workflow-spec-to-pbi

name	workflow-spec-to-pbi
description	[Workflow] Use when activating the Spec to PBI Backlog workflow for convert an existing engineering spec bundle into complete, prioritized, dependency-aware PBIs and stories.
disable-model-invocation	true

Codex compatibility note:

• Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.
• Prefer the plan-hard skill for planning guidance in this Codex mirror.
• Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.
• User-question prompts mean to ask the user directly in Codex.
• Ignore Claude-specific mode-switch instructions when they appear.
• Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.
• Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.
• Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.
• For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.
• If a required step/tool cannot run in this environment, stop and ask the user before adapting.

Codex Project-Reference Loading (No Hooks)

Codex does not receive Claude hook-based doc injection. When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.

Always read:

• docs/project-config.json (project-specific paths, commands, modules, and workflow/test settings)
• docs/project-reference/docs-index-reference.md (routes to the full docs/project-reference/* catalog)
• docs/project-reference/lessons.md (always-on guardrails and anti-patterns)

Situation-based docs:

• Backend/CQRS/API/domain/entity changes: backend-patterns-reference.md, domain-entities-reference.md, project-structure-reference.md
• Frontend/UI/styling/design-system: frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
• Spec/test-case planning or TC mapping: feature-docs-reference.md
• Integration test implementation/review: integration-test-reference.md
• E2E test implementation/review: e2e-test-reference.md
• Code review/audit work: code-review-rules.md plus domain docs above based on changed files

Do not read all docs blindly. Start from docs-index-reference.md, then open only relevant files for the task.

Quick Summary

Goal: Convert an existing engineering spec bundle into a complete, sprint-ready PBI backlog.

Canonical input: docs/specs/{app-bucket}/{system-name}/

Primary outputs:

• team-artifacts/pbis/{date}-pbi-{slug}.md for each generated PBI.
• team-artifacts/backlog/spec-to-pbi-{date}-backlog.md with priority order and dependency graph.
• plans/reports/spec-to-pbi-{date}-{system-name}.md with coverage matrix and unresolved questions.

When to Use

• User wants to create all PBIs from an existing engineering spec.
• User wants to split a very large spec into small sprint-ready PBIs.
• User wants a dependency-aware and priority-ranked backlog from docs/specs/.
• User wants shared/foundation tasks identified before feature PBIs.

When Not to Use

• Raw product vision without a spec bundle -> use $workflow-product-discovery.
• One informal idea -> use $workflow-idea-to-pbi.
• Spec creation/update only -> use $workflow-spec-driven-dev.
• Implementation after PBIs are ready -> use $workflow-feature or $workflow-big-feature.

Protocol

1. Activate

Run $workflow-start spec-to-pbi with the user's prompt as context.

2. Load Spec Context

Locate and read:

• docs/specs/{app-bucket}/{system-name}/README.md
• docs/specs/{app-bucket}/{system-name}/00-module-registry.md
• docs/specs/{app-bucket}/{system-name}/01-domain-erd.md
• Per-module README.md, A-domain-model.md, B-business-rules.md, C-api-contracts.md, D-events-jobs.md, and E-user-journeys.md

If the spec path is missing or ambiguous, ask the user for the exact spec bundle path before generating PBIs.

3. Freshness Gate

Run $spec-discovery in audit mode before PBI generation.

• If stale behavior is found, run/update the impacted spec sections before generating PBIs.
• If only structural/doc formatting is stale, record the risk and continue.
• If critical domain/API/business-rule sections are stale, stop and ask whether to update specs first.

4. Coverage Matrix

Create a matrix with one row per independently deliverable item:

Spec Source	Module	Feature/Operation	Domain Impact	Shared Dependency	PBI Type	Status
{file:section}	{module}	{feature}	entity/state/event/API/UI	yes/no	feature/foundation/shared/migration/test-data	planned

Every source feature/operation must map to exactly one of:

• Generated PBI
• Shared/foundation PBI
• Existing PBI reference
• Explicit out-of-scope decision with reason

5. Large Spec Decomposition

Apply these scale rules before creating PBIs:

Scope	Required Breakdown
1-3 modules	Process inline with one task per module and feature group
4-10 modules	Split by module, then feature/operation group
10+ modules	Incremental module-group batches with coverage matrix checkpoints
Any PBI > 8 story points	Split with SPIDR until each PBI is <= 8 story points
Cross-cutting prerequisite	Create shared/foundation PBI before dependent feature PBIs

6. Domain Analysis Gate

Run $domain-analysis when any spec item includes:

• New or changed entities, aggregates, value objects, or ownership boundaries
• State machines or lifecycle transitions
• Cross-service event ownership or synchronization
• Data migration or seed/test-data needs

Record domain findings in each affected PBI under ## Domain Impact.

