stark-ai-de/agent-skills / plugins/stark-ai-developer/skills/codex-spec-interviewer
codex-spec-interviewer
VerifiedTurn ambiguous coding requests into verified Codex implementation specs. Use when the user wants requirements, an implementation plan, or a spec before coding; include source checks, needed ADRs, and agreed delivery. Do not use for already specified direct implementation or memory cleanup.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.7 KB |
| agents/openai.yaml | config | 470 B |
| assets/codex-execution-prompt.md | markdown | 6.1 KB |
| assets/example-repo-refactor.spec.md | markdown | 10.0 KB |
| assets/example-small-task.spec.md | markdown | 3.5 KB |
| assets/openai-icon.png | binary | 32.8 KB |
| assets/product-planning-work-item.md | markdown | 2.6 KB |
| assets/spec-template.compact.md | markdown | 1.5 KB |
| assets/spec-template.deep.md | markdown | 3.9 KB |
| assets/spec-template.standard.md | markdown | 3.3 KB |
| references/adr-gate.md | markdown | 2.7 KB |
| references/artifact-destinations.md | markdown | 3.0 KB |
| references/host-adapters.md | markdown | 8.7 KB |
| references/product-planning-handoffs.md | markdown | 2.2 KB |
| references/question-bank.md | markdown | 4.8 KB |
| references/rollout-checklist.md | markdown | 2.7 KB |
| references/source-challenge.md | markdown | 2.5 KB |
| references/spec-rubric.md | markdown | 6.5 KB |
| references/workflow-details.md | markdown | 9.0 KB |
references/product-planning-handoffs.md
View on GitHub# Coordinated product-planning handoffs
Use only when a work item or accepted local coordination rule is supplied. Independent interviewer requests keep the existing workflow and do not require Architecture Zoom or Architecture Compass.
Read product-planning/v1 context through the [work-item template](../assets/product-planning-work-item.md). Reuse the product/release/slice identity, current blueprint, canonical contracts, relevant revision and uncommitted state, answered questions, fixed scope and non-goals, acceptance, evidence limits and genuine authorizations. A hash or approval field does not supply permission. Current local ADRs and host controls remain authoritative.
Select compact/standard/deep as before. Specify only the selected next slice, tracing it to a release that closes a complete user promise. A ticket or technical enabler can be smaller than that release but must name its consuming outcome; do not call it an MVP. Include success, material failure/recovery behavior and the required real integration/end-to-end evidence, not just mocked module tests.
If a material product promise is missing, return a targeted Zoom handoff to the coordinator. If a module contract or accepted architecture decision is unresolved, return its identity, violated criterion and bounded question for Compass. Do not start another whole planning chain, invoke unselected skills, save during audit/Plan, or change acceptance to bypass a blocker. Independent permitted draft work can continue.
Required decisions are handled through the existing ADR gate. One concrete final checkpoint can cover the unchanged spec and its authorized writes; reuse prior exact approval instead of asking again at every handoff. New outcomes, materially changed content or uncovered effects need their own decision. Delegates return results; one main agent integrates canonical artifacts.
On completion, emit the existing execution prompt with the current product/release/slice, scoped paths, non-goals, acceptance, relevant contracts and stop conditions. Do not implement. Stop when the planning deliverable is complete; optional improvements stay outside it. A later independently authorized implementation workflow may resume.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |