CtrlK
BlogDocsLog inGet started
Tessl Logo

recipe-fullstack-implement

Orchestrate full-cycle implementation across backend and frontend layers

39

Quality

25%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/recipe-fullstack-implement/SKILL.md
SKILL.md
Quality
Evals
Security

Context: Full-cycle fullstack implementation management (Requirements Analysis → Design (backend + frontend) → Planning → Implementation → Quality Assurance)

Orchestrator Definition

Core Identity: "I am not a worker. I am an orchestrator." (see subagents-orchestration-guide skill)

Required Reference

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.

Execution Protocol

  1. Delegate all work through Agent tool — invoke sub-agents, pass deliverable paths between them, and report results (permitted tools: see subagents-orchestration-guide "Orchestrator's Permitted Tools")
  2. Follow monorepo-flow.md for the design phase (multiple Design Docs, design-sync, vertical slicing)
  3. Follow subagents-orchestration-guide skill for all other orchestration rules (stop points, structured responses, escalation)
  4. Enter autonomous mode only after "batch approval for entire implementation phase"

CRITICAL: Execute all steps, sub-agents, and stopping points defined in both the monorepo-flow.md reference and subagents-orchestration-guide skill.

Execution Decision Flow

1. Current Situation Assessment

Instruction Content: $ARGUMENTS

Think deeply Assess the current situation:

Situation PatternDecision CriteriaNext Action
New RequirementsNo existing work, new feature/fix requestStart with requirement-analyzer
Flow ContinuationExisting docs/tasks present, continuation directiveIdentify next step in monorepo-flow.md
Quality ErrorsError detection, test failures, build errorsExecute quality-fixer (layer-appropriate)
AmbiguousIntent unclear, multiple interpretations possibleConfirm with user

2. Progress Verification for Continuation

When continuing existing flow, verify:

  • Latest artifacts (PRD/ADR/Design Docs/Work Plan/Tasks)
  • Current phase position (Requirements/Design/Planning/Implementation/QA)
  • Identify next step in monorepo-flow.md

3. UI Specification Phase (Frontend Layer)

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."

  • [STOP]: Wait for user response about prototype code availability

Then invoke ui-spec-designer:

  • subagent_type: "dev-workflows-frontend:ui-spec-designer"
  • If prototype provided: prompt: "Create UI Spec from PRD at [path]. Prototype code is at [user-provided path]."
  • If no prototype: prompt: "Create UI Spec from PRD at [path]. No prototype code available."

Invoke document-reviewer for UI Spec review, then [STOP] for user approval.

4. Design Phase and Work Planning

Follow monorepo-flow.md for the complete design-through-planning flow. Key differences from /recipe-implement:

  • Create separate Design Docs per layer (see monorepo-flow.md "Layer Context in Design Doc Creation")
  • Frontend Design Doc must reference the approved UI Spec (pass UI Spec path to technical-designer-frontend)
  • Execute document-reviewer once per Design Doc (separate invocations)
  • Run design-sync for cross-layer consistency verification
  • Pass all Design Docs to work-planner (subagent_type: "dev-workflows:work-planner") with vertical slicing instruction

5. Register All Flow Steps Using TaskCreate (MANDATORY)

After scale determination, register all steps of the monorepo-flow.md using TaskCreate:

  • First task: "Confirm skill constraints"
  • Register each step as individual task
  • Set currently executing step to in_progress using TaskUpdate
  • Complete task registration before invoking subagents

After requirement-analyzer [Stop]

When user responds to questions:

  • If response matches any scopeDependencies.question → Check impact for scale change
  • If scale changes → Re-execute requirement-analyzer with updated context
  • If confidence: "confirmed" or no scale change → Proceed to next step

Subagents Orchestration Guide Compliance Execution

Pre-execution Checklist (MANDATORY):

  • Read monorepo-flow.md reference
  • Confirmed relevant flow steps
  • Identified current progress position
  • Clarified next step
  • Recognized stopping points
  • codebase-analyzer included before each Design Doc creation
  • code-verifier included before document-reviewer for each Design Doc
  • Environment check: Can I execute per-task commit cycle?
    • If commit capability unavailable → Escalate before autonomous mode
    • Other environments (tests, quality tools) → Subagents will escalate

Required Flow Compliance:

  • Run quality-fixer (layer-appropriate) before every commit
  • Obtain user approval before Edit/Write/MultiEdit outside autonomous mode

CRITICAL Sub-agent Invocation Constraints

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.

Mandatory Orchestrator Responsibilities

Task Execution Quality Cycle (Filename-Pattern-Based)

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-frontend

Rules:

  1. Execute ONE task completely before starting next (each task goes through the full 4-step cycle via Agent tool, using the correct executor per filename pattern)
  2. Check executor status before quality-fixer (escalation check)
  3. Quality-fixer MUST run after each executor (no skipping)
  4. Commit MUST execute when quality-fixer returns approved: true (do not defer to end)

Security Review (After All Tasks Complete)

After all task cycles finish, invoke security-reviewer before the completion report:

  1. Agent tool (subagent_type: "dev-workflows:security-reviewer") → Pass Design Doc path(s) and implementation file list
  2. Check response:
    • 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-reviewer
    • blocked → Escalate to user

Test Information Communication

After acceptance-test-generator execution, when invoking work-planner (subagent_type: "dev-workflows:work-planner"), communicate:

  • Generated integration test file path
  • Generated E2E test file path
  • Explicit note that integration tests are created simultaneously with implementation, E2E tests are executed after all implementations

Execution Method

All work is executed through sub-agents. Sub-agent selection follows monorepo-flow.md reference and subagents-orchestration-guide skill.

Repository
shinpr/claude-code-workflows
Last updated
Created

Is this your skill?

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.