Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate professional resumes that conform to the Reactive Resume schema. Use when the user wants to create, build, or generate a resume through conversational AI, or asks about resume structure, sections, or content. This skill guides the agent to ask clarifying questions, avoid hallucination, and produce valid JSON output for https://rxresu.me.
.claude/skills/amruthpillai-resume-builder/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 89% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 69% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 33% | 0% |
Build professional resumes through conversational AI for Reactive Resume, a free and open-source resume builder.
Reactive Resume MCP can manage job applications as well as resumes. When the user wants to track applications through an agent, use the application tools instead of asking them to open the web UI.
list_applications before changing existing records.create_application for one new opportunity or import_applications for spreadsheet/CSV rows.update_application to move stages, archive/unarchive, edit contacts, set follow-ups, link a resume, or update job details.add_application_note to log timeline activity.attach_application_document and remove_application_document for sent resume or cover-letter PDFs.score_application_match, tailor_resume_for_application, and draft_application_message for Application Copilot workflows after a linked resume and job description exist.Ask for essential details first, unless the user has already provided them:
For each section the user wants to include, gather specific details. Never invent dates, company names, or achievements.
Experience: company, position, location, period (e.g., "Jan 2020 - Present"), description of responsibilities/achievements
Education: school, degree, area of study, grade (optional), location, period
Skills: name, proficiency level (Beginner/Intermediate/Advanced/Expert), keywords
Projects: name, period, website (optional), description
Other sections: languages, certifications, awards, publications, volunteer work, interests, references
Ask about preferences:
Output must conform to the Reactive Resume schema. See references/schema.md for the complete schema structure.
Key requirements:
id fields must be valid UUIDsurl and label propertiesrgba(r, g, b, a) formatShare these tips when helping users craft their resume content:
For most professionals:
For students/recent graduates:
When generating the resume, output a complete JSON object that conforms to the Reactive Resume schema. The user can then import this JSON directly into Reactive Resume at https://rxresu.me.
Example minimal structure:
json{ "picture": { "hidden": true, "url": "", "size": 80, "rotation": 0, "aspectRatio": 1, "borderRadius": 0, "borderColor": "rgba(0, 0, 0, 0.5)", "borderWidth": 0, "shadowColor": "rgba(0, 0, 0, 0.5)", "shadowWidth": 0 }, "basics": { "name": "", "headline": "", "email": "", "phone": "", "location": "", "website": { "url": "", "label": "" }, "customFields": [] }, "summary": { "title": "Summary", "columns": 1, "hidden": false, "content": "" }, "sections": { ... }, "customSections": [], "metadata": { "template": "onyx", "layout": { ... }, ... } }
For the complete schema, see references/schema.md.
When information is missing, ask specific questions:
Avoid compound questions. Ask one thing at a time for clarity.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 10,977 | 9,809 | -11% | 1 | 1 | 0% | 690 | 2,931 | +325% | 0 | 0 | — |
case-02 | fail→pass | 12,733 | 17,050 | +34% | 1 | 1 | 0% | 2,688 | 5,071 | +89% | 0 | 0 | — |
case-03 | fail→pass | 20,010 | 18,552 | -7% | 1 | 1 | 0% | 4,022 | 4,837 | +20% | 0 | 0 | — |
case-04 | fail→pass | 10,207 | 3,122 | -69% | 1 | 1 | 0% | 1,655 | 1,740 | +5% | 0 | 0 | — |
case-05 | fail→pass | 8,075 | 4,056 | -50% | 1 | 1 | 0% | 1,109 | 1,875 | +69% | 0 | 0 | — |
case-06 | fail→pass | 8,774 | 3,290 | -63% | 1 | 1 | 0% | 1,356 | 1,801 | +33% | 0 | 0 | — |
case-07 | fail→pass | 9,409 | 4,740 | -50% | 1 | 1 | 0% | 1,633 | 2,080 | +27% | 0 | 0 | — |
case-08 | fail→pass | 5,485 | 4,404 | -20% | 1 | 1 | 0% | 753 | 1,982 | +163% | 0 | 0 | — |
case-09 | fail→fail | 10,982 | 10,549 | -4% | 1 | 1 | 0% | 1,823 | 2,946 | +62% | 0 | 0 | — |
case-10 | pass→pass | 8,466 | 6,030 | -29% | 1 | 1 | 0% | 1,435 | 2,344 | +63% | 0 | 0 | — |
case-11 | pass→pass | 11,212 | 6,763 | -40% | 1 | 1 | 0% | 1,712 | 2,326 | +36% | 0 | 0 | — |
case-12 | fail→pass | 7,452 | 11,362 | +52% | 1 | 1 | 0% | 1,153 | 3,600 | +212% | 0 | 0 | — |
case-13 | pass→fail | 14,519 | 7,379 | -49% | 1 | 1 | 0% | 2,039 | 2,364 | +16% | 0 | 0 | — |
case-14 | pass→pass | 13,296 | 5,588 | -58% | 1 | 1 | 0% | 2,060 | 2,160 | +5% | 0 | 0 | — |
case-15 | fail→fail | 7,645 | 3,960 | -48% | 1 | 1 | 0% | 1,070 | 1,885 | +76% | 0 | 0 | — |
case-16 | pass→pass | 8,101 | 21,380 | +164% | 1 | 1 | 0% | 1,068 | 1,987 | +86% | 0 | 0 | — |
case-17 | pass→pass | 8,183 | 5,289 | -35% | 1 | 1 | 0% | 1,241 | 2,057 | +66% | 0 | 0 | — |
case-18 | fail→pass | 6,700 | 9,154 | +37% | 1 | 1 | 0% | 1,042 | 2,547 | +144% | 0 | 0 | — |
case-19 | fail→pass | 9,720 | 3,647 | -62% | 1 | 1 | 0% | 1,617 | 1,831 | +13% | 0 | 0 | — |
case-20 | fail→pass | 15,952 | 6,258 | -61% | 1 | 1 | 0% | 2,236 | 2,357 | +5% | 0 | 0 | — |
case-21 | pass→pass | 8,629 | 6,889 | -20% | 1 | 1 | 0% | 1,284 | 2,262 | +76% | 0 | 0 | — |
case-22 | pass→pass | 6,642 | 5,672 | -15% | 1 | 1 | 0% | 963 | 2,025 | +110% | 0 | 0 | — |
case-23 | pass→pass | 8,947 | 6,534 | -27% | 1 | 1 | 0% | 1,533 | 2,170 | +42% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 22 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +43 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.