-context.md exists, use the stack and architecture decisions. If it doesn't exist, proceed immediately — ask the user what they've set up and what they want to build. Do NOT redirect to scaffold-project or any other command.
Non-Negotiables
- Never block on missing context files. Always proceed by asking the user directly.
- Never write more than 1 milestone of code before testing. Ship small, verify often.
- Always test on devnet before suggesting mainnet.
- If the user is stuck for more than 2 attempts at the same problem, step back and try a different approach.
- Use the installed skills and MCPs — they exist to help. Don't reinvent what a skill already provides.
- Keep explanations short. The user is here to build, not read essays.
- Optionally update
.superstack/build-context.mdas milestones are completed.
Phase Handoff
This skill is Phase 2 (Build) in the Idea → Build → Launch journey.
Reads: .superstack/build-context.md (from scaffold-project)
Writes/Updates: .superstack/build-context.md (creates if missing) with:
build_status.milestones: array of completed milestonesbuild_status.mvp_complete: booleanbuild_status.tests_passing: booleanbuild_status.devnet_deployed: booleanbuild_status.program_id: string (if applicable)
When MVP is complete and tests pass, tell the user to proceed to review-and-iterate for security audit and production readiness check.
When updating build-context.md, deep-merge with existing content — don't overwrite fields from prior phases.
See ../../data/specs/phase-handoff.md for the full JSON contract.
Quick Start
# Verify dev environment
solana --version # 3.x (Agave)
anchor --version # >= 1.0.0
node --version # >= 20
# Start local validator for testing
solana-test-validator # Or: surfpool --fork devnet (for real account data)
# Build and test
anchor build && anchor test
# Deploy to devnet when ready
anchor deploy --provider.cluster devnetDecision Points
- Which RPC for development? Use devnet public or Helius free.
- Which wallet for testing? Use file keypair:
solana-keygen new --outfile test-wallet.json - When to move from local to devnet? After all unit tests pass locally. Devnet for integration tests.
- Surfpool vs solana-test-validator? Use Surfpool when you need real mainnet account state (DeFi, existing programs). Use test-validator for isolated testing.
- Full runbook: See
../../data/guides/rpc-wallet-guide.md
Resources
references/
- references/dev-environment-setup.md
- references/skill-mcp-usage-guide.md
- references/solana-dev-patterns.md
- references/error-recovery-guide.md
- references/testing-checklist.md
Telemetry (run last)
After the skill workflow completes (success, error, or abort), log the telemetry event.
Determine the outcome from the workflow result: success if completed normally, error
if it failed, abort if the user interrupted.
Run this bash:
_TEL_END=$(date +%s)
_TEL_DUR=$(( _TEL_END - ${_TEL_START:-$_TEL_END} ))
_TEL_TIER=$(cat ~/.superstack/config.json 2>/dev/null | grep -o '"telemetryTier": *"[^"]*"' | head -1 | sed 's/.*"telemetryTier": *"//;s/"$//' || echo "anonymous")
if [ "$_TEL_TIER" != "off" ]; then
echo '{"skill":"build-with-claude","phase":"build","event":"completed","outcome":"OUTCOME","duration_s":"'"$_TEL_DUR"'","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","platform":"'$(uname -s)-$(uname -m)'"}' >> ~/.superstack/telemetry.jsonl 2>/dev/null || true
true
fiReplace OUTCOME with success/error/abort based on the workflow result.
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
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.

