Resume tailor
Tailors a résumé to a specific job description — parses the JD for priorities, reorders and rewrites bullets to match, quantifies achievements, and passes ATS filters. Use when a user is applying to a specific role and wants their résumé to match the JD, or when their bullets are weak ("responsible for...") and need tightening.From its SKILL.md
npx -y skills add Solonnikov/agent-skills --skill resume-tailorAssembled 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.
- 2 stars2 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
4.4 KB, ~1.0k tokens by cl100k_base, as published. Nobody here has run it
Résumé Tailor
A résumé that matches the job description beats a generic one. Not by keyword-stuffing; by showing the exact evidence the hiring team is looking for.
When to use
- User is applying for a specific role and wants their résumé tuned to that JD.
- Résumé reads generic ("responsible for") and needs punch.
- User has 5+ years of experience and a résumé overflowing onto page 3 — needs cutting.
- ATS-compatibility is a concern (large companies; public sector; many online portals).
Before you start
Gather:
- The job description — full text, not a summary. Priorities are buried in specific wording.
- The current résumé — ideally in editable form (Markdown, Google Doc, Word). PDF only means you'll retype.
- The user's recent work + achievements that aren't on the résumé yet — often there's a strong story hidden in Slack DMs and project docs.
- Which companies they'd be most excited about — the one where they'll push hardest and get the most value from tailoring.
Tailoring workflow
- Parse the JD. Separate must-haves, nice-to-haves, culture signals. See jd-parsing.md.
- Audit the current résumé against the must-haves. What's already there? What's missing? What's there but buried?
- Reorder. Most relevant experience first — within the same role, reorder bullets. Across roles, keep reverse-chronological but consider a summary / highlights section at the top.
- Rewrite weak bullets. Apply STAR (Situation / Task / Action / Result). See bullet-rewrites.md.
- Quantify everything possible. "Improved performance" < "Cut p95 latency 40% (800ms → 480ms)" < "Cut p95 latency 40%, unblocking SLA target for 3M monthly users."
- Trim. One page if <10 years experience, two pages max otherwise. Recent and relevant stays; old and tangential goes.
- ATS pass. Remove fancy formatting, tables, text-in-images, two-column layouts. Single column, clean headers, normal fonts. See ats-formatting.md.
- Generate a short cover letter / email that leads with the specific reason this role is a match — not a restatement of the résumé.
Non-negotiable rules
- Never fabricate. Achievements, titles, metrics, dates — all real. Fabricated résumés get discovered in reference checks, probation reviews, or worse.
- Lead every bullet with a verb. "Led a team of 5..." not "Was responsible for leading..."
- Quantify every bullet you can. Numbers, percentages, counts, dollars. "Shipped feature" is weaker than "Shipped feature used by 2,400 users in week 1".
- Match the JD's vocabulary — where truthful. If the JD says "partner with stakeholders", use "partnered with stakeholders", not "worked closely with folks".
- Cut filler sections. "Objective" / "References available on request" / generic skills lists — delete. Wasted space.
- One page if possible. Hiring teams spend 30 seconds on first pass. Two pages means they might not reach page 2.
- Never use first person. "Shipped X" not "I shipped X". Not "Yaroslav shipped X" either — implied first person, no pronoun.
- Never use a photo (in the US/UK/Canada). In some European countries and APAC it's expected — match local norm.
- Dates on the right, roles on the left — makes scanning easy for recruiters.
Output
- The tailored résumé — full document, ready to copy into the user's source.
- A change log — what you rewrote, what you cut, what you reordered, and why. So the user can push back on your edits.
- A short cover email/letter — optional but almost always worth including.
References
- Parsing a JD — how to extract must-haves, nice-to-haves, and culture signals; common JD patterns.
- Bullet rewrites — STAR pattern, strong verb lists, quantification tactics, common bullet failures.
- ATS formatting — the layout choices that survive parsing, the ones that don't; Word vs PDF; file-naming.
What ships with it: 3 files
15.0 KB alongside SKILL.md
references/
- ats-formatting.md4.9 KB
- bullet-rewrites.md5.5 KB
- jd-parsing.md4.6 KB
Gives 0 of the 12 instructions most hr recruiting skills give in ~1.0k 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
- gather the full job description text
- apply ATS-compatible formatting
- generate a short cover letter
- produce a change log explaining edits
- match the job description vocabulary truthfully
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.