Engineering validation

Engineering Validation

Use this skill before saying a paper edit is complete, fixed, or ready.

Core Stance

• No verification, no completion claim.
• A dry read is not a build check.
• Report exactly what was run and what was not run.
• Treat evidence anchors, citations, figures, tables, and PDF output as part of manuscript correctness.
• For existing paper repos, read the current live draft and project-specific instructions before validating.
• This is readiness validation, not truth certification. Never certify experiment truth, citation truth, or venue compliance without the relevant source files, tools, and checks.

Boundaries

• Use this skill for readiness checks, not for drafting new manuscript prose.
• Use engineering-writing when the user needs new section structure or claim-evidence planning before validation.
• Use engineering-polishing for prose-only improvements.
• Use engineering-figure-table for visual design before final consistency checks.
• Use engineering-response for reviewer/advisor reply drafting before final response package validation.

Status Vocabulary

• PASS: checked directly and no issue found.
• FAIL: checked directly and an issue was found.
• PARTIAL: checked only in part; name the unchecked part.
• NOT_RUN: check was relevant but not run.
• UNKNOWN: cannot determine from provided material.

Overall readiness can only be READY, NOT_READY, or CANNOT_DETERMINE.

READY is allowed only when every required check for the user's stated goal is PASS. If any required check is FAIL, PARTIAL, NOT_RUN, or UNKNOWN, overall readiness must be NOT_READY or CANNOT_DETERMINE.

When to Open Extra Files

File	Open when
references/live-draft-check.md	Confirming source draft, input order, title, author/blind state, or final sync
references/latex-build.md	Compiling LaTeX, checking bibitem count, page count, warnings, or diff checks
references/evidence-audit.md	Checking contributions, claims, section anchors, citations, and overclaims
references/final-readonly-check.md	Running the final 30-minute style read-only inspection
references/error-archive.md	Diagnosing common manuscript failure symptoms and the first section to inspect
references/submission-checklist.md	Final read-only inspection before submission
references/venue-checklist.md	Venue family changes limits, reproducibility, checklist, or AI-disclosure requirements
references/citation-metadata-check.md	Citation existence, DOI, venue, year, or BibTeX consistency needs verification
references/ai-disclosure-check.md	AI-assisted writing, citation, or figure generation may require author verification or disclosure
references/examples.md	Needing concrete validation report examples
references/failure-modes.md	Handling requests to certify readiness without running checks
../_shared/story-spine.md	Checking whether Abstract/Conclusion claims match Methods/Experiments evidence
../_shared/evidence-boundary.md	Validation touches claims, citations, results, or completion status
../_shared/citation-boundary.md	Citation existence, citation placement, or reference claims are part of the check
../_shared/citation-verification-workflow.md	Externally discovered references need existence, metadata, or claim-support verification before readiness
../_shared/claim-strength.md	High-risk claim verbs need audit during validation
../_shared/ai-assisted-writing-policy.md	Venue disclosure or author-verification status is part of readiness
../_shared/output-mode.md	The user asks for a short validation result only

Workflow

1. State the validation goal being interpreted from the user request.
2. Identify manuscript root and live draft.
3. Read local instructions and relevant build files.
4. Check structure anchors: thesis, contribution list, main results, ablation, limitations.
5. Check story spine: Abstract and Conclusion claims must have Methods, Experiments, figure/table, and boundary anchors.
6. Check figures, tables, captions, labels, and category/metric names.
7. Run the smallest relevant build and consistency commands.
8. If tools or files are unavailable, mark command-dependent checks NOT_RUN and perform only the file-based or local-text audit that evidence allows.
9. For venue readiness, report whether official policy was checked, including source URL and source date. If not checked, venue compliance is NOT_RUN or PARTIAL. Static venue profiles count only as STATIC_SUMMARY_NOT_LIVE_CHECK, not as official policy verification.
10. Report evidence, failures, and unverified items.

Default Output

Validation result
- Goal interpreted as:
- Build: PASS / FAIL / NOT_RUN / UNKNOWN
- References: PASS / FAIL / PARTIAL / NOT_RUN / UNKNOWN
- Figures/tables: PASS / FAIL / PARTIAL / NOT_RUN / UNKNOWN
- Claim-evidence audit: PASS / FAIL / PARTIAL / NOT_RUN / UNKNOWN
- Story-spine audit: PASS / FAIL / PARTIAL / NOT_RUN / UNKNOWN
- AI/disclosure check: PASS / FAIL / PARTIAL / NOT_RUN / UNKNOWN
- Venue readiness: PASS / FAIL / PARTIAL / NOT_RUN / UNKNOWN
- Private/stale wording scan: PASS / FAIL / NOT_RUN / UNKNOWN
- Overall readiness: READY / NOT_READY / CANNOT_DETERMINE

Evidence
- Commands run:
- Files inspected:
- Outputs observed:
- Failures:
- Not verified:
- Official policy checked:
- Official policy source/date:
- Official page opened this run:
- Policy excerpt checked:
- Profile-only status:

Blocking issues
- ...

Next actions
- ...