@polymorphism-tech/morph-spec 4.9.0 → 4.10.1

package/framework/skills/level-1-workflows/morph-phase-clarify/SKILL.md

@@ -0,0 +1,247 @@
+---
+name: morph:phase-clarify
+description: MORPH-SPEC Phase 3 (Clarify). Iterative clarification loop driven by a satisfaction score (0-100). Generates targeted questions per round, always presents "End Clarify" as exit option, and stops when score >= 85 or user exits. Use after design approval to eliminate spec ambiguities before task breakdown begins.
+argument-hint: "[feature-name]"
+user-invocable: false
+allowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion
+cliVersion: "4.10.1"
+---
+
+# MORPH Clarify — Phase 3
+
+> INTERNAL: Workflow skill used by /morph-proposal during automated phase orchestration. Not a user command.
+
+Eliminate spec ambiguities through an iterative question loop until the spec has sufficient quality to generate tasks.
+
+## Prerequisites
+
+- [ ] Phase 2 (Design) completed
+- [ ] `spec.md` approved by user
+- [ ] `contracts.cs` (or `contracts.ts`) defined
+
+## Recommended Tools
+
+> **Ref:** `framework/skills/level-0-meta/morph-tool-usage-guide/SKILL.md` for complete guide.
+> **Example:** `references/clarifications-example.md` — filled-in clarifications.md showing expected Q&A format.
+
+| Action | Tool | Alternative |
+|--------|------|-------------|
+| Read spec + contracts | **Read** all design outputs | — |
+| Verify technical feasibility | **Context7 MCP** `query_docs()` | **WebSearch** |
+| Check external issues/limitations | **GitHub MCP** `search_issues()` | — |
+| Ask clarifying questions | **AskUserQuestion** (never plain text) | — |
+| Update spec with clarifications | **Edit** spec.md | — |
+| Create clarifications.md | **Write** | — |
+| Update state | **Bash** `npx morph-spec state mark-output $ARGUMENTS clarifications` | — |
+
+---
+
+## Satisfaction Scoring System
+
+Before each round, calculate the **Satisfaction Score (0-100)** by evaluating the current spec:
+
+| Dimension | Pts | Maximum Score Criteria |
+|-----------|-----|----------------------|
+| **Functional completeness** | 25 | All requirements have measurable acceptance criteria (no vague "should", "may", "generally") |
+| **Failure coverage** | 20 | All error paths have defined behavior (invalid input, not found, timeout, unauthorized) |
+| **Edge cases** | 20 | Boundaries, concurrent states, empty/extreme inputs documented |
+| **Definitional clarity** | 20 | No critical term undefined, no "TBD", no "to be defined" |
+| **Integration contracts** | 15 | External dependencies have payload format, errors, and retry policy defined |
+
+**Thresholds:**
+
+| Score | Action |
+|-------|--------|
+| >= 85 | Satisfied. Present results and offer "End Clarify" as the primary option |
+| 70-84 | Continue. Focus questions on the lowest-scoring dimensions |
+| < 70 | Continue. Broad questions covering the largest gaps |
+
+> The score rises as answers are incorporated. There's no fixed maximum rounds — the loop ends when score >= 85 **or** the user chooses to end.
+
+---
+
+## Workflow
+
+### Initialization
+
+**Step 0 (BEFORE any writing) — Ensure clarify phase:**
+
+```bash
+npx morph-spec state get $ARGUMENTS
+```
+
+Check the `"phase"` field in the output:
+
+**If `"phase": "clarify"`** → correct phase, proceed.
+
+**If `"phase": "design"`** → run in sequence:
+1. `npx morph-spec approve $ARGUMENTS design`
+2. `npx morph-spec phase advance $ARGUMENTS` (→ clarify)
+
+**Any other value** → STOP — inconsistent state, report to user.
+
+> **Rule:** Never write `clarifications.md` or update `spec.md` until the phase is `clarify`.
