AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Assessment — Read-Only Analysis & Decision Support

A seven-mode read-only skill for codebase onboarding, service health checks, ADR consultation, decision matrices, and multi-persona critique.

Dev & CodingIntermediate★ 445⑂ 51AI score 9/10Last updated: Nov 3, 2026

What it does

Routes an analysis request into one of seven inspection-only modes:

  • Read-Only Inspection — explicit allow list (ls, git log, ps, curl -s GET) and forbid list (rm, git commit, package installs, systemctl restart).
  • Codebase Overview — 4 phases (DETECT → EXPLORE → MAP → SUMMARIZE) with gates, producing an evidence-backed onboarding report plus a "Where to Add New Code" section; supports a parallel 4-agent deep dive.
  • Repo Value Analysis — shallow-clones an external repo, zones its files, dispatches up to 8 reader agents, builds a comparison table, grades gaps HIGH/MEDIUM/LOW, then audits each recommendation.
  • Service Health Check — cross-checks pgrep, health-file JSON staleness, and listening ports into DOWN/WARNING/ERROR/HEALTHY, never auto-restarting.
  • ADR Consultation — three parallel reviewer agents (contrarian, user advocate, meta-process) yielding PROCEED or BLOCKED.
  • Decision Scoring — weights locked before scoring (Correctness 5, Complexity 3, Maintainability 3, Risk 3, Effort 2...), then weighted averages with tie-break guidance.
  • Multi-Persona Critique — five personas rate proposals STRONG/PROMISING/WEAK/REJECT, synthesized into a consensus matrix.

Who it's for

  • Engineers and tech leads who must get oriented in an unfamiliar repository fast
  • Teams that want defensible, written reasoning behind architecture or build-vs-buy decisions
  • Operators who need a safe "audit current state" pass with no writes

Examples

  1. "Summarize this repo" → Codebase Overview detects the stack from package.json/go.mod, maps entry points and key abstractions, and cites absolute file paths for every claim.
  2. "Help me decide between managed Postgres and DynamoDB" → Decision Scoring locks weights, scores each option 1–10 with one-line justifications, and flags a close call when the top two land within 0.5.
  3. "Poke holes in this proposal" → Multi-Persona Critique runs five reviewers in parallel and returns a consensus matrix with 0–15 totals per proposal.

Caveats

Most modes load files under references/ and scripts/, so copy the full skill folder. Despite the read-only framing, Write, Edit, and Bash are still in allowed-tools.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/notque/vexjoy-agent/HEAD/skills/analysis/assessment/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/analysis/assessment folder from the GitHub repo notque/vexjoy-agent into my ~/.claude/skills/assessment/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/notque/vexjoy-agent.git && mkdir -p ~/.claude/skills && cp -r vexjoy-agent/skills/analysis/assessment ~/.claude/skills/assessment && cp -r vexjoy-agent/skills/shared-patterns ~/.claude/skills/shared-patterns

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repository: git clone https://github.com/notque/vexjoy-agent.git
  2. Create the skills directory if needed: mkdir -p ~/.claude/skills
  3. Copy the skill: cp -r vexjoy-agent/skills/analysis/assessment ~/.claude/skills/assessment
  4. Verify the supporting assets came along: ls ~/.claude/skills/assessment/references ~/.claude/skills/assessment/scripts
  5. For the report self-review step, also copy shared patterns: cp -r vexjoy-agent/skills/shared-patterns ~/.claude/skills/shared-patterns
  6. Restart Claude Code, then try "give me an overview of this repo" or "build a decision matrix" to confirm the skill triggers.
  7. For maximum safety, state "read-only, do not modify files" in your request, since the skill still declares write-capable tools.
View source on GitHub ↗License: MIT