Requirements Document Analysis

Analyze an OpenSpec requirements spec (from openspec/specs/<capability>/spec.md, or a delta spec under openspec/changes/**/specs/) and produce three outputs:

1. Internal consistency — whether requirements contradict each other or the schema.
2. Implementation compliance — whether the implementation meets each requirement.
3. Test opportunities — concrete unit or acceptance tests that would verify requirements programmatically.

Input

• Requirements document: User specifies the path (e.g. openspec/specs/elasticsearch-security-role/spec.md) or the entity name/implementation path. Resolve to the spec.md under openspec/specs/<capability>/ (or the relevant delta spec path).
• Implementation: From the doc’s “Resource implementation” or “Data source implementation” line (e.g. internal/elasticsearch/security/role). Use that package for compliance and test analysis.

Workflow

0. OpenSpec structural validation (recommended when a shell is available)

Before deep analysis, run the OpenSpec CLI so the spec matches what CI enforces. This checks structure (e.g. ### Requirement: / #### Scenario: shape, SHALL / MUST in requirement bodies)—not semantic consistency or implementation compliance.

• Repo root, after make setup (or make setup-openspec / npm ci):
  make check-openspec
  or: OPENSPEC_TELEMETRY=0 ./node_modules/.bin/openspec validate --specs
• Single spec (optional): OPENSPEC_TELEMETRY=0 ./node_modules/.bin/openspec validate <capability> --type spec (e.g. elasticsearch-security-role)
• Active change deltas (optional): openspec validate --all to include openspec/changes/**

If validation fails, report the CLI errors first and fix the markdown before spending effort on sections 1–3. If no terminal is available, proceed with manual review and note that openspec validate was not run.

1. Parse the requirements document

• Read the doc and extract: title/type name, implementation path (from Resource implementation: / Data source implementation: / Workflow implementation: / Script implementation:), Purpose, Schema (HCL/YAML block if present).
• List every ### Requirement: section: id (use (REQ-NNN) or (REQ-001–REQ-003) from the heading if present; otherwise derive a short id from the heading), category (infer from content: API, Identity, Import, etc.), and text (full SHALL/MUST statements in that section). Normalize references (e.g. “id format”, “cluster_uuid/name”) for consistency checks.

2. Internal consistency

Apply the checks in reference.md (Consistency checks):

• Identity/Import: Same id format in Identity and Import requirements; no conflicting formats.
• Schema vs requirements: Required/optional/computed in schema matches what requirements imply (e.g. “when X is configured” implies X is optional or optional+computed).
• Lifecycle: No requirement that X triggers replace and another that X is updated in place.
• Compatibility: Version numbers and feature names aligned across requirements; no conflicting minimum versions for the same feature.
• State/Plan: No requirement that the resource “preserve null” and another that it “store empty list” for the same field.
• StateUpgrade: Referenced prior schema version exists; upgrade steps are ordered and non-conflicting.

Output: Consistent or list Inconsistencies with requirement ids and short explanation.

3. Implementation compliance

• Resolve implementation package from the doc (e.g. internal/elasticsearch/security/role). Locate resource.go, schema.go, create.go, read.go, update.go, delete.go, models.go, state upgrade code, and any validators/plan modifiers.
• For each requirement, determine where the behavior would be implemented (see reference.md “Requirement → implementation mapping”). Search or read that code and verify the behavior.
• Classify each requirement: Met (code clearly implements it), Not met (code contradicts or omits it), Unclear (cannot determine from code or tests).
• Output: Table or list: REQ-ID, Category, Status (Met / Not met / Unclear), Evidence (file/function or “not found”).

4. Test opportunities

• Locate unit tests: *_test.go in the implementation package (e.g. resource_test.go, state_upgrade_test.go) and acceptance tests: acc_test.go (or *_acc_test.go) for the resource.
• For each requirement, decide whether it is verifiable by unit test (e.g. state upgrade logic, id parsing, validation) or verifiable by acceptance test (e.g. create/read/update/delete, import, error diagnostics). See reference.md “Test opportunity patterns”.
• Identify requirements that are not covered by existing tests (or only weakly covered). Suggest concrete test cases: unit test name + scenario, or acceptance test step (config + checks) that would assert the requirement.
• Output: List of Suggested tests, each with: requirement id(s), type (unit / acceptance), description, and how it would verify the requirement.

5. Report

Produce a single report with three sections:

1. Internal consistency: Result + any inconsistencies.
2. Implementation compliance: Summary (e.g. X/Y met, Z unclear) + per-requirement status table.
3. Test opportunities: List of suggested tests with requirement ids and verification approach.

Output format

markdown
1# Requirements analysis: <entity name>
2
3**Document**: `openspec/specs/.../spec.md`  
4**Implementation**: `internal/...` (or workflow/script path from the spec)
5
6## 1. Internal consistency
7
8- **Result**: Consistent | Inconsistent
9- **Inconsistencies** (if any): [REQ-xxx] vs [REQ-yyy]: ...
10
11## 2. Implementation compliance
12
13| REQ-ID | Category   | Status   | Evidence |
14|--------|------------|----------|----------|
15| REQ-001| API        | Met      | create.go, update.go call PutRole |
16...
17
18**Summary**: X met, Y not met, Z unclear.
19
20## 3. Test opportunities
21
22| REQ-ID(s) | Type       | Suggested test | Verifies |
23|-----------|------------|----------------|----------|
24| REQ-008   | Acceptance | Import with invalid id; expect error diagnostic | Import validation |
25...

Reference

• OpenSpec authoring and CLI overview: dev-docs/high-level/openspec-requirements.md
• Requirement categories and implementation mapping: reference.md
• Existing entity code-path checklist (for locating implementation): .agents/skills/existing-entity-requirements/reference.md
• Schema/acceptance test coverage (for test patterns): .cursor/skills/schema-coverage/ if analyzing attribute-level coverage alongside requirements.