Skills

Skills are reusable workflows built from your memories. They capture how you like things done and let your AI apply that knowledge automatically in future conversations.

What is a Skill?

A skill is a saved workflow or set of instructions that your AI can apply when the situation matches. For example, a "Weekly Client Report" skill might contain:

• Who receives the report (sarah@company.com)
• Which template to use (blue brand deck)
• Where to pull data from (Linear for hours, dashboard for metrics)
• When it's due (Friday by 5pm)

Once saved, your AI applies this automatically whenever you say "help me with this week's client report."

Skill Lifecycle

Skills follow a simple flow:

Draft → Active → Deprecated
          ↓
       Rejected

Draft

New skills start as drafts. They:

• Are not used automatically
• Can be reviewed and edited
• Require your explicit approval to activate

Active

Approved skills become active. They:

• Are suggested when the context matches
• Can be deprecated if they become outdated
• Track whether they're actually helping

Deprecated

When a skill becomes outdated:

• It's no longer suggested
• It can point to a replacement skill
• It stays in your history for reference

Rejected

If a skill isn't right:

• It won't become active
• Your rejection reason is saved
• It can be edited and resubmitted

Creating Skills

From Your Memories (Recommended)

The best skills come from patterns Kyew detects in your memories:

"analyze patterns in my client-reporting workflow"
"generate a skill from those client reporting memories"

Your AI synthesizes your memories into a structured workflow you can review and approve.

Manual Creation

You can also create a skill directly:

"create a skill called 'Weekly Standup Prep' with instructions for
pulling open tickets from Linear, checking the Slack channel for
blockers, and formatting the summary for our team meeting"

Managing Skills

Everything is done through conversation:

"list all my active skills"
"list skills about reporting"
"show draft skills waiting for my approval"
"show me the Weekly Client Report skill"

Updating

"update the Client Report skill to include the new Q1 metrics template"

Updates create new versions — your history is always preserved.

Searching

"search for skills about team processes"

Approval Workflow

Why Approval Matters

Skills require approval because:

• They influence how your AI behaves in future conversations
• Automatic learning could capture incorrect patterns
• You stay in control of what your AI knows and does

Reviewing Pending Skills

"show pending skills"

Before approving, check:

• Does this accurately capture my workflow?
• Is the scope right — not too broad, not too narrow?
• Would this actually help me in the future?

Approving

"approve the Client Report skill"
"approve the Standup Prep skill with note 'reviewed, looks good'"

Rejecting

"reject that skill — the process changed since last month"

How Skills Get Used

Automatic Suggestions

When you're working on something that matches an active skill, your AI applies it:

You: "Help me prepare this week's client report"

AI: Based on your "Weekly Client Report" skill, I'll pull hours from
    Linear, grab the metrics from the dashboard, and format everything
    in the blue brand template for sarah@company.com.

Explicit Requests

"what skills do I have for reporting?"
"apply my standup prep skill"

Feedback

After using a skill, let your AI know if it helped:

"that skill worked perfectly"
"the reporting skill needs updating — we switched from Linear to Asana"

Version History

Skills keep a full version history:

"show history for the Client Report skill"

Rollback

If an update made things worse:

"roll back the Client Report skill to the previous version"

Deprecation

When workflows change:

"deprecate the old onboarding skill — we have a new process now"

Deprecated skills stop being suggested but stay in your history.

Tips

Keep Skills Focused

One skill = one workflow. "Client Reporting" is good. "Everything About My Job" is too broad.

Use Specific Triggers

When creating skills manually, include the phrases that should trigger them:

"create a skill for client reporting, triggered by 'client report',
'weekly report', or 'report for Sarah'"

Check for Overlaps

Before creating a new skill:

"do I have any skills similar to 'meeting prep'?"

Deprecate, Don't Delete

When a skill becomes outdated, deprecate it rather than deleting. This preserves your history and can point to the replacement.