The Assay Standard

The grading rubric, rendered from the same code that grades.

This page mirrors assayed.xyz/standard. Both are generated from packages/tribunal/src/standard.ts — the module the grader runs (guardrail: published = shipped).

The Assay Standard — AS-1.1.0

The standard does not bend for our own marketing.

An artifact passes only when every hard check passes, the craft weighted mean is ≥ 72, and no craft axis is below 60. Failing drafts are repaired at most 2 times, and every draft's report ships in the dossier.

Hard checks (deterministic — any failure blocks or triggers repair)

  • Claim coverage (CLAIM_COVERAGE) — Every rendered sentence resolves to a confirmed claim backed by existing evidence, and every number appears in that evidence. Unsupported prose cannot ship.
  • Evidence resolves (EVIDENCE_RESOLVES) — Every referenced evidence item exists, and file-backed evidence has readable content. A dangling or unreadable source is a hard failure.
  • Link liveness (LINK_LIVENESS) — Every URL in the artifact is fetch-checked and must resolve live. A dead or unsafe link never passes.
  • No placeholders (PLACEHOLDER_TEXT) — No [BRACKETS], "YOUR X HERE", TBD, lorem, or XXX placeholder text survives into any artifact.
  • Date sanity (DATE_SANITY) — No future dates, each end is on/after its start, tenure math is correct, and overlaps are flagged — all evaluated in the candidate's timezone.
  • Cross-artifact consistency (XARTIFACT_CONSISTENCY) — Every number tied to a claim renders identically wherever that claim appears across the resume, letter, and stories.
  • Format law (FORMAT_LAW) — The ATS variant is single-column with no tables/images/text-boxes, uses only approved section headings, and stays within 2 pages; the designed variant meets a 4.5:1 body-text contrast ratio.
  • DOCX integrity (DOCX_INTEGRITY) — The generated .docx reopens in a parser and contains the same section headings as the ATS resume.
  • ATS parse-back (ATS_PARSE_BACK) — The ATS PDF is re-parsed by Assay's deterministic parser and diffed field-by-field against the source profile; 100% of required fields must survive. Verified against Assay's deterministic parser and ATS format law — not a simulation of any specific vendor.
  • Contact validity (CONTACT_VALIDITY) — The contact email is well-formed and every contact link is a syntactically valid URL.
  • PII hygiene (PII_HYGIENE) — A share-view artifact exposes only the fields the candidate approved; unapproved personal data must be redacted.
  • JD keyword coverage (informational) (JD_COVERAGE) — We report weighted must/nice keyword coverage against the job description. We report coverage; we do not stuff keywords. This check never fails.
  • Interview answer integrity (INTERVIEW_INTEGRITY) — A finalized interview answer must be STAR-complete and every factual number must agree with the confirmed ledger; contradictions block the answer.
  • STAR completeness (STAR_COMPLETENESS) — Story-bank entries must make situation, task, action, and result legible; a result without the path to it is not a complete interview story.
  • Rendered portfolio contrast (PORTFOLIO_CONTRAST) — Portfolio pages are screenshot-sampled in Chromium; rendered body text must measure at least 4.5:1 against its actual background.

