SkillsAdd

smithery/neversight

spec-analyze

Perform non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md. Use when user says "/spec-analyze", "analyze the spec", "check consistency" after /spec-tasks to identify issues before implementation.

Installation

$ npx skills add smithery/neversight --skill spec-analyze
View on skills.sh ↗ Website ↗

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

terraform-azurerm-set-diff-analyzer Similar name
github/awesome-copilot

Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive d…

8.9K installs
analyze Similar name
anthropics/knowledge-work-plugins

Answer data questions -- from quick lookups to full analyses. Use when looking up a single metr…

5.3K installs
tao-analyze-changenet-rca Similar name
nvidia/skills

Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experimen…

1.6K installs
tao-analyze-gaps-visual-changenet Similar name
nvidia/skills

Performs gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking…

1.5K installs
tao-analyze-gaps-vlm-bcq Similar name
nvidia/skills

Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, ye…

1.5K installs
margin-analyzer Similar name
anthropics/knowledge-work-plugins

Analyzes unit economics by product or service using PayPal merchant insights and QuickBooks cos…

1.4K installs

Also in this package

Other skills from smithery/neversight · top by installs.

npx skills add smithery/neversight
zoom-meeting 0 ziwei-doushu 0 zimage-skill 0 zig 0 zhimeng-agent 0 zfc 0 zenbin 0 zeberg-salomon-rotator 0 zdev 0 youtube-transcript 0

Browse all from smithery/neversight

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,844 B
  • docs SUMMARY.md 266 B

History

  1. First recorded snapshot · 0 installs

SKILL.md

Spec-Analyze

Cross-artifact consistency analysis - READ-ONLY, no file modifications.

Prerequisites: tasks.md must exist (run /spec-tasks first).

Workflow

  1. Initialize - Run .specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks
  2. Load artifacts - spec.md, plan.md, tasks.md, constitution.md
  3. Build semantic models - Requirements inventory, task mapping
  4. Detection passes - 6 analysis categories
  5. Assign severity - CRITICAL/HIGH/MEDIUM/LOW
  6. Produce report - Markdown table with findings
  7. Offer remediation - Ask before any edits

Detection Categories

A. Duplication Detection

  • Near-duplicate requirements
  • Mark lower-quality for consolidation

B. Ambiguity Detection

  • Vague adjectives (fast, scalable, intuitive)
  • Unresolved placeholders (TODO, ???)

C. Underspecification

  • Verbs without measurable outcomes
  • Missing acceptance criteria
  • Tasks referencing undefined components

D. Constitution Alignment

  • MUST principle violations → CRITICAL
  • Missing mandated sections

E. Coverage Gaps

  • Requirements with zero tasks
  • Tasks with no mapped requirement
  • Non-functional requirements not in tasks

F. Inconsistency

  • Terminology drift
  • Missing data entities
  • Task ordering contradictions
  • Conflicting requirements

Severity Levels

Level Criteria
CRITICAL Constitution violation, missing core artifact, baseline blocker
HIGH Duplicate/conflicting requirement, untestable criterion
MEDIUM Terminology drift, missing NFR coverage
LOW Style/wording, minor redundancy

Report Format

## Specification Analysis Report

| ID | Category | Severity | Location(s) | Summary | Recommendation |
|----|----------|----------|-------------|---------|----------------|
| A1 | Duplication | HIGH | spec.md:L120 | Similar requirements | Merge phrasing |

**Coverage Summary:**
| Requirement | Has Task? | Task IDs |
|-------------|-----------|----------|

**Metrics:**
- Total Requirements: X
- Coverage %: Y%
- Critical Issues: Z

Operating Constraints

  • STRICTLY READ-ONLY - No file modifications
  • Constitution is non-negotiable - Violations are CRITICAL
  • Max 50 findings (aggregate overflow)
  • Deterministic results on rerun

Next Actions

  • CRITICAL issues → Resolve before /spec-implement
  • LOW/MEDIUM only → May proceed with suggestions

Next Steps

After /spec-analyze:

  • Fix identified issues
  • /spec-implement - Execute implementation