Submission Pack Builder
Prepare evidence for the exact validated artifact. Do not use submission copy to hide unresolved package, brand, listing, or product problems.
Preconditions
Require:
- exact Plugin version/ref
- successful repository-native tests
- successful Autopilot package preflight
- deterministic package result when promised
- reviewed public Skill set and exclusions
- architecture decision:
skills-only, MCP-backed, or hybrid
- reviewed Plugin experience brief
- product-specific SVG brand pack with light and dark variants plus the declared small icon/composer asset
- successful directory listing pack with no blocking missing fields
- verified developer/business identity still confirmed in the OpenAI submission surface rather than inferred from repository metadata
If the host also provides a dedicated Skill Submission Pack Writer, use it for current portal-facing prose and field formatting after these evidence requirements are satisfied. This Skill remains the evidence contract and status gate.
Build the pack
- Re-check the current official OpenAI submission requirements.
- Record the artifact SHA256 and source commit/ref.
- Summarize the Plugin's user-facing job in plain language tied to actual packaged capabilities.
- List each public Skill and any required/optional app dependency.
- Record public exclusions from the source repository and why they were excluded.
- Include the exact directory listing fields and brand asset paths used for the artifact. Do not substitute a draft listing from another ref or version.
- Include discovery evidence from direct, indirect, and negative golden prompts when available. Record routing misses or ambiguous metadata instead of hiding them.
- Build reviewer test cases from real Plugin behavior. Positive cases should cover intended workflows; negative cases should show boundaries, refusal, clarification, fallback, or non-trigger behavior where relevant.
- At the repository's 2026-08-22 OpenAI baseline, require at least five positive and three negative reviewer cases. Re-check the live official requirement before every public submission.
- For MCP-backed/hybrid Plugins, document server/auth model, read/write behavior, sensitive actions, reviewer access requirements, tool annotations, and current production evidence required by the official submission flow.
- Verify listing fields, branding, URLs, privacy/terms/support claims, category, package name, version, and capabilities against the exact artifact.
- Record unresolved warnings instead of converting them into confident public claims.
- Emit one status only:
submission_ready or not_ready, with blockers.
Status discipline
Never use these as synonyms:
brand_ready
listing_ready
locally_validated
submission_ready
submitted
approved
published
A reviewer packet proves preparation, not acceptance by OpenAI.
Evidence output
The pack should contain or reference:
- source ref and artifact hash
- architecture
- public Skill/app inventory
- public exclusions
- brand rationale and exact light/dark/icon asset paths
- exact listing fields and field-limit checks
- developer identity verification status
- golden prompt set and discovery observations
- reviewer test cases
- privacy/terms/support URLs where applicable
- MCP review material where applicable
- validation and deterministic-package evidence
- residual warnings
- exact submission state
Use ../chatgpt-codex-plugin-autopilot/references/submission-checklist.md, ../chatgpt-codex-plugin-autopilot/references/branding-and-listing.md, and current official OpenAI documentation as the authority chain.
1---2name: submission-pack-builder3description: Use when an exact ChatGPT/Codex Plugin artifact has passed local package, brand, and listing gates and you need reviewer-ready submission evidence without confusing preparation, submission, approval, and publication states.4---56# Submission Pack Builder78Prepare evidence for the exact validated artifact. Do not use submission copy to hide unresolved package, brand, listing, or product problems.910## Preconditions1112Require:1314- exact Plugin version/ref15- successful repository-native tests16- successful Autopilot package preflight17- deterministic package result when promised18- reviewed public Skill set and exclusions19- architecture decision: `skills-only`, `MCP-backed`, or `hybrid`20- reviewed Plugin experience brief21- product-specific SVG brand pack with light and dark variants plus the declared small icon/composer asset22- successful directory listing pack with no blocking missing fields23- verified developer/business identity still confirmed in the OpenAI submission surface rather than inferred from repository metadata2425If the host also provides a dedicated Skill Submission Pack Writer, use it for current portal-facing prose and field formatting after these evidence requirements are satisfied. This Skill remains the evidence contract and status gate.2627## Build the pack28291. Re-check the current official OpenAI submission requirements.302. Record the artifact SHA256 and source commit/ref.313. Summarize the Plugin's user-facing job in plain language tied to actual packaged capabilities.324. List each public Skill and any required/optional app dependency.335. Record public exclusions from the source repository and why they were excluded.346. Include the exact directory listing fields and brand asset paths used for the artifact. Do not substitute a draft listing from another ref or version.357. Include discovery evidence from direct, indirect, and negative golden prompts when available. Record routing misses or ambiguous metadata instead of hiding them.368. Build reviewer test cases from real Plugin behavior. Positive cases should cover intended workflows; negative cases should show boundaries, refusal, clarification, fallback, or non-trigger behavior where relevant.379. At the repository's 2026-08-22 OpenAI baseline, require at least five positive and three negative reviewer cases. Re-check the live official requirement before every public submission.3810. For MCP-backed/hybrid Plugins, document server/auth model, read/write behavior, sensitive actions, reviewer access requirements, tool annotations, and current production evidence required by the official submission flow.3911. Verify listing fields, branding, URLs, privacy/terms/support claims, category, package name, version, and capabilities against the exact artifact.4012. Record unresolved warnings instead of converting them into confident public claims.4113. Emit one status only: `submission_ready` or `not_ready`, with blockers.4243## Status discipline4445Never use these as synonyms:4647- `brand_ready`48- `listing_ready`49- `locally_validated`50- `submission_ready`51- `submitted`52- `approved`53- `published`5455A reviewer packet proves preparation, not acceptance by OpenAI.5657## Evidence output5859The pack should contain or reference:6061- source ref and artifact hash62- architecture63- public Skill/app inventory64- public exclusions65- brand rationale and exact light/dark/icon asset paths66- exact listing fields and field-limit checks67- developer identity verification status68- golden prompt set and discovery observations69- reviewer test cases70- privacy/terms/support URLs where applicable71- MCP review material where applicable72- validation and deterministic-package evidence73- residual warnings74- exact submission state7576Use `../chatgpt-codex-plugin-autopilot/references/submission-checklist.md`, `../chatgpt-codex-plugin-autopilot/references/branding-and-listing.md`, and current official OpenAI documentation as the authority chain.