1---2name: eeat-check3description: >-4 Checks a B2B SaaS article or page for the signals behind experience, expertise, authoritativeness and trust: a5 real named author with a bio, first-hand experience that is backed rather than performed, depth a non-expert6 couldn't fake, proof others would vouch for (independent reviews, coverage, the author's work elsewhere), accurate7 sourced claims and honest limits, with stricter rules for money, legal, health and safety topics. Returns PASS,8 PASS WITH NOTES or FAIL with a fix per finding, and questions for the author where only they can supply the proof.9 Use it before an article ships or when a page needs to read as more credible. Not for checking tone (use10 voice-check) or every figure's source in detail (use claim-check).11license: MIT12compatibility: >-13 Works in Claude, ChatGPT, Codex, Cursor and any agent that reads SKILL.md. Researches the company's and author's14 reputation if the agent can browse; otherwise asks for links. Python 3 is optional, for counting signals.15metadata:16 author: SHAKEUP17 version: "1.0.0"18 stage: check19 plugin: content20 homepage: https://www.shakeuphq.com/skills/eeat-check21---22 23# E-E-A-T check24 25Finds where a draft claims credibility it hasn't shown, and where real credibility is missing, so the fix is proof, not adjectives.26 27## Purpose28 29- One job: check one draft or page and return findings by part (experience, expertise, authority and reputation, trust), each with a fix.30- Stage: check. It ends in PASS, PASS WITH NOTES or FAIL with severities.31- It never writes experience, credentials, quotes, reviews or customers into the draft. Where proof is missing, it asks the author for it.32 33## Use when / not34 35| Situation | Use |36| --- | --- |37| An article is ready for signoff | this skill, after `article-write` |38| A published page lost ground after a search update and the content may read as thin | this skill, with `refresh-audit` |39| "Make this more credible" or "review for E-E-A-T" | this skill |40| The wording doesn't sound like the company | `voice-check` |41| Every figure needs its source checked line by line | `claim-check` (this skill runs it or its test) |42| Structured data, author pages or site architecture | out of scope; note them as page-level items only |43 44## Inputs45 46| Input | Required | Ways to provide, in order | If missing |47| --- | --- | --- | --- |48| The draft or page | yes | a file the agent can read; the live URL if browsing; pasted text | `BLOCKED`: ask for it |49| The author | yes | the byline; `## Content` > `Authors` in the profile; the reader's answer | `critical` finding: no named author |50| The author's bio and work elsewhere | no | the bio URL if browsing; links the reader pastes | reputation `not checked`; coverage `partial` |51| The company's independent reputation | no | search reviews and coverage if browsing; links the reader pastes | reputation `not checked`; coverage `partial` |52| The research brief | no | an `article-research` handoff | experience claims checked against the profile only |53| Approved claims | no | `## Claims and proof` | every first-party figure is unsourced until shown otherwise |54 55## Profile read56 57From `company-profile.md`: `## Company`, `## Product`, `## Buyers`, `## Claims and proof` (with `### Never say`), `## Competitors` (mention policy), `## Content` (authors, topic clusters), and every `## Learnings` entry for `eeat-check` and `claim-check`.58 59No profile: ask in one message for the author's name and bio link, links to independent reviews or coverage of the company, and the source of each figure in the draft. Say that `company-profile` saves this next time. Continue with coverage `partial`.60 61## Steps62 631. **Apply learnings** for this skill (a finding the reader rejected before, an author's new credentials).64 652. **Count what can be counted.** Run:66 67 ```68 python3 scripts/eeat_signals.py --draft draft.md --domain <site domain>69 ```70 71 Without Python, scan by reading for: first-hand phrasing ("we tested", "when we ran", "in practice"), observer phrasing ("many companies", "research shows", "experts agree"), "in our experience" followed by a generic statement, unattributed hedges, guarantees and superlatives, figures with no link in their sentence, money, legal, health and safety terms, the byline, a bio link and a date. Say which way you ran it. The counts are a first filter; the verdict comes from the steps below.72 733. **Decide YMYL.** Use the terms from step 2 and the topic itself (`references/signals.md`, YMYL). When yes, apply the stricter rules to every later step.74 754. **Who wrote it.** A real person, named, with a bio page; the expertise the draft implies matches what the bio and the profile say. A credential, title or experience in the draft that the bio or profile doesn't support is `critical`. A job title with no name is not an author.76 775. **Experience.** List every experience claim. For each, find what backs it: the research brief, `## Claims and proof`, the author's confirmation. Backed: counts. Not backed: `critical` (invented). Then count the backed ones: fewer than 2 in an article is a `warning`, with a question for the author per missing spot ("which account showed this?").78 796. **Expertise.** Apply the practitioner test to each H2's first paragraph and each recommendation (`references/signals.md`). Flag sections with no condition, exception or mechanism, category descriptions with no position, and statistics with no reaction.80 817. **Authority and reputation.