From ai-analyst
Generates master plans for new projects or features using multi-persona methodology with debate, revision, and synthesis phases. Invoke via /architect or phrases like 'architect this'.
npx claudepluginhub ai-analyst-lab/ai-analyst-plugin --plugin ai-analystThis skill uses the workspace's default tool permissions.
Run the multi-persona planning methodology to produce a master plan for a new project or feature.
Generates atomic PLAN.md files for hierarchical project planning in solo agentic dev with Claude. Covers briefs, roadmaps, phases; includes tasks, verification, checkpoints, success criteria.
Generates sectioned implementation plans from markdown spec files via research, simulated interviews, synthesis, planning, multi-LLM reviews. Resumes from existing files for complex features.
Share bugs, ideas, or general feedback.
Run the multi-persona planning methodology to produce a master plan for a new project or feature.
/architect Build a centered-person thumbnail template/architect "Add YouTube upload to the podcast pipeline"/architect read evals-course/BUILD_PLAN.mdarchitect a new email drip sequence for cohort 4This skill implements references/planning-methodology.md. The full workflow:
Phase 0 Scope & Persona Selection → define brief, pick 3-5 expert personas
Phase 1 Independent Plans (Round 1) → all personas plan in parallel
Phase 2 Debate & Critique → single moderator resolves conflicts
Phase 3 Revised Plans (Round 2) → personas revise in parallel
Phase 4 Alignment & Synthesis → single architect produces master plan
Phase 5 Build Status Tracker → CREATE BUILD_STATUS.yaml
If the user provided a file path or "read [file]", read that file as the project brief. Otherwise, use the text they provided directly.
If the brief is too vague (under 20 words, no clear deliverable), ask one clarifying question before proceeding.
Look for context clues:
working/plans/ directory already exists nearby, use itworking/plans/ in the most relevant project directorySet:
PLANS_DIR: {project}/working/plans/MASTER_PLAN_PATH: {project}/MASTER_PLAN.md (or {PROJECT_NAME}_MASTER_PLAN.md)Read references/planning-methodology.md for the full methodology reference.
Based on the brief, select 3-5 personas. Use the archetype table from the methodology as a starting point, but customize roles to the specific project. For example:
Present the personas to the user:
Project: [brief summary]
Output: {MASTER_PLAN_PATH}
Personas:
1. [Name] — [Role]. Cares about: [focus]. Will challenge: [what].
2. ...
Proceed with these personas? (a) Yes (b) Swap one out (c) Add/remove
Wait for approval before launching Phase 1.
Launch all persona agents in parallel using the Task tool. Each persona gets:
{PLANS_DIR}/round1/{persona-slug}.mdEach persona produces:
Wait for all personas to complete.
If --skip-debate: skip to Phase 4.
Launch a single debate agent that receives all Round 1 plans. It identifies:
Output: {PLANS_DIR}/debate-summary.md
Launch all persona agents again in parallel. Each receives:
{PLANS_DIR}/round2/{persona-slug}.mdLaunch a single synthesis agent that receives all Round 2 plans + debate summary.
Produces the master plan with sections:
Output: {MASTER_PLAN_PATH}
After user approves the master plan, generate BUILD_STATUS.yaml following the schema in references/planning-methodology.md.
=== PLANNING COMPLETE ===
Master Plan: {MASTER_PLAN_PATH}
Build Tracker: {project}/BUILD_STATUS.yaml
Persona Plans: {PLANS_DIR}/round1/ (5 files)
Revised Plans: {PLANS_DIR}/round2/ (5 files)
Debate Summary: {PLANS_DIR}/debate-summary.md
Waves: [N]
Tasks: [N]
Ready to execute: "produce wave 0" or read the master plan first
/architect --quick [brief]: Use 3 personas, skip debate (Phases 0-1-4 only). Faster for smaller projects./architect --resume: Re-read existing plans in working/plans/ and pick up where we left off.