google-agents-cli-scaffold
Project scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.
ln-220-story-coordinator
CREATE/REPLAN Stories for Epic (5-10 Stories). Delegates ln-001-standards-researcher for standards research. Decompose-First Pattern. Auto-discovers team/Epic.
Full skill instructions
Universal Story management coordinator that delegates CREATE/REPLAN operations to specialized workers after building IDEAL Story plan.
Use when:
Key principle: Build IDEAL Story plan FIRST, THEN check existing Stories to determine mode:
Rationale: Ensures consistent Story decomposition based on current Epic requirements, independent of existing Story structure (may be outdated).
Rule: Stories start from Story 1 (US001), NO Story 0 reserved.
Rationale:
Numbering within Epic:
Next Story Number: Incremented sequentially across ALL Epics (read from kanban_board.md Epic Story Counters table)
Objective: Gather context for Story planning (Epic details, planning questions, frontend context, fallback docs, user input)
Step 1: Discovery (Automated)
Auto-discovers from docs/tasks/kanban_board.md:
get_project(query="Epic N") → Fetch full Epic documentStep 2: Extract Planning Information (Automated)
Parses Epic structure for Story planning questions:
| Question | Extraction Source |
|---|---|
| Q1 - User/Persona | Epic Goal ("Enable [persona]...") + Scope In (user roles) |
| Q2 - What they want | Epic Scope In (capabilities) + functional requirements |
| Q3 - Why it matters | Epic Success Criteria (metrics) + Goal (business value) |
| Q4 - Which Epic | Already from Step 1 |
| Q5 - Main AC | Derive from Epic Scope In features → testable scenarios |
| Q6 - Application type | Epic Technical Notes (UI/API mentioned) → Default: API |
Step 3: Frontend Research (Optional)
Trigger: If Q2 (capabilities) OR Q5 (AC) missing after Step 2
Process:
Glob **/*.html, src/**/*.html<form id="login"> → "Given valid credentials, When submit, Then login success")<button id="register"> → "User registration")minlength="8" → "Given password <8 chars, Then error")Fallback: If no HTML → Skip to Step 4
Step 4: Fallback Search Chain
Objective: Fill missing Q1-Q6 BEFORE asking user.
For each question with no answer from Step 2-3:
| Question | Fallback Search |
|---|---|
| Q1 (User/Persona) | Search requirements.md for "User personas", "Actors" → Default "User" if not found |
| Q3 (Why it matters) | Search requirements.md for "Business objectives", "Goals" → Infer from Epic Success Criteria |
| Q6 (Application type) | Search tech_stack.md for "Frontend", "Backend", "API" → Default "API" |
Skip: Q2, Q5 (Epic + HTML are sources of truth), Q4 (already known)
Step 5: User Input (Only if Missing)
If still missing after Step 2 + 3 + 4:
If all questions answered from Epic OR HTML OR fallback: Skip user prompts, proceed to Phase 2
Output: Complete context (Epic details, next Story number, Q1-Q6 answers)
Objective: Research industry standards/patterns BEFORE Story generation to ensure implementation follows best practices.
Why: Prevents outdated patterns or RFC violations (e.g., OAuth without PKCE).
Process:
Skill(skill: "ln-001-standards-researcher", epic_description="[Epic full description]", story_domain="[domain]")Output: Standards Research stored for ALL Stories in Epic
Skip conditions:
Time-box: 15-20 minutes (handled by ln-001)
Note: Research done ONCE per Epic, results reused for all Stories (5-10 Stories benefit from single research)
Objective: Build IDEAL Story plan, determine execution mode
Story Grouping Guidelines:
Each Story = ONE vertical slice of user capability (end-to-end: UI → API → Service → DB).
✅ GOOD Story Grouping (1 Story = 1 user journey):
❌ BAD Story Grouping (horizontal slices):
Rule: 1 Story = 1 user capability = 3-5 AC = 6-20 hours = 10-28 tests
Database Creation Principle (Incremental Schema Evolution):
Each Story creates ONLY the tables it needs (not all tables upfront).
✅ GOOD (Incremental):
❌ BAD (Big-Bang):
Rationale: Big-bang database setup violates incremental delivery. Each Story should deliver user value, not technical infrastructure.
Build IDEAL Plan (Automated):
Analyze Epic Scope: Review features in Epic Scope In, identify user capabilities
Determine Story Count:
Story Size Guidelines:
| Criterion | Min | Max | Under-decomposed | Over-decomposed |
|---|---|---|---|---|
| AC | 3 | 5 | >5 AC (split) | <3 AC (merge) |
| Duration | 6h | 20h | >20h (split) | <6h (merge) |
| Tests | 10 | 28 | >28 tests (split) | <10 tests (merge) |
Over-decomposition indicators:
Build IDEAL Plan "in mind":
AC Quality Validation (CRITICAL - delegates to workers):
Workers (ln-221, ln-222) must validate AC quality:
Completeness Check (3 scenario types required):
Example: ❌ BAD: "User can login" (only happy path) ✅ GOOD:
Specificity Check (measurable outcomes required):
Example: ❌ BAD: "Login should be fast" (vague) ✅ GOOD: "Then receive token <200ms" (measurable)
INVEST Checklist:
| Criterion | Check | ✅ GOOD | ❌ BAD |
|---|---|---|---|
| Independent | Can develop/deploy without blocking others + NO forward dependencies | "Request OAuth token" (Story N uses only N-1) | "Validate token depends on Story N+2 refresh flow" (forward dependency!) |
| Negotiable | AC focus on WHAT, not HOW | "User gets valid token" (what) | "Use authlib 1.3.0, store in Redis" (how) |
| Valuable | Clear business value | "User refreshes expired token to maintain session" | "Add token_refresh table" (no user value) |
| Estimable | Can estimate 6-20h | Clear scope, known patterns, researched standards | "Implement authentication" (too vague) |
| Small | Fits 1-2 sprints | 3-5 AC, 6-20h | "Full OAuth flow" (>5 AC, >20h) |
| Testable | AC measurable | "Given valid refresh token, Then receive token <200ms" | "Token refresh should be fast" (not measurable) |
Output: IDEAL Story plan (5-10 Stories) with titles, statements, core AC, ordering
Objective: Determine execution mode based on existing Stories AND user intent
Process:
Query Linear for existing Stories in Epic:
list_issues(project=Epic.id, label="user-story")
Mode Detection:
Analyze user request for keywords:
Decision matrix:
| Condition | Mode | Delegate To |
|---|---|---|
| Count = 0 | CREATE | Phase 5a: ln-221-story-creator |
| Count ≥ 1 AND ADD keywords | ADD | Phase 5c: ln-221-story-creator (appendMode) |
| Count ≥ 1 AND REPLAN keywords | REPLAN | Phase 5b: ln-222-story-replanner |
| Count ≥ 1 AND ambiguous | ASK USER | "Add new Story or revise the plan?" |
Important: Orchestrator loads metadata ONLY (ID, title, status). Workers load FULL descriptions (token efficiency).
