Business Problem to Blueprint
B2B problem to CLAUDE.md: architecture, DB schema, phased plan
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 16, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Jul 16, 2026
⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (SKILL.md not found in repo tree). The test below is what we measured on Jul 16, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.
Gave the task 'dentistry for 4 doctors: paper appointment book, 18% no-shows, manual insurance claims' and checked the result not visually, but by execution: transferred the DB schema from each blueprint to real DDL and ran in SQLite with PRAGMA foreign_keys enabled. The baseline schema without skill compiled, but it was a flat 5 tables, and for seven mandatory business queries, it yielded 1 out of 7 — no next_recall_due field (meaning the main overdue dashboard had nothing to record), no reminders table, claims not linked to procedures. The skill's schema — 11 tables, 7 out of 7 queries passed, FK-check clean. Caveat: I wrote both blueprints myself, so part of the gap is my effort distribution, not just the skill; the skill's honest contribution here is that the 'complete database schema + phased breakdown' standard forces entities to be listed exhaustively. Minuses, preventing a higher score: SKILL.md is essentially one expanded example about fire inspections (38 lines) with a hardcoded Next.js/Supabase/Vercel stack (11 mentions), and it prescribes always outputting 'Pricing Recommendation' and ROI calculation, meaning the model is forced to invent numbers like $12–35K and 'saving $78,000/year' — for a catalog, this is a risk, not a feature.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 4/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 3/5
What Business Problem to Blueprint does
Transforms a verbally described B2B problem into a ready CLAUDE.md blueprint, including architecture, database schema, feature breakdown by MVP/2/3 phases, tech stack selection, step-by-step implementation plan, and timeline estimation. Triggers when a client's problem needs to be translated into a technical specification ready for immediate development.
How to install Business Problem to Blueprint
Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.
Commands — how to trigger Business Problem to Blueprint
-
/business-problem-to-blueprintB2B problem to CLAUDE.md: architecture, DB schema, phased plan
It also activates on plain-language prompts like these:
-
Turn my dental clinic's scheduling problem into a technical build blueprint -
I need a database schema and phased MVP plan for this client's business issue -
Draft a CLAUDE.md spec from this customer's messy manual workflow description
Frequently asked questions
- Is the Business Problem to Blueprint skill free?
- Yes. The skill itself is free from zanecole10/software-tailor-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Business Problem to Blueprint work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Gave the task 'dentistry for 4 doctors: paper appointment book, 18% no-shows, manual insurance claims' and checked the result not visually, but by execution: transferred the DB schema from each blueprint to real DDL and ran in SQLite with PRAGMA foreign_keys enabled. The baseline schema without skill compiled, but it was a flat 5 tables, and for seven mandatory business queries, it yielded 1 out of 7 — no next_recall_due field (meaning the main overdue dashboard had nothing to record), no reminders table, claims not linked to procedures. The skill's schema — 11 tables, 7 out of 7 queries passed, FK-check clean. Caveat: I wrote both blueprints myself, so part of the gap is my effort distribution, not just the skill; the skill's honest contribution here is that the 'complete database schema + phased breakdown' standard forces entities to be listed exhaustively. Minuses, preventing a higher score: SKILL.md is essentially one expanded example about fire inspections (38 lines) with a hardcoded Next.js/Supabase/Vercel stack (11 mentions), and it prescribes always outputting 'Pricing Recommendation' and ROI calculation, meaning the model is forced to invent numbers like $12–35K and 'saving $78,000/year' — for a catalog, this is a risk, not a feature.
- What is the Business Problem to Blueprint SkillProof Score?
- 7.6/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 3/5.
- How do I install Business Problem to Blueprint?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Business Problem to Blueprint with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.