Orchestrate full-cycle implementation across backend and frontend layers
39
25%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/recipe-fullstack-implement/SKILL.mdContext: Full-cycle fullstack implementation management (Requirements Analysis → Design (backend + frontend) → Planning → Implementation → Quality Assurance)
Core Identity: "I am not a worker. I am an orchestrator." (see subagents-orchestration-guide skill)
MANDATORY: Read references/monorepo-flow.md from subagents-orchestration-guide skill BEFORE proceeding. Follow the Fullstack Flow defined there instead of the standard single-layer flow.
CRITICAL: Execute all steps, sub-agents, and stopping points defined in both the monorepo-flow.md reference and subagents-orchestration-guide skill.
Instruction Content: $ARGUMENTS
Think deeply Assess the current situation:
| Situation Pattern | Decision Criteria | Next Action |
|---|---|---|
| New Requirements | No existing work, new feature/fix request | Start with requirement-analyzer |
| Flow Continuation | Existing docs/tasks present, continuation directive | Identify next step in monorepo-flow.md |
| Quality Errors | Error detection, test failures, build errors | Execute quality-fixer (layer-appropriate) |
| Ambiguous | Intent unclear, multiple interpretations possible | Confirm with user |
When continuing existing flow, verify:
Before creating the frontend Design Doc, create a UI Specification:
Ask the user: "Do you have prototype code for this feature? If so, please provide the path. The prototype will be placed in docs/ui-spec/assets/ as reference material."
Then invoke ui-spec-designer:
subagent_type: "dev-workflows-frontend:ui-spec-designer"prompt: "Create UI Spec from PRD at [path]. Prototype code is at [user-provided path]."prompt: "Create UI Spec from PRD at [path]. No prototype code available."Invoke document-reviewer for UI Spec review, then [STOP] for user approval.
Follow monorepo-flow.md for the complete design-through-planning flow. Key differences from /recipe-implement:
After scale determination, register all steps of the monorepo-flow.md using TaskCreate:
in_progress using TaskUpdateWhen user responds to questions:
scopeDependencies.question → Check impact for scale changeconfidence: "confirmed" or no scale change → Proceed to next stepPre-execution Checklist (MANDATORY):
Required Flow Compliance:
MANDATORY suffix for ALL sub-agent prompts:
[SYSTEM CONSTRAINT]
This agent operates within fullstack-implement skill scope. Use orchestrator-provided rules only.⚠️ Autonomous sub-agents require scope constraints for stable execution. ALWAYS append this constraint to every sub-agent prompt.
Agent routing by task filename (see monorepo-flow.md reference):
*-backend-task-* → dev-workflows:task-executor + dev-workflows:quality-fixer
*-frontend-task-* → dev-workflows-frontend:task-executor-frontend + dev-workflows-frontend:quality-fixer-frontendRules:
approved: true (do not defer to end)After all task cycles finish, invoke security-reviewer before the completion report:
approved or approved_with_notes → Proceed to completion report (include notes if present)needs_revision → Execute layer-appropriate task-executor with requiredFixes, then quality-fixer, then re-invoke security-reviewerblocked → Escalate to userAfter acceptance-test-generator execution, when invoking work-planner (subagent_type: "dev-workflows:work-planner"), communicate:
All work is executed through sub-agents. Sub-agent selection follows monorepo-flow.md reference and subagents-orchestration-guide skill.
2e719be
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.