원클릭으로
blueprint-research
Research phase for blueprint workflow - toolbox resolution, lessons discovery, and parallel research agents
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Research phase for blueprint workflow - toolbox resolution, lessons discovery, and parallel research agents
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | blueprint-research |
| description | Research phase for blueprint workflow - toolbox resolution, lessons discovery, and parallel research agents |
Handles the research phase of the blueprint workflow: Toolbox resolution, lessons discovery, local/external research decision, and spec review.
feature_description: string
tech_stack: string | string[] # From config-reader
discovery_result:
user_familiarity: high | medium | low # Do they know the codebase?
user_intent: speed | thoroughness # What matters more?
topic_risk: high | medium | low # Security, payments, external APIs?
uncertainty_level: high | medium | low # Is the approach clear?
Read config (parallel):
config_read("tech_stack", "generic")
config_read("lessons_path", ".agents/lessons/")
Spawn agents (parallel):
Task(majestic-engineer:workflow:toolbox-resolver):
prompt: "Stage: blueprint | Tech Stack: {tech_stack}"
Task(majestic-engineer:workflow:lessons-discoverer):
prompt: "workflow_phase: planning | tech_stack: {tech_stack} | task: {feature_description}"
Store outputs:
research_hooks → for Step 4 (external research)coding_styles → for Step 5 (skill injection)lessons_context → for architect agentNon-blocking errors:
Fast, local research to understand codebase patterns before deciding on external research.
Task(majestic-engineer:research:git-researcher, prompt="{feature}")
Task(majestic-engineer:research:repo-analyst, prompt="{feature}")
Store: local_findings - patterns, conventions, similar implementations
Based on discovery signals + local findings, decide if external research adds value.
Decision matrix:
| Condition | External Research |
|---|---|
topic_risk: high (security, payments, external APIs) | Always - cost of missing something too high |
local_findings has strong patterns + user_familiarity: high | Skip - codebase is authoritative |
uncertainty_level: high OR user_familiarity: low | Research - external perspective valuable |
user_intent: speed + adequate local patterns | Skip - optimize for velocity |
| Default (no strong signal) | Research - err on side of thoroughness |
research_decision = evaluate(discovery_result, local_findings)
→ SKIP_EXTERNAL | RUN_EXTERNAL
If research_decision == SKIP_EXTERNAL:
Announce: "Codebase has solid patterns for this. Proceeding without external research."
Else:
Announce: "Running external research for {reason}."
Only runs if research_decision == RUN_EXTERNAL
Task(majestic-engineer:research:docs-researcher, prompt="{feature}")
Task(majestic-engineer:research:best-practices-researcher, prompt="{feature}")
Stack-specific agents (from toolbox):
For each hook in research_hooks:
If hook.triggers.any_substring matches feature_description:
Task(subagent_type=hook.agent, prompt="{feature} | Context: {hook.context}")
Cap: Maximum 4 external agents to avoid noise.
Wait: Collect all results before proceeding.
Run in parallel:
Apply spec-reviewer skill:
context: "Feature: {feature} | Research: {combined_research}"
For each skill in coding_styles:
Skill(skill: skill)
Outputs:
spec_findings → gaps, edge cases, questionsskill_content → loaded coding style contentresearch_result:
toolbox:
research_hooks: array
coding_styles: array
lessons_context: string | null
research_decision: SKIP_EXTERNAL | RUN_EXTERNAL
research_decision_reason: string
research_findings:
local:
git: string
repo: string
external: # null if research_decision == SKIP_EXTERNAL
docs: string | null
best_practices: string | null
stack_specific: array | null
spec_findings:
gaps: array
edge_cases: array
questions: array
skill_content: string
ready_for_architecture: boolean
Create distinctive, production-grade frontend interfaces with high design quality. Use when building web components, pages, or applications. Includes framework-specific guidance for Tailwind, React, Vue, and Rails/Hotwire ecosystems.
Skill file structure, naming conventions, directory layout, frontmatter requirements, and invocation control. Use when creating skill files or slash commands to ensure correct format and validation.
Forces adversarial reasoning before committing to decisions. Triggers on architectural choices, approach selection, and planning phases to prevent premature commitment bias.
Verify LLM reasoning using Reverse Chain-of-Thought (RCoT) to detect overlooked conditions.
Autonomous task implementation - research, plan, build, review, fix, ship
Generate a complete favicon set (ICO, PNG variants, apple-touch-icon, web manifest) from a source image and integrate into the project's HTML layout. Use when user asks to generate favicons, set up PWA icons, or add an apple-touch-icon.