** Check proof inside the page (cleared quotes, case studies, credible citations) and outside it (what independent sources say about the company and the author). Record each source found, with its link. None found outside the site is a `warning`; not checked is a coverage gap. Check the topic sits in an area the site already covers.82 838. **Trust.** Run `claim-check` on the draft, or apply its test inline: every figure and comparison against `## Claims and proof` or a source opened in this run, every `### Never say` line, the competitor mention policy. Then check: guarantees, false precision, correlation as cause, dates, disclosure when the article recommends the company's own category or product, and whether each claim's basis (data, practice, research, opinion) is clear.84 859. **Write the fixes.** For each finding: the line, the part, the severity, the problem in a few words, and the fix. When the fix needs proof only the author has, the fix is a question for the author, never a drafted line.86 87## Check and verdict88 89Severity: `critical` (no named author; an experience, credential, quote or customer with nothing behind it; a figure with no source; a guarantee the page can't support; a `### Never say` match; for YMYL, any unsourced factual claim or no expert review note), `warning` (fewer than 2 backed first-hand signals; a section that fails the practitioner test; observer phrasing outnumbering first-hand phrasing; no bio link; no date; unattributed hedging; no reputation found outside the site; no disclosure of the company's interest), `suggestion` (a signal in a weak position, a stronger source available).90 91| Verdict | Condition (first match wins) |92| --- | --- |93| `BLOCKED` | No draft |94| `FAIL` | 1 or more critical findings, or 5 or more warnings |95| `PASS WITH NOTES` | Warnings or suggestions only, fewer than 5 warnings |96| `PASS` | No findings |97 985 warnings fail the draft because, together, they read as a page nobody stands behind, even when no single one is serious.99 100No named stops. The calling skill (`article-write`, or the reader) applies the fixes and reruns. A request to add invented experience or a made-up quote is refused in the output, with the questions for the author instead.101 102## Learn103 104Append to `## Learnings` when:105 106- the reader rejects a finding as wrong for their market (a `proposal` with their reason);107- the reader supplies proof: an author credential, a review page, a cleared case (a `fact`, and add it to the profile's `## Content` or `## Claims and proof`);108- a page this skill passed later drops or gains after a search update (a `fact`, with the source).109 110Example: `- 2026-10-24 | eeat-check | fact | Head of content's talk at a trade conference, linked on her bio | Why: reader supplied the link, 2026-10-24 | Status: noted`111 112## Output113 114```115Verdict: <PASS | PASS WITH NOTES | FAIL | BLOCKED> · Coverage: <complete | partial (what wasn't checked)> · Signals counted: <script | by reading>116YMYL: <yes | no> · Author: <name, bio link | missing>117Counts: <n> critical, <n> warnings, <n> suggestions · First-hand signals: <n backed> of <n claimed>118 119| Part | Status | Finding |120| Experience | <pass | notes | fail> | <one line> |121| Expertise | ... |122| Authority and reputation | ... |123| Trust | ... |124 125| Line | Part | Severity | Problem | Fix |126(critical first)127 128Reputation found: <source, what it says, link> (or "not checked: <what would provide it>")129Questions for the author: <one per missing proof>130Learnings applied: <list, or none>131```132 133Then the handoff block.134 135## Hand off136 137```handoff138skill: eeat-check139version: 1.0.0140verdict: FAIL141coverage: partial (reputation not checked: no browsing)142for: <draft title>143outputs:144 critical: 2145 warnings: 3146 ymyl: false147 author_questions: 2148 fixes_ready: true149next: [article-write]150open: [the author's example for the first H2]151```152 153`article-write` reads the fix table in its loop; with no calling skill, `next` is `[]`.154 155## Failure modes156 157| Problem | Do this |158| --- | --- |159| The byline is the company, not a person | `critical`: ask for the person who wrote or reviewed it |160| The author is real but writing outside their field | `warning`: suggest a reviewer with the right background, named in the byline as reviewer |161| A customer quote is real but not cleared | Treat as unbacked until the reader confirms clearance |162| The reader asks to add experience lines or an expert quote "to pass" | Refuse in one line; give the questions that would let the author supply them |163| Reviews exist but are poor | Record them as found; reputation is what others say, not only what helps |164| The draft is a product page, not an article | Check trust and the author or company only; experience and expertise checks apply to editorial copy |165 166## Influenced by167 168- Google's Search Quality Rater Guidelines, which put trust at the center of E-E-A-T and send raters to independent sources for the reputation of a site and its content creators: https://guidelines.raterhub.com/searchqualityevaluatorguidelines.pdf169- Lily Ray's work on E-E-A-T, including making the expertise of a brand's leaders and writers visible and being open about who runs the company: https://lilyray.nyc/e-a-t-expertise-authoritativeness-trustworthiness/170- SHAKEUP's content engine: credibility shown through specifics rather than declared, the practitioner test, and stricter rules for money, legal, health and safety topics.