shadow-profile

View and reset personal skill usage profiles stored in PostgreSQL.

Updated Jul 16, 2026
One-click install
npx skills add https://github.com/pjherron/hypoc --skill shadow-profile-pjherron
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: shadow-profile
Source: https://github.com/pjherron/hypoc/tree/main/hypoc/skills/shadow-profile
Command: npx skills add https://github.com/pjherron/hypoc --skill shadow-profile-pjherron

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Developers using the hypoc platform have no visibility into how the system learns from their accept, decline, and revise decisions, making it hard to understand or correct which skills get recruited for future sessions. ## Core Features & Use Cases - Profile Inspection: Query the user_shadow_profile PostgreSQL table to see invocation counts, decline counts, last-used timestamps, and average task complexity per skill. - Recruitment Transparency: Understand how accept, decline, and revise actions shape future skill recruitment weighting, including project-scoped patterns. - Profile Reset: Clear all learned profile data with a single DELETE query to start fresh. - Use Case: A developer notices an unwanted skill keeps being suggested. They query their shadow profile, confirm a high invocation count for that skill, and reset or adjust their profile to change recruitment behavior. ## Quick Start Ask the assistant to show your shadow profile so you can see which skills you use most and which you consistently decline.

Frequently Asked Questions about shadow-profile

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I view my skill usage profile in hypoc?▼

Query the user_shadow_profile table in PostgreSQL filtering by your user_id, ordered by invocation_count descending. This shows which skills you use most, which you decline, last-used timestamps, and average task complexity.

How does skill recruitment learn from my decisions?▼

Every consent prompt interaction updates your profile: accepts increment invocation_count, declines increment decline_count, and revise-plus-accept counts as an invocation with a noted revision. High-accept skills surface first while high-decline skills are gradually suppressed.

How do I reset my shadow profile data?▼

Run a DELETE statement on the user_shadow_profile table filtered by your user_id. This clears all learned patterns so recruitment starts fresh with no historical weighting.

Does my shadow profile data leave my machine?▼

No. Profile data lives in your own PostgreSQL instance and does not leave your infrastructure. All learning and storage happen locally.

Can skill preferences be scoped to specific projects?▼

Yes. The profile distinguishes project-scoped patterns from global ones, so recruitment behavior learned in one project context only applies when you work in that project.