+
+---
+
+Read the base files in PARALLEL:
+
+```
+Read: .morph/features/$ARGUMENTS/1-design/spec.md
+    + Read: .morph/features/$ARGUMENTS/1-design/contracts.cs  (or contracts.ts for TypeScript)
+    + Read: .morph/features/$ARGUMENTS/1-design/schema-analysis.md  (if exists)
+```
+
+Calculate the initial score. Track accumulated answers from prior rounds to avoid repeating already-answered questions.
+
+---
+
+### Main Loop
+
+**Repeat until: score >= 85 OR user chooses to end.**
+
+#### A. Calculate Current Round Score
+
+Score each dimension based on the spec + accumulated answers. Note which dimensions are weakest — they guide this round's questions.
+
+#### B. Identify New Questions
+
+Analyze only what **hasn't been answered yet**. Categorize by dimension:
+
+| Category | Example Questions |
+|----------|-------------------|
+| **Validation** | Field limits, accepted formats, business rules |
+| **Behavior** | What happens when X fails? Empty state? Loading state? |
+| **Priority** | Must-have vs nice-to-have? MVP vs v2? |
+| **Integration** | Webhook vs polling? Retry policy? Timeout? |
+| **Performance** | Expected volume? Response SLA? |
+| **UX** | Error message shown to user? Visual feedback? |
+
+#### C. Present Questions via `AskUserQuestion`
+
+**Why this matters:** AskUserQuestion gives structured options the user can click — far better UX than walls of text. It also captures answers programmatically for the clarifications.md output.
+
+**Rules:**
+
+1. Use `AskUserQuestion` — **NEVER list questions as plain text**
+2. Maximum **4 questions per call** (tool limit)
+3. If there are more than 3 new questions, make sequential calls — the **exit option always appears in the last call of each round**
+4. **Always include the following question as the last in the final batch of each round:**
+
+```json
+{
+  "header": "End Clarify?",
+  "question": "End the Clarify phase now or continue refining the spec?",
+  "multiSelect": false,
+  "options": [
+    {
+      "label": "Continue refining",
+      "description": "There are still open questions identified in this round"
+    },
+    {
+      "label": "End Clarify",
+      "description": "Proceed to Plan phase with the spec in its current state"
+    }
+  ]
+}
+```
+
+> If score >= 85, adjust the first option label to: `"Continue (optional)"` with description: `"Score ${score}/100 — spec is satisfactory, but you can refine further"`
+
+#### D. Wait and Incorporate Answers
+
+**Do not proceed before receiving all responses.**
+
+After receiving answers:
+1. Check if the answer is consistent with `contracts.cs` and `schema-analysis.md`
+2. If any answer is ambiguous or contradictory → ask for clarification before updating
+3. Update `spec.md` with:
+   - Section `## Clarifications (Phase 3)` with structured Q&A
+   - Updates to affected functional sections
+   - New edge cases in `## Edge Cases`
+
+#### E. Check Exit Condition
+
+- User chose **"End Clarify"** → exit loop
+- Score >= 85 AND no new questions identified → exit loop
+- Otherwise → return to A
+
+---
+
+### Post-Loop: Generate Outputs
+
+**Step 1: Create `clarifications.md`**
+
+Write to `.morph/features/$ARGUMENTS/1-design/clarifications.md`:
+
+```markdown
+# Clarifications — {Feature Name}
+
+**Phase:** Clarify (Phase 3)
+**Rounds completed:** {N}
+**Final score:** {score}/100
+**Status:** Resolved — incorporated into spec.md
+
+---
+
+## Questions & Answers
+
+### Q{N}: {Title}
+**Question:** {question}
