Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is completab
SkillScore82Maintained
Automatic
◆Coding pack
Last verified 8/21/2026
What it changes
Passed 18 of 22 test cases with the skill, and 14 of 22 without it.
Without skill64%
With skill82%
Checks it passed that the model alone missed
Saves the output plan file under the plans/ path.
Targets a typical step count between 3 and 12 steps for the overall plan.
Evaluates the draft plan against a checklist and an anti-pattern catalog.
and 6 more in the full report
5 fixed13 passed either way3 still failing1 broke
Pass-rate lift
+18 pp
Tokens
+18%
Agent turns
0%
Response time
-39%
Model gemini-3.6-flashMeasured 8/21/2026v718 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
What initial checks should be performed during the research phase before gathering context for a new construction plan?
case-14 · gemini-3.6-flash · 8/21/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md97 linessingle file
Blueprint — Construction Plan Generator
Turn a one-line objective into a step-by-step construction plan that any coding agent can execute cold.
When to Use
Breaking a large feature into multiple PRs with clear dependency order
Planning a refactor or migration that spans multiple sessions
Coordinating parallel workstreams across sub-agents
Any task where context loss between sessions would cause rework
Do not use for tasks completable in a single PR, fewer than 3 tool calls, or when the user says "just do it."
How It Works
Blueprint runs a 5-phase pipeline:
Research — Pre-flight checks (git, gh auth, remote, default branch), then reads project structure, existing plans, and memory files to gather context.
Design — Breaks the objective into one-PR-sized steps (3–12 typical). Assigns dependency edges, parallel/serial ordering, model tier (strongest vs default), and rollback strategy per step.
Draft — Writes a self-contained Markdown plan file to plans/. Every step includes a context brief, task list, verification commands, and exit criteria — so a fresh agent can execute any step without reading prior steps.
Review — Delegates adversarial review to a strongest-model sub-agent (e.g., Opus) against a checklist and anti-pattern catalog. Fixes all critical findings before finalizing.
Register — Saves the plan, updates memory index, and presents the step count and parallelism summary to the user.
Blueprint detects git/gh availability automatically. With git + GitHub CLI, it generates full branch/PR/CI workflow plans. Without them, it switches to direct mode (edit-in-place, no branches).
Examples
Basic usage
/blueprint myapp "migrate database to PostgreSQL"
Produces plans/myapp-migrate-database-to-postgresql.md with steps like:
Step 1: Add PostgreSQL driver and connection config
Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.