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.zipInstalls 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 phaseKey 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
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-phaseas{{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:
header→headerquestion→question- Options formatted as
"Label" — description→{label: "Label", description: "description"} - Generate
idfrom header: lowercase, replace spaces with underscores
Batched calls:
AskUserQuestion([q1, q2])→ singlerequest_user_inputwith multiple entries inquestions[]
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_inputis rejected or unavailable, activate TEXT_MODE: append--textto{{GSD_ARGS}}so the workflow's built-in text-mode branching takes over. Present everyAskUserQuestioncall 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 (
--autoor--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_agenthas no inlinemodelparameter; GSD embeds the resolved per-agent model directly into each agent's.tomlat install time somodel_overridesfrom.planning/config.jsonand~/.gsd/defaults.jsonare honored automatically by Codex's agent router.- Resolved
reasoning_effort="low|medium|high|xhigh"(xhighis a GSD/Codex tier, not a generic runtime enum) → passreasoning_efforttospawn_agentwhen the runtime/tool supports it. Omit missing, empty, inherited, or unsupported values; do not invent one-off effort literals in workflow prose. fork_context: falseby default — GSD agents load their own context via<files_to_read>blocksTask(isolation="worktree")/Agent(isolation="worktree")→ no direct Codex mapping. Codexspawn_agentdoes 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_agentto 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_agentis not currently visible, discover tools first viatool_searchbefore 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>
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.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| gsd-validate-phase (this skill) | 0 | 1mo | No flags | Intermediate |
| tpp | 0 | 5mo | No flags | Intermediate |
| do-plan | 0 | 1mo | No flags | Advanced |
| acceptance-criteria | 0 | 3mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by pjmagee
View all by pjmagee →You might also like
tpp
photostructure
Work on a Technical Project Plan. Use when starting or continuing work on a TPP from _todo/.
do-plan
elekktrisch
(Re-)shape the remaining backlog into vertical journey slices — one SPA screen/route each, provable by a green Playwright run. Maintains a thin value-ordered roadmap and deep-carves ONE journey JIT for /do-ship. Trigger: /do-plan [J-NNN | next].
acceptance-criteria
Eric-Pacheco95
You expand a user story into a complete set of acceptance criteria using Given-When-Then (Gherkin) format. Cover the happy path, edge cases, negative paths, and applicable non-functional criteria. The output is ready to paste into Jira or a BDD test harness.
gsd-audit-uat
electroheadfx
Cross-phase audit of all outstanding UAT and verification items
empirical-validation
toonight
Requires proof before marking work complete — no "trust me, it works"
linear-ci-integration
jeremylongshore
Configure Linear CI/CD integration with GitHub Actions and testing. Use when setting up automated testing, configuring CI pipelines, or integrating Linear sync into your build process. Trigger with phrases like "linear CI", "linear GitHub Actions", "linear automated tests", "CI linear pipeline", "linear CI/CD".