Per-artifact profiles

Artifact kindDeterministic checks routed to it
resume_atsCLAIM_COVERAGE, EVIDENCE_RESOLVES, LINK_LIVENESS, PLACEHOLDER_TEXT, DATE_SANITY, XARTIFACT_CONSISTENCY, FORMAT_LAW, ATS_PARSE_BACK, CONTACT_VALIDITY, PII_HYGIENE, JD_COVERAGE
resume_designedCLAIM_COVERAGE, EVIDENCE_RESOLVES, LINK_LIVENESS, PLACEHOLDER_TEXT, DATE_SANITY, XARTIFACT_CONSISTENCY, FORMAT_LAW, CONTACT_VALIDITY, PII_HYGIENE, JD_COVERAGE
resume_docxCLAIM_COVERAGE, EVIDENCE_RESOLVES, LINK_LIVENESS, PLACEHOLDER_TEXT, DATE_SANITY, XARTIFACT_CONSISTENCY, DOCX_INTEGRITY, CONTACT_VALIDITY, PII_HYGIENE, JD_COVERAGE
cover_letterCLAIM_COVERAGE, EVIDENCE_RESOLVES, LINK_LIVENESS, PLACEHOLDER_TEXT, DATE_SANITY, XARTIFACT_CONSISTENCY, CONTACT_VALIDITY, PII_HYGIENE, JD_COVERAGE
story_bankCLAIM_COVERAGE, EVIDENCE_RESOLVES, LINK_LIVENESS, PLACEHOLDER_TEXT, DATE_SANITY, XARTIFACT_CONSISTENCY, CONTACT_VALIDITY, PII_HYGIENE, JD_COVERAGE, STAR_COMPLETENESS
fit_mapCLAIM_COVERAGE, EVIDENCE_RESOLVES, LINK_LIVENESS, PLACEHOLDER_TEXT, DATE_SANITY, XARTIFACT_CONSISTENCY, CONTACT_VALIDITY, PII_HYGIENE, JD_COVERAGE
gap_briefCLAIM_COVERAGE, EVIDENCE_RESOLVES, LINK_LIVENESS, PLACEHOLDER_TEXT, DATE_SANITY, XARTIFACT_CONSISTENCY, CONTACT_VALIDITY, PII_HYGIENE, JD_COVERAGE
portfolio_pageCLAIM_COVERAGE, EVIDENCE_RESOLVES, LINK_LIVENESS, PLACEHOLDER_TEXT, DATE_SANITY, XARTIFACT_CONSISTENCY, CONTACT_VALIDITY, PII_HYGIENE, JD_COVERAGE, PORTFOLIO_CONTRAST
manifest_jsonCLAIM_COVERAGE, EVIDENCE_RESOLVES, LINK_LIVENESS, PLACEHOLDER_TEXT, DATE_SANITY, XARTIFACT_CONSISTENCY, CONTACT_VALIDITY, PII_HYGIENE, JD_COVERAGE
interview_evaluationCLAIM_COVERAGE, EVIDENCE_RESOLVES, LINK_LIVENESS, PLACEHOLDER_TEXT, DATE_SANITY, XARTIFACT_CONSISTENCY, CONTACT_VALIDITY, PII_HYGIENE, JD_COVERAGE, INTERVIEW_INTEGRITY
promotion_narrativeCLAIM_COVERAGE, EVIDENCE_RESOLVES, LINK_LIVENESS, PLACEHOLDER_TEXT, DATE_SANITY, XARTIFACT_CONSISTENCY, CONTACT_VALIDITY, PII_HYGIENE, JD_COVERAGE
promotion_memoCLAIM_COVERAGE, EVIDENCE_RESOLVES, LINK_LIVENESS, PLACEHOLDER_TEXT, DATE_SANITY, XARTIFACT_CONSISTENCY, CONTACT_VALIDITY, PII_HYGIENE, JD_COVERAGE
manager_one_pagerCLAIM_COVERAGE, EVIDENCE_RESOLVES, LINK_LIVENESS, PLACEHOLDER_TEXT, DATE_SANITY, XARTIFACT_CONSISTENCY, CONTACT_VALIDITY, PII_HYGIENE, JD_COVERAGE
capability_statementCLAIM_COVERAGE, EVIDENCE_RESOLVES, LINK_LIVENESS, PLACEHOLDER_TEXT, DATE_SANITY, XARTIFACT_CONSISTENCY, CONTACT_VALIDITY, PII_HYGIENE, JD_COVERAGE
case_studiesCLAIM_COVERAGE, EVIDENCE_RESOLVES, LINK_LIVENESS, PLACEHOLDER_TEXT, DATE_SANITY, XARTIFACT_CONSISTENCY, CONTACT_VALIDITY, PII_HYGIENE, JD_COVERAGE
proposal_letterCLAIM_COVERAGE, EVIDENCE_RESOLVES, LINK_LIVENESS, PLACEHOLDER_TEXT, DATE_SANITY, XARTIFACT_CONSISTENCY, CONTACT_VALIDITY, PII_HYGIENE, JD_COVERAGE

Craft axes (Claude critic, scored 0–100)

AxisWeightWhat it grades
Voice1Confident, human, and specific — not generic AI prose.
Specificity1.5Concrete actions, tools, and outcomes rather than vague responsibilities.
Quantification1.5Impact is measured where evidence supports it — never invented.
Positioning1The strongest, most relevant evidence leads.
Tailoring1.5The artifact answers this specific brief, not a generic role.
Evidence honesty2Every claim is framed at the strength its evidence earns — no overreach.