7. PBI Generation Loop

For each matrix row that needs a new PBI:

1. Run $refine to create the PBI artifact.
2. Run $refine-review.
3. Run $story to create vertical-slice stories.
4. Run $story-review.
5. Run $pbi-challenge.
6. Run $dor-gate.
7. Run $pbi-mockup only when UI is involved.

Each PBI MUST include:

• Source spec references with file:section evidence.
• GIVEN/WHEN/THEN acceptance criteria.
• Story points and complexity.
• Dependencies table with must-before, can-parallel, blocked-by, or independent.
• Priority input data for $prioritize.
• Test specification needs, including expected TC categories.
• Domain impact and shared/foundation task references.

8. Cross-PBI Prioritization

After all PBI loops finish, run $prioritize once across the full generated set.

The backlog artifact MUST include:

• Rank and recommended implementation order.
• Dependency graph and first-do/blocked/defer groups.
• Foundation/shared tasks first when other PBIs depend on them.
• RICE or MoSCoW rationale.
• DoR status per PBI.
• Remaining open questions.

8.5 Near-Final Documentation Synchronization

Run $docs-update after $prioritize and before $watzup.

Purpose:

• Sync generated PBIs/stories/backlog outputs back into business feature docs where applicable.
• Sync feature doc Section 15 test specifications and docs/specs/ dashboards.
• Verify engineering spec bundle indexes, feature docs, and TDD/spec docs do not drift after PBI generation.
• Record skipped sub-phases explicitly when no impacted docs exist.

9. Completion Criteria

Workflow can close only when:

• Every spec source item is represented in the coverage matrix.
• Every generated PBI has dependency and priority fields.
• Shared/foundation PBIs are explicit and ordered before dependents.
• Domain-analysis findings are attached where domain changes are implied.
• The final backlog artifact ranks all PBIs and explains what to do first.
• $docs-update has run as the near-final sync gate, with specs, feature docs, and TDD/spec dashboards either updated or explicitly marked unchanged.

IMPORTANT MANDATORY Steps: $scout -> $spec-discovery -> $domain-analysis -> $why-review -> $plan-hard -> $why-review -> $plan-review -> $why-review -> $plan-validate -> $why-review -> $refine -> $why-review -> $refine-review -> $story -> $why-review -> $story-review -> $pbi-challenge -> $dor-gate -> $pbi-mockup -> $prioritize -> $docs-update -> $watzup -> $workflow-end

[BLOCKING] Each step MUST invoke its skill invocation. Marking a workflow step completed without skill invocation is a workflow violation.

Nested Task Expansion Contract — For workflow-step invocation, the [Workflow] ... row is only a parent container; the child skill still creates visible phase tasks.

1. Call the current task list first. If a matching active parent workflow row exists, set nested=true and record parentTaskId; otherwise run standalone.
2. Create one task per declared phase before phase work. When nested, prefix subjects [N.M] $skill-name — phase.
3. When nested, link the parent with TaskUpdate(parentTaskId, addBlockedBy: [childIds]).
4. Orchestrators must pre-expand a child skill's phase list and link the workflow row before invoking that child skill or sub-agent.
5. Mark exactly one child in_progress before work and completed immediately after evidence is written.
6. Complete the parent only after all child tasks are completed or explicitly cancelled with reason.

Blocked until: the current task list done, child phases created, parent linked when nested, first child marked in_progress.

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

AI Mistake Prevention — Failure modes to avoid on every task:

Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal. Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing. Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain. Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path. When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site. Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code. Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks. Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis. Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly. Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.

Incremental Result Persistence — MANDATORY for all sub-agents or heavy inline steps processing >3 files.

1. Before starting: Create report file plans/reports/{skill}-{date}-{slug}.md
2. After each file/section reviewed: Append findings to report immediately — never hold in memory
3. Return to main agent: Summary only (per SYNC:subagent-return-contract) with Full report: path
4. Main agent: Reads report file only when resolving specific blockers

Why: Context cutoff mid-execution loses ALL in-memory findings. Each disk write survives compaction. Partial results are better than no results.