Output: Execution mode determined + existingCount for workers
Trigger: Epic has no Stories yet (first decomposition)
Delegation:
Call ln-221-story-creator via Skill tool:
Skill(
skill: "ln-221-story-creator",
epicData: {id, title, description},
idealPlan: [ /* 5-10 Stories from Phase 3 */ ],
standardsResearch: "Standards Research from Phase 2",
teamId: "team-id",
autoApprove: false // or true for automation
)
Worker handles:
Output: Created Story URLs + summary from worker
Trigger: Epic already has Stories (requirements changed)
Delegation:
Call ln-222-story-replanner via Skill tool:
Skill(
skill: "ln-222-story-replanner",
epicData: {id, title, description},
idealPlan: [ /* 5-10 Stories from Phase 3 */ ],
standardsResearch: "Standards Research from Phase 2",
existingCount: N,
teamId: "team-id",
autoApprove: false // or true for automation
)
Worker handles:
Output: Operation results + warnings + affected Story URLs from worker
Trigger: Epic has Stories, user wants to ADD more (not replan existing)
Delegation:
Call ln-221-story-creator via Skill tool with appendMode:
Skill(
skill: "ln-221-story-creator",
appendMode: true, // ADD to existing, don't replace
epicData: {id, title, description},
newStoryDescription: userRequestedStory, // Single Story from user request
standardsResearch: "Standards Research from Phase 2",
teamId: "team-id",
autoApprove: false
)
Key differences from CREATE MODE:
appendMode: true → Skip full IDEAL plan, create only requested StorynewStoryDescription → User's specific request (e.g., "add authorization Story")Worker handles:
Output: Created Story URL + summary from worker
TodoWrite format (mandatory): Add phases to todos before starting:
- Phase 1: Context Assembly (in_progress)
- Phase 2: Standards Research via ln-221 (pending)
- Phase 3: Build IDEAL Story Plan (pending)
- Phase 4: Check Existing Stories (pending)
- Phase 5: Delegate to ln-222/ln-223 (pending)
- Wait for worker result (pending)
Mark each as in_progress when starting, completed when done.
Calls:
Called by:
Upstream:
Downstream:
✅ Phase 1: Context Assembly Complete:
✅ Phase 2: Standards Research Complete:
✅ Phase 3: Planning Complete:
✅ Phase 4: Check Existing Complete:
✅ Phase 5: Delegation Complete:
CREATE MODE (First Time):
"Create stories for Epic 7: OAuth Authentication"
Process:
REPLAN MODE (Requirements Changed):
"Replan stories for Epic 7 - removed custom token formats, added scope management"
Process:
Story Content:
Story Decomposition:
User Interaction:
Delegation:
Version: 5.0.0 (BREAKING: Added AC Quality Validation in Phase 3 (completeness: happy path + errors + edge cases; specificity: HTTP codes + timing). Updated INVEST Independent criterion with forward dependency check. Added Database Creation Principle to Story Grouping Guidelines per BMAD Method best practices.) Last Updated: 2026-02-03
Project scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.
Set up tracing, logging, and monitoring for deployed ADK agents across Cloud Trace, BigQuery, and third-party platforms.
Enterprise Azure infrastructure architect generating Bicep or Terraform from workload descriptions.
Plan and configure production-ready Azure Kubernetes Service clusters with Day-0 and Day-1 best practices.
Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
Web search, scraping, extraction, crawling, and monitoring via ScrapeGraph AI CLI.
Skill for working with Firebase Hosting (Classic). Use this when you want to deploy static web apps, Single Page Apps (SPAs), or simple microservices. Do NOT use for Firebase App Hosting.
Deploy and manage web apps with Firebase App Hosting. Use this skill when deploying Next.js/Angular apps with backends.
Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".
Build SEO-optimized pages at scale using templates, data, and proven playbook patterns.
Design and build isolated, reusable Convex backend components with clear boundaries and app-facing wrappers.
Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".
Opus.ai: Revolutionize Your Web Experience
Build a no-code AI app in minutes.
An IDE for code migration from legacy to modern frameworks through coding agents.
Automate CGI animation in live-action scenes
Branded artistic QR-code concepts
Launch a website in seconds with AI.
Streamline Your Coding Experience with AI Code Helper
Convert any screenshot or design to clean code.