Blueprinting
Interview-driven planner turning a vague idea into an approved bundle-plugin design doc
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 31, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 9b19b2a
Located SKILL.md at skills/blueprinting/SKILL.md; frontmatter parses with name+description. Spot-checked all 3 body-referenced files (references/dialogue-strategies.md, design-document-template.md, platform-reference.md) via raw fetch — all HTTP 200; no security smells. For the output test I fixed a self-contained scenario (bundle three sequential SEO skills into a Claude Code plugin) and wrote two artifacts: a baseline ad-hoc plan (13-line flat prose) and a skill-following design document per the template. Concrete difference: the skill artifact adds structured fields the baseline entirely omits — Target Users, measurable Success Criteria, per-skill Visibility (entry-point/internal) and rigid/flexible Type, an explicit artifact-continuity Workflow Chain with Calls/Called-by symmetry constraints, a reasoned Bootstrap yes decision, and [TBD]-flagged open questions (standalone keyword input, Article vs Product schema) surfaced for user review that the baseline never raised. I could not exercise the interactive interview loop or the Orchestration Pipeline (scaffolding/authoring/auditing) since those sibling skills weren't invoked — that downstream value is unverified; the design-document authoring (blueprinting's own declared Output) is what I measured.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 4/5
What Blueprinting does
Runs a three-phase structured interview (needs exploration, architecture design, design-document review) to plan a new multi-skill "bundle-plugin," then chains into the bundles-forge scaffolding/authoring/auditing pipeline. Triggers when you want to package scattered skills into a plugin, split one complex skill into several, or combine skills into a new unified bundle. Produces an approved design document as its handoff artifact; adding skills to an existing project is out of scope (that is optimizing).
How to install Blueprinting
git clone --depth 1 https://github.com/OdradekAI/bundles-forge.git /tmp/blueprinting-src
mkdir -p ~/.claude/skills
cp -R /tmp/blueprinting-src/skills/blueprinting ~/.claude/skills/blueprinting
# Standalone copy above gives you the blueprinting planner + its references/.
# Preferred (full workflow): install the whole bundle as a plugin so the
# downstream scaffolding/authoring/auditing skills it orchestrates are present:
# /plugin marketplace add OdradekAI/bundles-forge
# /plugin install bundles-forge@bundles-forge-dev
# No API keys or external deps. The Orchestration Pipeline only functions when
# the sibling bundles-forge skills are installed (plugin route).
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Blueprinting
-
/blueprintingInterview-driven planner turning a vague idea into an approved bundle-plugin design doc
It also activates on plain-language prompts like these:
-
Plan a new bundle-plugin for these skills -
Split this complex skill into smaller ones -
Combine these related skills into one bundle
Frequently asked questions
- Is the Blueprinting skill free?
- Yes. The skill itself is free from OdradekAI/bundles-forge. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Blueprinting work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Tested · Works. Located SKILL.md at skills/blueprinting/SKILL.md; frontmatter parses with name+description. Spot-checked all 3 body-referenced files (references/dialogue-strategies.md, design-document-template.md, platform-reference.md) via raw fetch — all HTTP 200; no security smells. For the output test I fixed a self-contained scenario (bundle three sequential SEO skills into a Claude Code plugin) and wrote two artifacts: a baseline ad-hoc plan (13-line flat prose) and a skill-following design document per the template. Concrete difference: the skill artifact adds structured fields the baseline entirely omits — Target Users, measurable Success Criteria, per-skill Visibility (entry-point/internal) and rigid/flexible Type, an explicit artifact-continuity Workflow Chain with Calls/Called-by symmetry constraints, a reasoned Bootstrap yes decision, and [TBD]-flagged open questions (standalone keyword input, Article vs Product schema) surfaced for user review that the baseline never raised. I could not exercise the interactive interview loop or the Orchestration Pipeline (scaffolding/authoring/auditing) since those sibling skills weren't invoked — that downstream value is unverified; the design-document authoring (blueprinting's own declared Output) is what I measured.
- What is the Blueprinting SkillProof Score?
- 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
- How do I install Blueprinting?
- 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 Blueprinting 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.