> For the complete documentation index, see [llms.txt](https://docs.zipwire.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zipwire.io/zipwire-approve/unboxing-key-concepts/skills-extraction.md).

# Skills Extraction

Skills live in your timesheets but stay buried. You log detailed activity descriptions—the projects, technologies, companies—but when you need to write a proposal or update your CV, those skills aren't labeled or easy to find.

**Skills extraction automatically discovers professional skills from your timesheet activities** using AI, so you never lose track of what you've built.

## How It Works

When you create a timesheet, the system analyzes your activities:

* **Activity names** — What did you work on?
* **Companies and projects** — Organizational context
* **Duration** — How much time did you spend?
* **Comments** — Any notes you added?

An LLM reads this context and identifies skills you've used. It returns:

* **Skill name** — "React", "Project Management", "TypeScript"
* **Category** — "Frontend Development", "Leadership", "Language"
* **Confidence score** — 0.0–1.0 indicating extraction reliability

## What You Get

**Automatic skill profile:** As you log work, your skills accumulate automatically. No manual entry. No forgetting.

**Grounded in real work:** Skills come from activities you've actually logged with timestamps and context—not guesses or self-reported claims.

**Soft skills too:** The system catches leadership, mentoring, stakeholder management, and other soft skills you performed and documented.

**Non-blocking:** If extraction fails (bad response, network issue), your timesheet still gets created. Skills are a bonus, not a blocker.

## Use Cases

**Portfolio building:** Your extracted skills feed your public profile automatically. No tedious manual skill lists.

**Job matching:** Hiring platforms can match you to opportunities based on your actual extracted skills, not self-reported ones.

**Proposal writing:** When you need to write a proposal, your extracted skills are there: "I have 500+ hours of React, 200+ hours of TypeScript, and led a team of 3 engineers."

**Audit trail:** Extracted skills are tied to logged work, creating a verifiable record of what you've done.

## Integration with Verifiable Timesheets

Extracted skills are included in your **frozen timesheet record** when it's approved. They become part of the Merkle tree and are attested to the blockchain via EAS, so you can prove your skills with cryptographic evidence.

See [Verifiable Timesheets](/zipwire-approve/verifiable-timesheets.md) to learn how your extracted skills become verifiable, portable proofs.

## Learn More

{% content-ref url="<https://github.com/zipwireapp/gbk-tz-docs/blob/main/blog/your-skills-are-already-in-your-timesheets/README.md>" %}
<https://github.com/zipwireapp/gbk-tz-docs/blob/main/blog/your-skills-are-already-in-your-timesheets/README.md>
{% endcontent-ref %}

{% content-ref url="/pages/bBE0TkceIu9QSt3a5zX3" %}
[Verifiable Timesheets with Selective Disclosure](/zipwire-approve/verifiable-timesheets.md)
{% endcontent-ref %}

{% content-ref url="/pages/P1oSNNJGnWqncV3gLSln" %}
[Timesheets](/zipwire-approve/unboxing-key-concepts/timesheets.md)
{% endcontent-ref %}