From speckit-helper
Expertise in detecting inconsistencies, gaps, and conflicts across specification documents. Activates when user asks about document quality or consistency. Trigger keywords: consistency, analysis, gap analysis, conflict detection, spec review, cross-reference, traceability
npx claudepluginhub datamaker-kr/synapse-claude-marketplace --plugin speckit-helperThis skill is limited to using the following tools:
This skill provides expertise in detecting inconsistencies, gaps, and conflicts across specification documents. It performs read-only cross-document analysis to ensure that requirements, tasks, data models, and plans are aligned and complete. The output is a structured analysis report with categorized findings and severity levels.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
This skill provides expertise in detecting inconsistencies, gaps, and conflicts across specification documents. It performs read-only cross-document analysis to ensure that requirements, tasks, data models, and plans are aligned and complete. The output is a structured analysis report with categorized findings and severity levels.
IMPORTANT: This skill NEVER modifies files. It is strictly a read-only analysis tool. All findings are reported for human review and resolution.
The skill is triggered when the conversation involves:
The skill evaluates documents against eight rule categories:
Verify that every functional requirement (FR-XXX) and non-functional requirement (NFR-XXX) in the specification is addressed by at least one implementation task or plan item. Flag orphaned requirements with no downstream mapping.
Ensure every task in tasks.md traces back to a specific requirement or user story in spec.md. Flag tasks with missing [Spec §X.Y] references or invalid reference targets.
Check that the implementation plan is consistent with the task list and specification. Detect mismatches in scope, ordering assumptions, or phase assignments between documents.
Verify that entity definitions, field names, types, and relationships are consistent across the specification, data model section, and API contracts. Flag naming mismatches, type conflicts, or missing fields.
Ensure every API endpoint defined in the specification has corresponding tasks for implementation and testing. Flag endpoints missing from the task list or with incomplete request/response schema definitions.
If a project constitution exists, verify that the specification and tasks comply with its architectural principles, technology constraints, and coding conventions.
Identify duplicate or near-duplicate requirements, tasks, or definitions across documents. Flag redundancies that may lead to conflicting implementations or wasted effort.
Scan for vague, unmeasurable, or subjective language in requirements (e.g., "fast," "user-friendly," "scalable"). Flag ambiguous terms that need quantification or clarification.
Each finding is assigned a severity level:
| Severity | Meaning | Action Required |
|---|---|---|
| CRITICAL | Blocking issue that prevents correct implementation | Must resolve before proceeding |
| HIGH | Significant gap or conflict likely to cause defects | Should resolve before implementation |
| MEDIUM | Inconsistency that may cause confusion or rework | Resolve during implementation |
| LOW | Minor style or convention issue | Resolve at convenience |
The analysis report is structured as follows:
# Consistency Analysis Report
## Summary
- Total findings: N
- Critical: N | High: N | Medium: N | Low: N
## Findings
### [CRITICAL] RC-001: FR-012 has no implementing task
- **Category**: Requirement Coverage
- **Location**: spec.md FR-012
- **Details**: Payment retry logic requirement has no corresponding task in tasks.md.
- **Recommendation**: Add a task in the Stories phase covering FR-012.
### [HIGH] TT-001: Task T008 references non-existent FR-099
- **Category**: Task Traceability
- **Location**: tasks.md T008
- **Details**: The [Spec FR-099] reference does not match any requirement.
- **Recommendation**: Correct the reference or add the missing requirement.
Each finding includes an ID, category, location, detailed description, and a recommended resolution.
For detailed analysis rules, severity definitions, and configuration options, consult:
references/analysis-rules.md -- Full rule definitions with detection logic for each categoryreferences/severity-levels.md -- Severity classification criteria and escalation guidelines