Report naming: plans/reports/{skill-name}-{YYMMDD}-{HHmm}-{slug}.md

Sub-Agent Return Contract — When this skill spawns a sub-agent, the sub-agent MUST return ONLY this structure. Main agent reads only this summary — NEVER requests full sub-agent output inline.

## Sub-Agent Result: [skill-name]

Status: ✅ PASS | ⚠️ PARTIAL | ❌ FAIL
Confidence: [0-100]%

### Findings (Critical/High only — max 10 bullets)

- [severity] [file:line] [finding]

### Actions Taken

- [file changed] [what changed]

### Blockers (if any)

- [blocker description]

Full report: plans/reports/[skill-name]-[date]-[slug].md

Main agent reads Full report file ONLY when: (a) resolving a specific blocker, or (b) building a fix plan. Sub-agent writes full report incrementally (per SYNC:incremental-persistence) — not held in memory.

• MANDATORY Parent workflow rows do not replace child phase tracking; expand phases and link the parent when nested.
• MANDATORY Orchestrators pre-expand child skill phases before invocation; use [N.M] $skill-name — phase prefixes and one-in_progress discipline.

Closing Reminders

• MUST use the spec bundle as canonical input; do not invent unrelated opportunities.
• MUST decompose big specs into small PBIs before story generation.
• MUST include dependency, priority, domain impact, and shared-task details.
• MUST write artifacts incrementally after each module/feature.
• MUST run $prioritize once at the end across all generated PBIs.
• MUST run $docs-update after $prioritize and before $watzup to keep specs, feature docs, and TDD/spec docs synchronized.

Hookless Prompt Protocol Mirror (Auto-Synced)

Source: .claude/hooks/lib/prompt-injections.cjs + .claude/.ck.json

[WORKFLOW-EXECUTION-PROTOCOL] [BLOCKING] Workflow Execution Protocol — MANDATORY IMPORTANT MUST CRITICAL. Do not skip for any reason.

1. DETECT: Match prompt against workflow catalog
2. ANALYZE: Find best-match workflow AND evaluate if a custom step combination would fit better
3. ASK (REQUIRED FORMAT): Use a direct user question with this structure:
   • Question: "Which workflow do you want to activate?"
   • Option 1: "Activate [BestMatch Workflow] (Recommended)"
   • Option 2: "Activate custom workflow: [step1 → step2 → ...]" (include one-line rationale)
4. ACTIVATE (if confirmed): Call $workflow-start <workflowId> for standard; sequence custom steps manually
5. CREATE TASKS: task tracking for ALL workflow steps
6. EXECUTE: Follow each step in sequence [CRITICAL-THINKING-MINDSET] Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination principle: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination. AI Attention principle (Primacy-Recency): Put the 3 most critical rules at both top and bottom of long prompts/protocols so instruction adherence survives long context windows.

Learned Lessons

Lessons Learned

[CRITICAL] Hard-won project debugging/architecture rules. MUST ATTENTION apply BEFORE forming hypothesis or writing code.

Quick Summary

Goal: Prevent recurrence of known failure patterns — debugging, architecture, naming, AI orchestration, environment.

Top Rules (apply always):

• MUST ATTENTION verify ALL preconditions (config, env, DB names, DI regs) BEFORE code-layer hypothesis
• MUST ATTENTION fix responsible layer — NEVER patch symptom sites with caller-specific defensive code
• MUST ATTENTION use ExecuteInjectScopedAsync for parallel async + repo/UoW — NEVER ExecuteUowTask
• MUST ATTENTION name by PURPOSE not CONTENT — adding member forces rename = abstraction broken
• MUST ATTENTION persist sub-agent findings incrementally after each file — NEVER batch at end
• MUST ATTENTION Windows bash: verify Python alias (where python/where py) — NEVER assume python/python3 resolves

---

Debugging & Root Cause Reasoning

• [2026-04-11] Holistic-first: verify environment before code. Failure → list ALL preconditions (config, env vars, DB names, endpoints, DI regs, credentials, permissions, data prerequisites) → verify each via evidence (grep/cat/query) BEFORE code-layer hypothesis. Worst rabbit holes: diving nearest layer while bug sits elsewhere — e.g., hours debugging "sync timeout", real cause: test appsettings pointing wrong DB. Cheapest check first.
• [2026-04-01] Ask "whose responsibility?" before fixing. Trace: bug in caller (wrong data) or callee (wrong handling)? Fix responsible layer — NEVER patch symptom site masking real issue.
• [2026-04-01] Trace data lifecycle, not error site. Follow data: creation → transformation → consumption. Bug usually where data created wrong, not consumed.
• [2026-04-01] Code is caller-agnostic. Functions/handlers/consumers don't know who invokes them. Comments/guards/messages describe business intent — NEVER reference specific callers (tests, seeders, scripts).

