Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Assessment — Read-Only Analysis & Decision Support Skill

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

Dev & CodingIntermediate★ 421⑂ 44AI score 9/10Last updated: Sep 19, 2026

What it does

  • Routes your request to one of seven modes: read-only inspection, codebase overview, repo value analysis, service health check, ADR consultation, decision scoring, and multi-persona critique.
  • Read-only inspection enumerates allowed commands (ls, git log, curl -s) versus forbidden ones (rm, git commit, npm install), so nothing gets mutated.
  • Codebase overview runs DETECT → EXPLORE → MAP → SUMMARIZE with per-phase gates, absolute paths, evidence citations, and a post-run secret scan.
  • ADR consultation dispatches three parallel agents (contrarian, user advocate, meta-process) and returns a PROCEED or BLOCKED verdict with a written synthesis.
  • Decision scoring locks a weighted rubric (Correctness 5, Complexity 3, Maintainability 3, Risk 3, Effort 2, Familiarity 2, Ecosystem 1) before any scores are assigned.

Who it's for

  • Engineers who must get productive in an unfamiliar repository fast
  • Tech leads who want structured pushback before committing to an architecture decision
  • Teams comparing technology options who prefer a scored matrix over gut feel
  • Product/design folks who want ideas stress-tested from multiple viewpoints

Examples

  1. "Give me an overview of this repo" → onboarding report covering entry points, core modules, data layer, API surface, config, and tests.
  2. "Check whether the services are healthy" → verifies process via pgrep, parses the health JSON for staleness, checks the listening port, then reports X/N healthy with copy-pasteable remediation.
  3. "Help me decide between Postgres and DynamoDB" → weighted matrix with per-criterion justifications and a >0.5 margin rule for declaring a winner.
  4. "Roast these proposals" → five personas critique in parallel, then a consensus matrix classifies each idea as CONSENSUS, CONTESTED, or OUTLIER.

· · · 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 Claude 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 /tmp/vexjoy-agent && mkdir -p ~/.claude/skills && cp -r /tmp/vexjoy-agent/skills/analysis/assessment ~/.claude/skills/assessment

⚠ 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 it does not exist: mkdir -p ~/.claude/skills
  3. Copy the entire skill folder so the bundled references/ and scripts/ come along: cp -r vexjoy-agent/skills/analysis/assessment ~/.claude/skills/assessment
  4. Verify the copy: ls ~/.claude/skills/assessment
  5. Restart Claude Code and confirm assessment appears in your skill list.
  6. Trigger it with a phrase such as "summarize this repo" or "help me decide".
  7. Install Python 3 if you plan to use the scripts/cartographer*.py helpers.
View source on GitHub ↗License: MIT