Health (Grade A) logo

Health (Grade A)Security-tested development skill for Claude AI. Grade A. Check planning directory integrity. Find and fix corrupted state.

— (0)
Daniel NikulshynReviewed by Daniel Nikulshyn·Updated July 2026

Overview

The Health skill for Claude AI is a security-tested development tool designed to check the integrity of the planning directory and fix corrupted states. It runs inline and is read-only by default but offers an optional auto-fix flow for common corruption patterns. The tool validates the .planning/ directory, reports problems, and suggests targeted fixes. It uses a CLI-driven approach via 'verify health' and returns a JSON object with check results, including status, message, and fix suggestions. The tool can automatically apply fixes for certain issues when the '--repair' flag is used. The Health skill performs various checks, including verifying the STATE.md frontmatter, phase_slug consistency, config.json existence, and the presence of the phases directory. It also detects and handles issues like orphaned .active-skill files and empty phases directories. The tool provides a branded output with a summary table, status indicators, issues list, and a final result line. If any auto-fixable issues are found, it offers to apply fixes immediately. The Health skill is part of the plan-build-run system and requires Read, Write, Bash, Glob, Grep, and AskUserQuestion tools. Overall, the Health skill helps maintain the integrity and consistency of the planning directory, ensuring that the system operates correctly and efficiently.

Key features

  • Checks planning directory integrity
  • Fixes corrupted states
  • Optional auto-fix flow
  • Detailed output with status indicators

Pricing

Model
Free
Category
Skills
Rating
No reviews yet

Use cases

Planning Directory Validation

Use the Health skill to validate the integrity of the .planning/ directory and detect potential issues.

Automated Issue Resolution

Run the Health skill with the '--repair' flag to automatically apply fixes for common corruption patterns.

Pros & Cons

Pros

  • Validates planning directory integrity
  • Detects and fixes common corruption patterns
  • Optional auto-fix flow for easy issue resolution
  • Provides detailed output with status indicators and fix suggestions

Cons

  • Requires CLI-driven approach, which may not be user-friendly for non-technical users
  • Limited to specific checks and auto-fixable issues

Reviews

Sign in to leave a review.

No reviews yet. Be the first!

Q&A

Do I need technical expertise to use the Health skill effectively?

The tool is CLI‑driven, so basic command‑line familiarity is required. While it automates detection and repair, non‑technical users may find the interface less user‑friendly compared to graphical tools.

Asked by Boris Yankov · Feb 19, 2026

What kind of output does the Health skill provide after a check?

The command returns a JSON object that includes each check’s status, a descriptive message, and any suggested or applied fix details, giving you a clear view of the directory’s health.

Asked by Wei Chen · Jan 27, 2026

Is the Health skill read‑only by default, and can I opt into automatic fixes?

Yes, the tool runs in read‑only mode by default. You can enable the optional auto‑fix flow by adding the `--repair` flag to the `verify health` CLI command, which will apply fixes for supported issues.

Asked by Quentin Lefevre · Jan 11, 2026

How does the Health skill detect and repair corrupted planning directories?

It validates the .planning/ directory, checking items like STATE.md frontmatter, phase_slug consistency, config.json, and the phases folder. When run with the `--repair` flag, it automatically applies fixes for known corruption patterns and returns a JSON report with status, messages, and fix suggestions.

Asked by Sanjay Gupta · Dec 8, 2025

Ask a question

Skills alternatives

Using Git Worktrees (Grade A) logo
Using Git Worktrees (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktre

— (0)
Free
Ga4 Bigquery Schema (Grade A) logo
Ga4 Bigquery Schema (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. GA4 BigQuery Export Schema Reference — complete field reference, nested structures, query patterns, and performance tips

— (0)
Free
Meta Capi (Grade A) logo
Meta Capi (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Meta Conversions API (CAPI) Setup Reference — architecture, event types, customer information hashing, deduplication, implementation examples, AEM

— (0)
Free
Callees (Grade A) logo
Callees (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. Lista o que uma funcao/metodo chama (call graph direto)

— (0)
Free
Test Module Name (Grade A) logo
Test Module Name (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Name Haskell test modules after the module under test with a Spec suffix in the same namespace. Use when writing or reviewing Haskell test module

— (0)
Free
Board Of Directors (Grade A) logo
Board Of Directors (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Simulate a 5-member expert board deliberation for major decisions. Use when evaluating plans, architecture choices, feature designs, or any decisi

— (0)
Free
Advpl Mvc Avancado (Grade A) logo
Advpl Mvc Avancado (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. MVC avançado via PE (Pontos de Entrada) — adicionar grids customizadas em telas MVC padrão (CNTA300/MATA070/MATA440/MATA460/FINA040 via *STRU)

— (0)
Free
D
Docs Writer (Grade A)Skills

Security-tested devops skill for Claude AI. Grade A. **WORKFLOW SKILL** — Maintains repository documentation accuracy and freshness across the docs site, agent files, and changelog. WHEN: "update docs

— (0)
Free