gaket/talent-agent

tailor-resume

Produces a one-page Markdown or LaTeX resume tailored to a specific internship, co-op, or new-grad SWE / data science / ML posting using only facts from the student's profile, with every bullet verified against facts.json.

Ver código fuente

Cómo usar

  1. Copia el comando y revisa el paquete antes de instalarlo en tu entorno de agente.
  2. Consulta las herramientas, credenciales y entornos necesarios en el documento original.
  3. Describe las entradas y el resultado deseado; contrasta la salida con las fuentes.
npx skills add https://github.com/gaket/talent-agent --skill tailor-resume

Antes de empezar

  • La instalación no incluye suscripción al modelo, cuota API ni permisos sobre tus archivos.
  • Las estrellas e instalaciones reflejan actividad, no una prueba independiente de calidad o seguridad.
Documento original del Skill

Contenido del repositorio de origen con títulos, ejemplos, código, tablas, enlaces e imágenes preservados.

tailor-resume

Inputs

  • Target JD (and score-fit output if available).
  • profile/cv.md and profile/facts.json (source of truth).

Steps

  1. Extract the JD's top 6–8 keywords (languages, frameworks, ML/data tools, responsibilities).
  2. Select content: education first for students; then the 2–3 most relevant experiences/projects by keyword overlap. Drop weak items to stay on one page.
  3. Rewrite bullets: action verb + what + tool + result. Reuse metrics only if present in facts.json. Mirror JD wording only where the fact supports it (e.g. "REST API" if FastAPI service exists).
  4. Reorder the skills line to put JD-matching, evidenced skills first. Never add a skill not in facts.json.skills or a project stack.
  5. Verify: produce a mapping table — each bullet → source fact id (exp1, proj1…). Any bullet without a source is removed or flagged as [NEEDS FACT] and you ask the user.
  6. Output to output/resume-<company>-<role>.md (default) or .tex (simple one-column LaTeX, no exotic packages). Keep to one page: ≤ ~550 words, ≤ 4 bullets per entry.
  7. Show a short diff summary: what moved up, what was cut, keywords covered / still missing (missing ones go back to score-fit gaps, not into the resume).

Rules

  • No invented experience, employers, dates, metrics, or skills. Rephrasing is fine; fabrication is not.
  • Keep contact info and education dates exactly as in facts.json.
  • ATS-friendly: no tables/columns/images in the resume itself; standard headings.
del mismo repositorio

Más Skills

Todos los Skills
gaket
Comunidad

find-people

Identifies hiring managers, recruiters, team engineers, and alumni founders at a target company for a DS/CS student using public sources such as team pages, engineering blogs, news, GitHub, and university pages, plus an opt-in, read-only LinkedIn search through a browser agent. Use when the user asks who to contact, who to ask for a referral, or which alumni founded or work at a company.

Instalaciones / 1h
1
GitHub Stars
0
Actualizado
7 nov
gaket
Comunidad

find-roles

Finds live internship, co-op, and new-grad SWE / data science / ML roles for DS/CS students in Canada and the US using public Greenhouse, Lever, and Ashby job-board APIs, Hacker News "Who is hiring" threads, and (optionally) the user's own JobRight feed read through a browser agent. Use when the user asks to find jobs, internships, new-grad openings, or what a company is hiring for.

Instalaciones / 1h
1
GitHub Stars
0
Actualizado
7 nov
gaket
Comunidad

score-fit

Scores how well a DS/CS student's profile fits an internship, co-op, or new-grad SWE / data science / ML job posting on a 1-5 scale, listing skill gaps, years-of-experience mismatch, and visa/sponsorship blockers. Use when the user asks "should I apply", "how good a fit is this", or wants roles ranked.

Instalaciones / 1h
1
GitHub Stars
0
Actualizado
7 nov
gaket
Comunidad

track-pipeline

Maintains a DS/CS student's job-application pipeline for internships, co-op, and new-grad SWE / data science / ML roles in tracker.md or tracker.csv, with statuses, follow-up dates, and a weekly digest. Use when the user asks to log an application, update a status, see what's due, or get a weekly job-search summary.

Instalaciones / 1h
1
GitHub Stars
0
Actualizado
7 nov