GS

gsd-validate-phase

Retroactively audits completed phases to identify and resolve missing validation steps.

Install

mkdir -p .claude/skills/gsd-validate-phase-pjmagee && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18904" && unzip -o skill.zip -d .claude/skills/gsd-validate-phase-pjmagee && rm skill.zip

Installs to .claude/skills/gsd-validate-phase-pjmagee

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.

Retroactively audit and fill Nyquist validation gaps for a completed phase
74 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Audit Nyquist validation coverage
  • Identify gaps in validation
  • Reconstruct validation from existing artifacts
  • Generate updated VALIDATION.md files
  • Generate test files

How it works

The skill audits validation coverage for a completed phase by checking for an existing VALIDATION.md, reconstructing it from SUMMARY.md if absent, or exiting with guidance if the phase is not executed. It then updates VALIDATION.md and generates test files.

Inputs & outputs

You give it
A completed phase, optionally specified by GSD_ARGS
You get back
Updated VALIDATION.md and generated test files

When to use gsd-validate-phase

  • Auditing phase validation
  • Ensuring project quality standards
  • Filling missing test gaps

About this skill

<codex_skill_adapter>

A. Skill Invocation

  • This skill is invoked by mentioning $gsd-validate-phase.
  • Treat all user text after $gsd-validate-phase 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 or unavailable, activate TEXT_MODE: append --text to {{GSD_ARGS}} so the workflow's built-in text-mode branching takes over. Present every AskUserQuestion call as a plain-text numbered list, then stop and wait for the user's reply. Do NOT pick a default and continue (#3018 / #3808).
  • You may only proceed without a user answer when one of these is true: (a) the invocation included an explicit non-interactive flag (--auto or --all), (b) the user has explicitly approved a specific default for this question, or (c) the workflow's documented contract says defaults are safe (e.g. autonomous lifecycle paths).
  • Do NOT write workflow artifacts (CONTEXT.md, DISCUSSION-LOG.md, PLAN.md, checkpoint files) until the user has answered the plain-text questions or one of (a)-(c) above applies. Surfacing the questions and waiting is the correct response — silently defaulting and writing artifacts is the #3018 failure mode.

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")
  • Agent(subagent_type="X", prompt="Y")spawn_agent(agent_type="X", message="Y")
  • Task(model="...") → omit. spawn_agent has no inline model parameter; GSD embeds the resolved per-agent model directly into each agent's .toml at install time so model_overrides from .planning/config.json and ~/.gsd/defaults.json are honored automatically by Codex's agent router.
  • Resolved reasoning_effort="low|medium|high|xhigh" (xhigh is a GSD/Codex tier, not a generic runtime enum) → pass reasoning_effort to spawn_agent when the runtime/tool supports it. Omit missing, empty, inherited, or unsupported values; do not invent one-off effort literals in workflow prose.
  • fork_context: false by default — GSD agents load their own context via <files_to_read> blocks
  • Task(isolation="worktree") / Agent(isolation="worktree") → no direct Codex mapping. Codex spawn_agent does not create or bind a git worktree automatically. Workflows that require this isolation must fail closed or use an explicit manual worktree protocol before spawning (#3360).

Spawn restriction:

  • Codex restricts spawn_agent to cases where the user has explicitly requested sub-agents. When automatic spawning is not permitted, do the work inline in the current agent rather than attempting to force a spawn.
  • In some Codex sessions, multi-agent tooling can be deferred. If spawn_agent is not currently visible, discover tools first via tool_search before defaulting to inline execution.

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> Audit Nyquist validation coverage for a completed phase. Three states: - (A) VALIDATION.md exists — audit and fill gaps - (B) No VALIDATION.md, SUMMARY.md exists — reconstruct from artifacts - (C) Phase not executed — exit with guidance

Output: updated VALIDATION.md + generated test files. </objective>

<execution_context> @D:/Projects/pjmagee/multi-stream-viewer/.codex/gsd-core/workflows/validate-phase.md </execution_context>

<context> Phase: {{GSD_ARGS}} — optional, defaults to last completed phase. </context> <process> Execute end-to-end. Preserve all workflow gates. </process>

When not to use it

  • When the user explicitly requests a non-interactive flag
  • When the user has explicitly approved a specific default

Limitations

  • The skill does not proceed without a user answer unless specific conditions are met.
  • It does not write workflow artifacts until user questions are answered or conditions apply.

How it compares

This skill automates the process of auditing and filling validation gaps, providing a structured approach compared to manually reviewing project artifacts.

Compared to similar skills

gsd-validate-phase side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
gsd-validate-phase (this skill)01moNo flagsIntermediate
tpp05moNo flagsIntermediate
do-plan01moNo flagsAdvanced
acceptance-criteria03moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry