Project Health
Assess an active project against plan, risk, and team signals and return a consistent health verdict with next actions.
Before & after
Same prompt, same agent — the only difference is the skill.
I can help assess your project's health. To do this effectively, I'd need to understand a few things about your setup. You might want to check test coverage, dependency security, documentation completeness, and deployment status. These are common areas where projects tend to slip. If you can share details about your current state, I'd be happy to provide more specific guidance.
PROJECT HEALTH REPORT CRITICAL ISSUES (fix immediately) -> 3 unpatched security vulnerabilities in dependencies • lodash-es v4.17.15: prototype pollution risk • next-auth v4.2: session fixation (3.5 CVSS) • react-dom v18.0.1: reconciliation bug -> 2 failing test suites blocking CI/CD • auth integration tests (5 failures) • payment webhook handler (3 failures) WARNINGS (address in next sprint) -> Type coverage dropped to 82% (was 94%) -> Database migration queue: 4 pending migrations, oldest is 14 days -> Missing error boundaries in 3 new feature routes OPPORTUNITIES -> Bundle size grew 340 KB; consider code-splitting admin routes -> API response time P95 at 1.2s; cache layer underutilized -> Sentry captures 47 unique errors daily, top 5 errors account for 68% NEXT ACTION: Merge open PRs fixing auth tests, then deploy v2.1.4 with security patches.
About this skill
name: project-health description: Use when Structured Claude skill that gives Claude a repeatable workflow for project health.
Project Health
One of 337+ skills in the original author's multi-agent claude-skills mega-collection (~19k GitHub stars). Packages the Project Health workflow with its own instructions and validation so outputs stay consistent.
What you get
- Public GitHub repo (alirezarezvani/claude-skills)
- the project-health skill folder with SKILL.md. Part of a 337-skill / 30-agent / 70-command install.
Customize your output
- Fork the repo and adapt the skill's instructions and references to your workflow.
Example output
Activates automatically when your request matches Project Health; chains with the other skills, agents, and commands in the collection.
Best for
Creators, builders, and teams using Claude Code.
SKILL.md preview
---
name: project-health
description: Use this skill when the user wants a repeatable, structured workflow for assessing project health.
version: 1.0.0
category: AI Agents / Development
author: AgentVolt
license: proprietary
tags:
- ai-agents
- development
---
# Project Health
Provides a structured, repeatable workflow for assessing the health of an active project, with consistent instructions and validation so outputs stay comparable across runs.
## When to use
… (sign up to view the full skill)More ai & agents skills
View all AI & Agents skills →Skill Status Report
Scan every skill in a project and report which pass validation, which are stale, and which lack required metadata.
Skills Scaffolder
Scaffold a new skills directory — folder structure, metadata, a baseline validation pass — with the right conventions from day one.
Research Bundle
Run a multi-step research task as one pipeline: gather sources, extract findings, validate consistency, emit one structured bundle.
Workspace Admin
Administer a Cowork or Claude workspace — settings, access, configuration — with every change scoped and verified.