+**Answer:** {user's answer}
+**Spec Updates:** {which sections were updated}
+**Priority:** High/Medium/Low
+**Resolved:** Yes
+
+---
+
+## Edge Cases
+
+### EC{N}: {Name}
+**Scenario:** {when it happens}
+**Expected Behavior:** {how the system reacts}
+**Implementation Notes:** {tips}
+
+---
+
+## Summary
+
+| | Count |
+|---|---|
+| Questions Answered | {N} |
+| Edge Cases Documented | {N} |
+| Spec Sections Updated | {N} |
+| Final Score | {score}/100 |
+```
+
+**Step 2: Update State**
+
+```bash
+npx morph-spec state mark-output $ARGUMENTS clarifications
+```
+
+---
+
+## Phase Outputs
+
+<!-- morph:outputs:clarify -->
+| Output | Path |
+|--------|------|
+| `clarifications` | `.morph/features/{feature}/1-design/clarifications.md` |
+<!-- /morph:outputs -->
+
+## Advancement Criteria
+
+- [x] Satisfaction score >= 85 OR user opted to end
+- [x] All answers are consistent with `contracts.cs`
+- [x] `spec.md` updated with clarifications and edge cases
+- [x] `clarifications.md` created with Q&A and final score
+- [x] State updated (`mark-output clarifications`)
+
+---
+
+```bash
+npx morph-spec phase advance $ARGUMENTS
+```
+
+Continue automatically to Phase 4 (Plan) after clarifications.md is generated.

package/framework/skills/level-1-workflows/morph-phase-codebase-analysis/SKILL.md

@@ -0,0 +1,270 @@
+---
+name: morph:phase-codebase-analysis
+description: MORPH-SPEC Design sub-phase that analyzes existing codebase and database schema, producing schema-analysis.md with real column names, types, relationships, and field mismatches. Use at the start of Design phase before generating contracts.cs to prevent incorrect field names or types.
+user-invocable: false
+allowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion
+cliVersion: "4.10.1"
+---
+
+# MORPH Codebase Analysis - Design Sub-phase
+
+> INTERNAL: Automation skill for schema analysis step within Phase 2 (Design).
+> Called by `phase-design.md` Step 2. Not a standalone user command.
+
+Automates existing code analysis to generate `schema-analysis.md` with real database/code data.
+
+## Prerequisites
+
+- [ ] Phase 1 (Setup) completed
+- [ ] Feature has approved `proposal.md`
+- [ ] Project context loaded (stack, agents)
+
+## Recommended Tools
+
+> **Ref:** `framework/skills/level-0-meta/morph-tool-usage-guide/SKILL.md` for complete guide.
+> **Ref:** `framework/standards/integration/mcp/mcp-tools.md` for MCP reference.
+
+| Action | Tool | Alternative |
+|------|------------|-------------|
+| List database tables | **Supabase MCP** `list_tables()` | **Grep** `.from(` in code |
+| Get table schema | **Supabase MCP** `get_table_schema()` | **Read** type definitions |
+| Get FK relationships | **Supabase MCP** `get_relationships()` | **Grep** JOIN/FK patterns |
+| Get RLS policies | **Supabase MCP** `query()` | **Read** policy files |
+| Find queries in code | **Grep** `\.from\(` in `*.ts,*.tsx,*.js,*.cs` | — |
+| Find type definitions | **Glob** `src/**/types/**/*.ts` or `**/Entities/**/*.cs` | — |
+| Read found files | **Read** each file | — |
+| Complex multi-file analysis | **Task** (subagent Explore) | Read individual |
+| Generate schema-analysis.md | **Write** using template | **Bash** template render |
+
+**MCPs for this phase:** Supabase (schema — **PRIORITY**), Generic database MCPs.
+
+---
+
+## Automated Workflow
+
+### Step 1: Detect Analysis Method
+
+**IMPORTANT:** Do not assume the MCP is available and accessible.
+Verify first with a test call before attempting to use it.