Architecture Invariants

• [2026-03-31] ParallelAsync + repo/UoW MUST use ExecuteInjectScopedAsync, NEVER ExecuteUowTask. ExecuteUowTask creates new UoW but reuses outer DI scope (same DbContext) — parallel iterations sharing non-thread-safe DbContext silently corrupt data. ExecuteInjectScopedAsync creates new UoW + new DI scope (fresh repo per iteration).
• [2026-03-31] Bus message naming MUST include service name prefix — core services NEVER consume feature events. Prefix declares schema ownership (AccountUserEntityEventBusMessage = Accounts owns). Core services (Accounts, Communication) are leaders. Feature services (Growth, Talents) sending to core MUST use {CoreServiceName}...RequestBusMessage — never define own event for core to consume.

Naming & Abstraction

• [2026-04-12] Name PURPOSE not CONTENT — "OrXxx" anti-pattern. HrManagerOrHrOrPayrollHrOperationsPolicy names set members, not what it guards. Add role → rename = broken abstraction. Rule: names express DOES/GUARDS, not CONTAINS. Test: adding/removing member forces rename? YES = content-driven = bad → rename to purpose (e.g., HrOperationsAccessPolicy). Nuance: "Or" fine in behavioral idioms (FirstOrDefault, SuccessOrThrow) — expresses HAPPENS, not membership.

Environment & Tooling

• [2026-04-20] Windows bash: NEVER assume python/python3 resolves — verify alias first. Python may not be in bash PATH under those names. Check: where python / where py. Prefer py (Windows Python Launcher) for one-liners, node if JS alternative exists.

Test-specific lessons → docs/project-reference/integration-test-reference.md Lessons Learned section. Production-code anti-patterns → docs/project-reference/backend-patterns-reference.md Anti-Patterns section. Generic debugging/refactoring reminders → System Lessons in .claude/hooks/lib/prompt-injections.cjs.

---

Closing Reminders

• IMPORTANT MUST ATTENTION holistic-first: verify ALL preconditions (config, env, DB names, endpoints, DI regs) BEFORE code-layer hypothesis — cheapest check first
• IMPORTANT MUST ATTENTION fix responsible layer — NEVER patch symptom site; trace caller (wrong data) vs callee (wrong handling), fix root owner
• IMPORTANT MUST ATTENTION parallel async + repo/UoW → ALWAYS ExecuteInjectScopedAsync, NEVER ExecuteUowTask (shared DbContext = silent data corruption)
• IMPORTANT MUST ATTENTION bus message prefix = schema ownership; feature services NEVER define events for core services — use {CoreServiceName}...RequestBusMessage
• IMPORTANT MUST ATTENTION name by PURPOSE — adding/removing member forces rename = broken abstraction
• IMPORTANT MUST ATTENTION sub-agents MUST write findings after each file/section — NEVER batch all findings into one final write
• IMPORTANT MUST ATTENTION Windows bash: NEVER assume python/python3 resolves — run where python/where py first, use py launcher or node

[LESSON-LEARNED-REMINDER] [BLOCKING] Task Planning & Continuous Improvement — MANDATORY. Do not skip.

Break work into small tasks (task tracking) before starting. Add final task: "Analyze AI mistakes & lessons learned".

Extract lessons — ROOT CAUSE ONLY, not symptom fixes:

1. Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value".
2. Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up.
3. Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase.
4. Consolidate: multiple mistakes sharing one failure mode → ONE lesson.
5. Recurrence gate: "Would this recur in future session WITHOUT this reminder?" — No → skip $learn.
6. Auto-fix gate: "Could $code-review/$code-simplifier/$security/$lint catch this?" — Yes → improve review skill instead.
7. BOTH gates pass → ask user to run $learn. [TASK-PLANNING] [MANDATORY] BEFORE executing any workflow or skill step, create/update task tracking for all planned steps, then keep it synchronized as each step starts/completes.