Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/SudharakaA/ai-job-search/llms.txt

Use this file to discover all available pages before exploring further.

/expand finds the competencies that /setup could not extract on its own. A CV lists what you did, but it rarely captures everything you know: a course name implies a syllabus worth of skills, a GitHub repository implies a toolchain, a reference letter uses competency language that your own documents never do. /expand traces each of those signals, looks up what they imply via web search, and proposes additions to your profile with a source tag attached to every item. Nothing is written until you review and approve the full list.

​
Syntax

/expand
Run /expand with no arguments. It discovers sources automatically from your existing profile files.
The best time to run /expand is right after /setup, before you start applying to jobs. It surfaces skills your documents alone do not make explicit, giving /apply a richer profile to tailor from.

​
Sources scanned

/expand processes sources in a fixed order, reading what you have and skipping what you do not.
1

documents/cv/

Reads all CV files and extracts every course or module listed, every certification with issuer and date, every job responsibility bullet, every independent or side project, and every volunteer or extracurricular role.
2

documents/linkedin/

Reads LinkedIn export files and extracts the Licenses and Certifications section, skills and endorsements, volunteer experiences, projects, and any items not already found in the CV.
3

documents/diplomas/

Reads diploma and transcript files and extracts all course and module names, the thesis title and subject area, and any specialization or track name.
4

documents/references/

Reads reference letters and extracts the competency language used by each referee, including specific skills, tools, or methods they name, and any projects they describe.
5

GitHub profile

Looks up the GitHub username from 01-candidate-profile.md. For each public repository (not just pinned ones), fetches the README and records the name, description, primary languages, topics, and any frameworks or libraries mentioned.
6

Other URLs in profile

Checks 01-candidate-profile.md for any other URLs (portfolio site, Kaggle, Google Scholar, ResearchGate, publication links) and fetches each one to extract tools, methods, datasets, awards, or skills mentioned.

​
Two enrichment approaches

For every experience item discovered, /expand applies both enrichment approaches, not just one.
If the item names a specific tool, framework, course, or certification, /expand searches for it directly:
  • "[Course name] [Provider] syllabus learning outcomes"
  • "[Certification name] skills covered exam guide"
  • "[Tool/framework name] skills what you learn"
This approach is used for named online courses (Coursera, edX, fast.ai, DataCamp, etc.), named certifications (AWS, GCP, Azure, Databricks, Tableau, etc.), university courses with a standard syllabus, and GitHub repositories whose README names specific technologies.

​
Competency map structure

After enriching all items, /expand builds a deduplicated competency map grouped into five categories:
CategoryWhat goes here
Technical Skills: PrimaryCore languages, frameworks, and methods you use regularly
Technical Skills: SecondaryTools you have used but are not primary
Domain KnowledgeSubject matter expertise: geophysics, ML, NLP, climate tech, etc.
Methods and PracticesAgile, version control, reproducibility, testing, CI/CD, etc.
Soft / BehavioralLeadership, communication, and collaboration signals from references and project descriptions
Any competency already present in 01-candidate-profile.md or 02-behavioral-profile.md is removed from the map before the review step.

​
Review flow

/expand presents the full competency map before writing anything: 
## /expand found [N] new competency signals across [M] sources

**COURSES & CERTIFICATIONS**
Source: Deep Learning Specialisation (Coursera)
  + Convolutional neural networks (CNNs)
  + Sequence models and LSTMs
  + Hyperparameter tuning and batch normalization

**GITHUB: project-name**
Source: README + inferred from tech stack
  + Apache Airflow (pipeline orchestration)
  + dbt (data transformation)
You then choose one of three responses:
  • all: add everything to your profile
  • review: walk through each source group one at a time
  • skip: cancel without writing anything
You can also list specific groups to skip, for example: "skip GitHub, add everything else".

​
Source tagging

Every addition written to 01-candidate-profile.md or 02-behavioral-profile.md includes a brief source annotation in parentheses, for example (Coursera: Deep Learning Specialisation) or (GitHub: project-name). This annotation lets you verify where each skill came from, and it makes future /expand runs idempotent by ensuring the same item is never proposed twice. Behavioral signals inferred from reference letters or LinkedIn About text are always labeled as inferred: [Inferred from reference letter, Name / review before relying on this].
/expand is additive only. It never modifies existing profile content, only appends new items. If you want to remove something it added, edit the skill file directly.

/setup

Run /setup first to populate the base profile that /expand builds on

/upskill

Analyze gaps between your enriched profile and target job postings

/apply

Apply to jobs using the richer profile /expand produces

/reset

Clear your profile and start the enrichment process over

Build docs developers (and LLMs) love

Get started for freeTalk to us