Skip to content

stark-ai-de/agent-skills / plugins/stark-ai-developer/skills/codex-spec-interviewer

codex-spec-interviewer

Verified

Turn 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.

assets/product-planning-work-item.md

View on GitHub
# Product-planning work item

> Derived, non-normative asset. The applicable canonical Long ADRs prevail.

> Contract: product-planning/v1. A Markdown handoff, not a native host schema or an authorization token. Reference canonical artifacts; do not copy their whole contents. This template is owned by Architecture Compass and synchronized into its consumers.

## Identity and intent

- Work item and requested outcome:
- Product goal / capability / release / next slice:
- Current stage and next missing result:
- Coordinator and artifact owner:
- Delivery boundary: conversation | authorized documents | separately authorized implementation
- Explicit non-goals:

## Current context

| Canonical artifact                     | Relevant revision or content digest | Purpose / consumers | Current, changed, or unknown |
| -------------------------------------- | ----------------------------------- | ------------------- | ---------------------------- |
| Product blueprint / delivery map       |                                     |                     |                              |
| Module contracts / accepted local ADRs |                                     |                     |                              |
| Current spec / acceptance scenarios    |                                     |                     |                              |

Record relevant uncommitted changes as well as HEAD. A digest detects change; it does not establish truth, approval, or host loading. Ignore unrelated changes only after impact is understood.

## Decisions, evidence and authority

- Previously answered questions and their sources:
- Assumptions and decision-relevant risks:
- Required unresolved decisions / owner:
- Evidence: scenario, artifact revision, environment, observed result and limitation:
- Actual user authorization reference, exact content/scope and affected paths:
- Skill preselection: identities, approved sources/revisions and allowed planning outcomes:
- Installation/update authorization: separate exact action/scope, or absent:
- Host Plan state, read-only enforcement and current write permissions:
- No authority may be inferred from a model-authored approval field or from this template.

## Completion and feedback

- Current release's complete user promise and end-to-end acceptance:
- Required corrections (criterion + owning contract + impact):
- Optional improvements, outside the current scope:
- Review budget / rounds consumed / stop condition:
- Changed prerequisites and affected consumers or evidence:
- Completion: planned | specified | implemented | verified in named environment | actually available to named users
- Next handoff, or explicit stop at done:
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall