$npx -y skills add SeanJ1ang/design-judge-skills --skill design-submission-checkAudit a design-award submission package against the current official rules for a specific award cycle. Check required materials and technical constraints, cross-material facts and claims, rights and disclosure risks, and final submission readiness. Use when a user asks for a pre-
| 1 | # Design Submission Check |
| 2 | |
| 3 | ## Purpose |
| 4 | |
| 5 | Determine whether a concrete design-award submission package is complete, internally consistent, and ready to submit under the current official rules for one exact award, track, category, and cycle. |
| 6 | |
| 7 | Return one of three decisions: |
| 8 | |
| 9 | - `Ready`: no Blocker or Important findings remain. |
| 10 | - `Conditionally ready`: no Blocker remains, but one or more Important findings require attention. |
| 11 | - `Not ready`: at least one Blocker remains. |
| 12 | |
| 13 | ## Scope Boundary |
| 14 | |
| 15 | - Convert current official submission rules into a project-specific checklist. |
| 16 | - Check required files, fields, declarations, and technical constraints. |
| 17 | - Compare names, facts, claims, credits, metrics, and versions across materials. |
| 18 | - Screen rights, permissions, confidentiality, personal-data, and disclosure risks. |
| 19 | - Perform a final package-level audit and prioritize fixes. |
| 20 | - Stop after the audit. Do not select the award, score design quality, redesign the project, or perform comprehensive copy-editing. |
| 21 | |
| 22 | Use `$design-award-match` before this skill when the award, track, or category has not been selected. Route design-quality questions to `design-evaluation` and substantive redesign or rewriting to `design-optimization` when those skills are available. |
| 23 | |
| 24 | ## Severity Model |
| 25 | |
| 26 | Read [references/checking-framework.md](references/checking-framework.md). Classify every finding: |
| 27 | |
| 28 | - `Blocker`: likely prevents submission, violates an explicit hard rule, invalidates eligibility, or leaves a mandatory item absent. |
| 29 | - `Important`: materially weakens clarity, credibility, consistency, or rights readiness but is not a confirmed hard-rule failure. |
| 30 | - `Optimization`: optional improvement that does not affect basic submission readiness. |
| 31 | |
| 32 | Never hide an unresolved rule or unreadable file inside an overall percentage. The highest unresolved severity controls the final decision. |
| 33 | |
| 34 | ## User Interaction Contract |
| 35 | |
| 36 | Accept: |
| 37 | |
| 38 | - the exact award, track, category, and submission cycle; |
| 39 | - official rule page, entry guide, or terms when supplied; |
| 40 | - the submission files or a manifest describing them; |
| 41 | - applicant, team, project, release, authorship, and rights facts relevant to the entry. |
| 42 | |
| 43 | If the award, track/category, or cycle is missing, ask one concise question containing only the missing identifiers. If materials are incomplete, audit what is available and list everything that could not be checked; do not invent a pass. |
| 44 | |
| 45 | Offer this template when the user asks how to use the skill: |
| 46 | |
| 47 | ```text |
| 48 | Award / cycle: {exact award and year} |
| 49 | Track / category: {exact official names} |
| 50 | Official rules: {URL or attached guide, optional} |
| 51 | Applicant / team: {names, roles, organization, country or student status} |
| 52 | Submission materials: {attach files or provide paths} |
| 53 | Known third-party content: {images, fonts, music, data, trademarks, AI-generated content} |
| 54 | Requested mode: {full audit / technical check / consistency check / final check} |
| 55 | ``` |
| 56 | |
| 57 | ## Audit Workflow |
| 58 | |
| 59 | ### 1. Lock the submission target |
| 60 | |
| 61 | Record the exact award program, cycle, track, category, applicant type, submission stage, deadline, and official timezone. Do not combine requirements from different cycles, categories, or judging stages. |
| 62 | |
| 63 | If the selected target appears inconsistent with the package, report it and refer category selection back to `$design-award-match`; do not silently change the target. |
| 64 | |
| 65 | ### 2. Verify and extract current rules |
| 66 | |
| 67 | Read [references/rule-evidence-policy.md](references/rule-evidence-policy.md). At request time, verify current official sources and create a requirement ledger containing: |
| 68 | |
| 69 | - mandatory and optional materials; |
| 70 | - form fields and declarations; |
| 71 | - accepted file types, counts, sizes, dimensions, aspect ratios, duration, word or character limits, and languages; |
| 72 | - filename, anonymity, branding, caption, and credit rules; |
| 73 | - applicant, authorship, release-window, prototype, and publication restrictions relevant to final submission; |
| 74 | - rights, consent, AI-use, confidentiality, and disclosure requirements; |
| 75 | - deadline with an absolute date and official timezone. |
| 76 | |
| 77 | Attach an official URL and `checked on` date to each rule group. Search snippets and third-party summaries are discovery evidence only. When official sources conflict, the most specific current official terms control; report unresolved conflicts as Blockers. |
| 78 | |
| 79 | ### 3. Inventory the package |
| 80 | |
| 81 | List every supplied file and form field. Assign each item to exactly one requirement ID an |