+
+```
+1. IF Supabase MCP configured in settings.json:
+   → Try mcp__supabase__list_tables() with implicit timeout
+   → IF returns valid data (array of tables with content):
+      → Use Method A (direct MCP)
+   → IF returns error, timeout, empty array, or inaccessible data:
+      → Log: "Supabase MCP configured but inaccessible (CloudSQL? Auth? Permissions?)"
+      → Use Method B (static code analysis)
+
+2. IF Database MCP (other) configured:
+   → Test connectivity with trivial query before using
+   → IF OK: Use adapted Method A
+   → IF fails: Use Method B
+
+3. IF no MCP available:
+   → Use Method B (static code analysis)
+```
+
+**Signs of inaccessible MCP:**
+- Empty response or `[]` from `list_tables()`
+- Authentication error / permission denied
+- Returned schema doesn't match code (e.g., tables exist in code but not in MCP)
+- Project uses database other than Supabase (CloudSQL, RDS, Azure SQL, etc.)
+
+### Step 2A: MCP Method (Preferred)
+
+**Tools:** Supabase MCP
+
+```javascript
+// 1. List all tables
+const tables = await mcp__supabase__list_tables();
+
+// 2. For each feature-relevant table:
+for (const table of relevantTables) {
+  // 2a. Complete schema
+  const schema = await mcp__supabase__get_table_schema({ table: table.name });
+  // → column_name, data_type, is_nullable, column_default
+
+  // 2b. Relationships
+  const rels = await mcp__supabase__get_relationships({ table: table.name });
+  // → foreign_table, foreign_column, constraint_type
+
+  // 2c. Indexes
+  const indexes = await mcp__supabase__query({
+    query: `SELECT indexname, indexdef FROM pg_indexes WHERE tablename = '${table.name}'`
+  });
+
+  // 2d. RLS policies (security)
+  const policies = await mcp__supabase__query({
+    query: `SELECT policyname, cmd, qual FROM pg_policies WHERE tablename = '${table.name}'`
+  });
+}
+```
+
+### Step 2B: Static Analysis Method (Fallback)
+
+**Tools:** Grep, Glob, Read, Task (subagent for large projects)
+
+**Phase B1: Find Queries**
+
+```
+Grep: "\.from\(|\.select\(|SELECT |supabase\.|context\.|dbContext\.|DbSet<"
+Type: ts,tsx,js,jsx,cs
+Output: files_with_matches
+```
+
+**Phase B2: Read Query Files**
+
+For each found file, use **Read** to extract:
+- Table names: `from('leads')`, `DbSet<Lead>`, `FROM leads`
+- Column names: `.select('fullname, phonenumber')`, `l.FullName`
+- Data types: TypeScript interfaces, C# DTOs
+- Relationships: JOIN clauses, navigation properties
+
+**Phase B3: Find Type Definitions**
+
+```
+# TypeScript/JavaScript:
+Glob: "src/**/types/**/*.ts"
+Glob: "src/**/*.d.ts"
+Glob: "src/**/interfaces/*.ts"
+
+# .NET:
+Glob: "**/*Dto.cs"
+Glob: "**/Entities/**/*.cs"
+Glob: "**/Models/**/*.cs"
+```
+
+**Phase B4: When to use Task (subagent)**
+
+Use Task subagent **ONLY** when:
+- Project has 20+ query files
+- Multiple data access patterns (Supabase + EF Core + raw SQL)
+- Precise cross-context analysis across many files
+
+Do not use Task subagent when:
+- Project has < 10 query files (direct Read is faster)
+- Data access pattern is uniform (only Supabase OR only EF Core)
+
+### Step 2B-Format: Standardized Format for Static Analysis
+
+**IMPORTANT:** When using Method B (static analysis), **always use the official template**.
+This ensures `contracts.cs` can be generated mechanically, without manual interpretation.
