Cv tailoring
Tailor a CV to a specific job description with strict factual integrity. Use when the user asks to create, tailor, or adapt a CV or resume for a role. Enforces a no-fabrication rule, role-relevance ordering, and the user's own formatting and vocabulary preferences. Requires the user's career facts to be configured below before first use.From its SKILL.md
npx -y skills add Chandragopaluk/claude-skills --skill cv-tailoringAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
3.3 KB, 658 tokens by cl100k_base, as published. Nobody here has run it
CV Tailoring
Tailors a CV to a target job description without inventing anything. The skill's core bet: a slightly less impressive true CV beats an impressive embellished one, every time, because interviews and referencing exist.
Configuration (fill in before first use)
Replace this section with your own facts. The skill refuses to work from memory or inference about your career; only what is written here may appear in a CV.
chronology:
# Locked list. Every role, exact dates. The skill may OMIT roles, never alter them.
- { title: "", employer: "", from: "YYYY-MM", to: "YYYY-MM", domain: "" }
credentials:
# Only completed or explicitly in-progress items. Mark in-progress as such.
- ""
formatting:
heading_font: ""
body_font: ""
accent_colour: ""
layout_notes: ""
banned_words: []
# Words/phrases that must never appear, e.g. corporate filler you dislike.
voice:
# One line on tone, e.g. "direct, no softening, achievements as facts not adjectives"
Hard rules
- No fabrication. Nothing appears on the CV that is not in the configuration or supplied by the user in the current conversation. No invented metrics, no rounded-up team sizes, no inferred responsibilities. If a job description asks for something the user doesn't have, the CV stays silent on it; flag the gap to the user separately.
- Chronology is immutable. Roles may be omitted for relevance; dates and titles may never be adjusted. Gaps are allowed to exist.
- Claims must be load-bearing. Every bullet must survive the follow-up question "tell me more about that". If the user couldn't speak to it for two minutes, it doesn't go in.
- Banned words are banned everywhere, including quotes from the job description.
Tailoring process
- Parse the job description: extract must-have requirements, nice-to-haves, the domain (sector, regulatory context), and the seniority signals (budget, team size, stakeholder level).
- Map honestly: for each must-have, find genuine evidence in the configured chronology. Build a two-column map: requirement → strongest true evidence. Where evidence is weak or absent, record the gap.
- Select and order roles: lead with domain-relevant roles; compress or omit roles that add length without relevance. Earlier career can collapse to a single line.
- Write bullets as outcomes: what changed because this person was there, with numbers only where the user has supplied them. Activity descriptions ("responsible for...") are rewritten or cut.
- Apply formatting and voice from configuration.
- Report the gaps: alongside the CV, give the user the honest gap list from step 2 and how they might address each in a cover letter or interview, or whether to skip applying.
Output
A formatted CV document (use the docx skill for professional output) plus a short gap report. Never deliver the CV without the gap report; the report is where the user's real decision lives.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most hr recruiting skills give in 658 tokens
Counted across 356 of the 357 authors here whose files we hold, read 2026-08-07
- Quantify achievements with specific metricsin 14 of 356, across 6 files
- Keep the resume under two pagesin 14 of 356, across 6 files
- Request the full job description if not providedin 12 of 356, across 4 files
- Extract keywords and prioritize job requirementsin 12 of 356, across 4 files
- Stop and ask for clarification if required inputs are missingin 12 of 356, across 5 files
- Map candidate experience to job requirementsin 11 of 356, across 3 files
- Ask if the user wants adjustmentsin 11 of 356, across 3 files
- Provide strengths and gap analysis after the resumein 10 of 356, across 2 files
- Request candidate background details if not providedin 10 of 356, across 2 files
- Format experience bullets as action verb plus resultin 10 of 356, across 2 files
- Ask for missing inputs before startingin 10 of 356, across 9 files
- Use exact job description terminologyin 9 of 356, across 1 file
Said here and by no other author read
- use configured career facts only
- omit roles for relevance but never alter dates or titles
- lead with domain-relevant roles
- write bullet points as outcomes
- include numbers only when the user supplies them
- apply configured formatting and voice preferences
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.