The structured data, exactly as delivered
{
"oqsVersion": "1.2.0",
"profile": "written",
"deterministic": [
{
"id": "BUDGET_SUM_MISMATCH",
"hard": true,
"passed": true,
"detail": "Not a budget.",
"evidence": []
},
{
"id": "CONTRAST_LOW",
"hard": false,
"passed": true,
"detail": "A launch_thread has no text surface; contrast does not apply.",
"evidence": []
},
{
"id": "DATE_INVALID",
"hard": true,
"passed": true,
"detail": "Not a plan; no date to check.",
"evidence": []
},
{
"id": "DIM_ASPECT_MISMATCH",
"hard": true,
"passed": true,
"detail": "Not an image.",
"evidence": []
},
{
"id": "FILE_TOO_LARGE",
"hard": false,
"passed": true,
"detail": "Not an image.",
"evidence": []
},
{
"id": "LINK_DEAD",
"hard": false,
"passed": true,
"detail": "No links asserted.",
"evidence": []
},
{
"id": "PALETTE_DRIFT",
"hard": false,
"passed": true,
"detail": "Not an image.",
"evidence": []
},
{
"id": "PLACEHOLDER_TEXT",
"hard": true,
"passed": true,
"detail": "No placeholder text survives in the finished copy.",
"evidence": []
},
{
"id": "POLICY_VIOLATION",
"hard": true,
"passed": true,
"detail": "Final copy is clean.",
"evidence": []
},
{
"id": "SCHEDULE_CONSTRAINT",
"hard": true,
"passed": true,
"detail": "Not a schedule.",
"evidence": []
},
{
"id": "SCHEDULE_OVERLAP",
"hard": true,
"passed": true,
"detail": "Not a schedule.",
"evidence": []
},
{
"id": "SCHEMA_INVALID",
"hard": true,
"passed": true,
"detail": "Artifact and payload satisfy their schemas.",
"evidence": []
},
{
"id": "SOURCE_MISSING",
"hard": true,
"passed": true,
"detail": "Not a plan; no grounded claims.",
"evidence": []
},
{
"id": "TEXT_OVERFLOW_RISK",
"hard": false,
"passed": true,
"detail": "965/2400 characters — fits.",
"evidence": []
}
],
"axes": {
"voice": 78,
"specificity": 55,
"factual_support": 42,
"structure": 72,
"platform_fit": 70
},
"issues": [
"Post 3 contains 'up to 80%' and 'game changer' and 'best tooling decision they made all year' — the first is an overclaim relative to the brief's instruction that claims be traceable to beta data, and the latter two are hype adjectives/boilerplate the brief explicitly forbids.",
"Post 3's 'finally got their systems under control' is vague filler that passes the substitution test unchanged into any SaaS launch copy.",
"Post 5 fails the brief's explicit requirement: pricing ($9/mo) must be stated plainly in the CTA post. It is absent entirely.",
"Post 5's 'let us know what you think' is generic boilerplate; the brief requires a concrete call to action.",
"Post 3 drops the dry practitioner-to-practitioner register the brief mandates — 'game changer for design ops at scale' is marketing register, not peer register."
],
"pass": false,
"failedOn": "both",
"repairs": 0,
"notes": [
"Critique by claude-sonnet-4-6, written profile."
],
"coverageGaps": [],
"repairBrief": "Post 3: Strip all three flagged claims. Replace with grounded beta data — state the cohort (14 teams, 6 weeks) and use a specific, honest metric (e.g. median reduction in design-review cycles, or a concrete number of token drift incidents caught). Remove 'game changer for design ops at scale' entirely — it violates the no-hype-adjectives rule and the register. If the testimonial quote is real and attributable, reframe it as a direct quote with context ('One design-system lead at a 40-person team told us…'); if it cannot be sourced, cut it. Post 5: Add the price plainly — '$9/month' — before or immediately after the URL. Replace 'let us know what you think' with a specific action: e.g. 'Download the beta build, point it at a live file, and reply here with what it catches.' The CTA must be concrete and must state pricing per the brief."
}