Menu
Use when planning has an approved work shape and needs feasibility validation before swarming.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when the user asks to commit everything, smart commit, group commits, organize staged or unstaged changes, create logical commits, push current work, or preserve a clean commit stack from an existing working tree.
Use when starting or resuming any Khuym project session, choosing the next Khuym skill, running go mode, checking onboarding/scout state, or enforcing workflow gates. Bootstrap meta-skill for routing across the Khuym agentic development ecosystem.
Use when the user wants to turn a rough idea, vague task, feature wish, bug-fix intent, or Codex /goal objective into a clear verifiable goal prompt. Use when the user mentions goal mode, /goal, set_goal, long-running autonomous Codex work, or asks to be interviewed/grilled before creating a goal.
Create self-contained interactive HTML visual explainers that turn difficult topics, concepts, code, math, systems, or arguments into memorable explorable artifacts. Use when Codex should research a topic, choose an interaction model, and build an artifact with simulations, diagrams, charts, sliders, hover inspection, scrollytelling, or small game mechanics so readers can explore and understand the message.
Use when Codex should turn a concept, topic, tutorial, lesson, algorithm, system, workflow, or abstract idea into a playable browser game that teaches through interaction. Use for planning or implementing educational web games with the Game Studio plugin, including concept-to-mechanic translation, gameplay loop design, learning progression, and browser-game QA.
Use when exploring has locked CONTEXT.md and the work needs planning before validation.
| name | validating |
| description | Use when planning has an approved work shape and needs feasibility validation before swarming. |
| metadata | {"version":"1.2","position":3,"chain":"exploring -> planning -> validating -> swarming","ecosystem":"khuym","dependencies":{"beads-cli":{"kind":"command","command":"br","missing_effect":"unavailable","reason":"Validation creates and closes spike beads during gating."},"beads-viewer":{"kind":"command","command":"bv","missing_effect":"unavailable","reason":"Validation depends on bv graph checks for polishing and risk review."}}} |
If .khuym/onboarding.json is missing or stale for the current repo, stop and invoke khuym:using-khuym before continuing.
Validating is the hard gate between planning and execution. It rejects beautiful fantasy plans by requiring repo/system evidence, feasibility proof, and current-story readiness.
history/<feature>/CONTEXT.mdhistory/<feature>/discovery.mdhistory/<feature>/approach.mdphase-plan.md, or epic-map.mdcurrent-story-pack.md, phase-<n>-contract.md, or story map.beads/ for the current execution surface when beads are requiredIf any mode-required input is missing, return to khuym:planning. If the shape artifact has not been approved by the user, stop immediately.
.spikes/.Load references/validation-reference.md for the detailed checklist, repair routing, spike handling, approval gate, and subagent prompts.
NO spike result returns the workflow to khuym:planning.When the user approves, update .khuym/state.json so the next action is swarming:
{
"active_skill": "validating",
"feature_slug": "<feature-name>",
"phase": "validated",
"mode": "<mode>",
"current_work": "<story/direct/phase>",
"summary": "Current work passed feasibility validation and is ready for swarming.",
"next_action": "Invoke khuym:swarming for the validated work."
}
Then hand off: Validation complete. Current work passes. Invoke khuym:swarming skill.
| File | When to Load |
|---|---|
references/validation-reference.md | Validation phases, repairs, approval, plan-checker, bead-reviewer |