> 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 %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.zipwire.io/zipwire-approve/unboxing-key-concepts/skills-extraction.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.