aliatx2017/reasonix-hermes/intent-gap-analysis

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Analyze a codebase by identifying where the implementation lags behind the stated intent, rather than searching for generic improvements or missing features.

Install

npx vskill@latest install aliatx2017/reasonix-hermes/intent-gap-analysis

SKILL.md

Intent Gap Analysis

When to Use

  • User asks "is this codebase doing what it claims to do?"
  • Auditing a project against its stated goals or SPEC.md
  • Comparing implementation against constitution or design principles
  • Finding drift between documentation and reality

Method

Instead of searching for "what's missing" (which returns everything), compare the codebase against its OWN stated intent:

  1. Extract intent — Read SPEC.md, README, constitution, package comments, design docs
  2. Map implementation — For each stated intent, find the corresponding code paths
  3. Measure gap — Where does the implementation fall short of the intent?
  4. Prioritize — Rank gaps by impact: correctness > security > performance > completeness

Output

A markdown report with:

## Intent vs. Implementation
| Stated Intent | Source | Implementation | Gap | Severity |
|--------------|--------|---------------|-----|----------|
| "Single static binary" | SPEC.md §1.2 | go build produces 6 binaries | 6 binaries, not 1 | Low |
| "Cache-first prefix" | constitution.json | controller.go Compose | ✅ matches | None |
...

Key Questions

  • What does this codebase CLAIM to be/do?
  • Where in the code is each claim implemented?
  • What claims have no corresponding code?
  • What code exists that contradicts a claim?
  • What's changed since the docs were written?

Related

  • Project skill: evidence-first-reasoning — verify discriminatively
  • Project skill: github-repo-eval — evaluate external repos
  • Constitution: .reasonix/constitution.json — project invariants
  • SPEC: docs/SPEC.md — engineering contract

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/aliatx2017/reasonix-hermes/intent-gap-analysis/badge)](https://verified-skill.com/skills/aliatx2017/reasonix-hermes/intent-gap-analysis)

Something wrong with this skill or its page? Tell us.