← ClaudeAtlas

cv-evidence-baselisted

Interrogates a CV or resume to recover the evidence that never made it onto the page, and works out which roles the person is genuinely credible for. Grades their background against role archetypes derived from what they actually did rather than from their job titles - including archetypes they are NOT credible for - asks the oblique questions that dislodge buried achievements, names where the page would get binned in a seven-second scan, and maintains an evidence base plus an action ledger across sessions. Use this whenever the user has NO target role in mind and is asking an open question about themselves: what roles they could realistically go for, whether they are pitching themselves right, whether they are pigeonholed, why they get no callbacks or interviews, what they are missing, or what their CV says about them. Use it when they hand over a CV with no clear instruction - "does this look OK", "be honest with me", "am I positioned right". ALSO use for a career change, a step up, going freelance or contr
kevin-burns/claude-skills · ★ 7 · Code & Development · score 78
Install: claude install-skill kevin-burns/claude-skills
# CV evidence base ## What this is for Most CVs are not weak because the wording is bad. They are weak because the person's best evidence never made it onto the page. They omit the things they found easy, because they assume everyone finds them easy. They describe responsibilities they held rather than outcomes they caused. They file their whole career under a job title the market has quietly moved past. None of that is fixable by rewriting sentences. It is fixable by asking questions until the missing material comes out, and then deciding what deserves space. So this skill does not polish prose. It interrogates a person, produces a durable record of what is true about their career, and tells them what to change and why. The rewriting happens elsewhere. ## The two readers Everything here follows from a fact about how CVs are actually consumed. There are two readers, and they want opposite things. **Reader one** spends roughly seven seconds deciding whether to bin it. For this reader, only the top third of page one exists. Their job is elimination, and they are looking for reasons to stop reading. **Reader two** has already decided the candidate is interesting and is now hunting for reasons to be confident. This reader wants *more*. Shortening the document actively hurts here. This is why "how long should it be" is the wrong question. The right question is whether the top third earns reader two's attention, and whether the rest rewards it. Keep both readers in mind wh