+
+The template is at `framework/templates/docs/schema-analysis.md`. Use it via:
+
+```bash
+npx morph-spec template render docs/schema-analysis \
+  .morph/features/{feature}/1-design/schema-analysis.md \
+  '{
+    "FEATURE_NAME": "{feature}",
+    "FEATURE_NAME_TITLE": "{Feature Display Name}",
+    "DATE": "YYYY-MM-DD",
+    "AUTHOR": "Claude Code (Sonnet 4.6)",
+    "method": "Static Code Analysis",
+    "mcpUsed": "No",
+    "tableCount": N,
+    "fileCount": N,
+    "tables": [
+      {
+        "name": "table_name",
+        "codeSource": "path/to/file.ts",
+        "columns": [
+          { "name": "column_name", "type": "string", "nullable": false, "notes": "from SELECT query" }
+        ],
+        "relationships": [{ "description": "belongs to users via user_id" }],
+        "indexes": [{ "description": "idx_leads_created_at (created_at DESC)" }]
+      }
+    ],
+    "fieldMismatches": [
+      { "description": "Code uses user.name but DB column is users.fullname" }
+    ],
+    "typeMismatches": [],
+    "relationshipIssues": [],
+    "dtoRecommendations": [
+      {
+        "tableName": "leads",
+        "dtoName": "LeadDto",
+        "fields": [
+          { "type": "Guid", "name": "Id", "nullable": false, "comment": "PK" },
+          { "type": "string", "name": "FullName", "nullable": false, "comment": "leads.fullname" }
+        ]
+      }
+    ]
+  }'
+```
+
+**If template render is not available**, use **Write** tool to create the file directly
+following the structure above. The table and mismatch format is MANDATORY — without standard format
+it's not possible to generate contracts.cs mechanically.
+
+### Step 3: Map Inconsistencies
+
+Create a map of:
+
+| Frontend/Code | Database | Type | Problem |
+|----------------|----------------|------|----------|
+| user.name | users.fullname | string | MISMATCH |
+| lead.phone | leads.phonenumber | string | MISMATCH |
+| order.metadata | orders.metadata | JSONB | Type complex |
+
+### Step 4: Generate `schema-analysis.md`
+
+Use the template at `framework/templates/docs/schema-analysis.md`:
+
+```bash
+npx morph-spec template render docs/schema-analysis \
+  .morph/features/{feature-name}/1-design/schema-analysis.md \
+  '{ "FEATURE_NAME": "{feature-name}", "DATE": "..." }'
+```
+
+OR use **Write** tool to create directly with collected data.
+
+### Step 5: Update State
+
+```bash
+npx morph-spec state mark-output {feature-name} schema-analysis
+```
+
+---
+
+## Outputs
+
+- `.morph/features/{feature}/1-design/schema-analysis.md`
+- State updated with `schemaAnalysis` output
+
+## CHECKPOINT
+
+Before proceeding to contracts.cs, present results and ask for confirmation using `AskUserQuestion`:
+
+```json
+{
+  "questions": [
+    {
+      "header": "Schema Review",
+      "question": "Schema analysis complete: {N} tables, {N} field mismatches, {N} type mismatches, {N} relationships. Is the analysis correct?",
+      "multiSelect": false,
+      "options": [
+        { "label": "Correct", "description": "Schema analysis matches the real database" },
+        { "label": "Has issues", "description": "I see problems — let me explain" }
+      ]
+    },
+    {
+      "header": "Contracts",
+      "question": "May I generate contracts.cs based on this real schema?",
+      "multiSelect": false,
+      "options": [
+        { "label": "Generate contracts", "description": "Proceed to contracts.cs using the analyzed schema" },
+        { "label": "Wait", "description": "I want to review schema-analysis.md first" }
+      ]
+    }
+  ]
+}
+```
+
+**If "Has issues"** → ask what's wrong, fix schema-analysis.md, re-present checkpoint.
+**If "Correct" + "Generate contracts"** → proceed to contracts generation.
+
+---
+
+*MORPH-SPEC by Polymorphism Tech*