Checks for structural integrity in planning directories and fixes common issues.

Install

mkdir -p .claude/skills/gsd-health && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12852" && unzip -o skill.zip -d .claude/skills/gsd-health && rm skill.zip

Installs to .claude/skills/gsd-health

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Diagnose planning directory health and optionally repair issues
63 charsno explicit “when” trigger
Beginner

Key capabilities

  • Diagnose `.planning/` directory integrity
  • Check for missing GSD files
  • Identify invalid GSD configurations
  • Detect inconsistent GSD state
  • Find orphaned GSD plans
  • Optionally repair identified issues

How it works

The skill scans the `.planning/` directory for missing files, invalid configurations, inconsistent state, and orphaned plans, then reports these issues and can optionally repair them.

Inputs & outputs

You give it
A request to check GSD planning directory health, optionally with a '--repair' flag
You get back
A report of issues found in the `.planning/` directory, with optional repairs applied

When to use gsd-health

  • Check planning directory integrity
  • Fix broken GSD state
  • Verify project health
  • Repair missing artifacts

About this skill

<codex_skill_adapter>

A. Skill Invocation

  • This skill is invoked by mentioning $gsd-health.
  • Treat all user text after $gsd-health as {{GSD_ARGS}}.
  • If no arguments are present, treat {{GSD_ARGS}} as empty.

B. AskUserQuestion → request_user_input Mapping

GSD workflows use AskUserQuestion (Claude Code syntax). Translate to Codex request_user_input:

Parameter mapping:

  • headerheader
  • questionquestion
  • Options formatted as "Label" — description{label: "Label", description: "description"}
  • Generate id from header: lowercase, replace spaces with underscores

Batched calls:

  • AskUserQuestion([q1, q2]) → single request_user_input with multiple entries in questions[]

Multi-select workaround:

  • Codex has no multiSelect. Use sequential single-selects, or present a numbered freeform list asking the user to enter comma-separated numbers.

Execute mode fallback:

  • When request_user_input is rejected (Execute mode), present a plain-text numbered list and pick a reasonable default.

C. Task() → spawn_agent Mapping

GSD workflows use Task(...) (Claude Code syntax). Translate to Codex collaboration tools:

Direct mapping:

  • Task(subagent_type="X", prompt="Y")spawn_agent(agent_type="X", message="Y")
  • Task(model="...") → omit (Codex uses per-role config, not inline model selection)
  • fork_context: false by default — GSD agents load their own context via <files_to_read> blocks

Parallel fan-out:

  • Spawn multiple agents → collect agent IDs → wait(ids) for all to complete

Result parsing:

  • Look for structured markers in agent output: CHECKPOINT, PLAN COMPLETE, SUMMARY, etc.
  • close_agent(id) after collecting results from each agent </codex_skill_adapter>
<objective> Validate `.planning/` directory integrity and report actionable issues. Checks for missing files, invalid configurations, inconsistent state, and orphaned plans. </objective>

<execution_context> @C:/Users/gusta/OneDrive/Documentos/gerenciador-de-quadras/.codex/get-shit-done/workflows/health.md </execution_context>

<process> Execute the health workflow from @C:/Users/gusta/OneDrive/Documentos/gerenciador-de-quadras/.codex/get-shit-done/workflows/health.md end-to-end. Parse --repair flag from arguments and pass to workflow. </process>

When not to use it

  • When the user needs to execute GSD workflows
  • When the user needs to modify project content outside of GSD planning files

Limitations

  • The skill is specific to GSD planning directories
  • The skill focuses on directory integrity and state consistency
  • The skill's repairs are limited to GSD-related issues

How it compares

This skill provides an automated health check and repair mechanism for GSD planning directories, ensuring workflow continuity and data integrity, unlike manual inspection and correction.

Compared to similar skills

gsd-health side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
gsd-health (this skill)04moNo flagsBeginner
dispatching-parallel-agents03moNo flagsAdvanced
n8n-expression-syntax64moNo flagsBeginner
python-repl64moReviewBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry