Help us improve
Share bugs, ideas, or general feedback.
From looplia-writer
Reads user-profile.json from workspace root, calculates relevance scores for content by matching tags to user topics and interest levels for personalized output.
How this skill is triggered — by the user, by Claude, or both
Slash command
/looplia-writer:user-profile-readerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read and interpret user preferences for content personalization.
Share bugs, ideas, or general feedback.
Read and interpret user preferences for content personalization.
user-profile.json from workspace root~/.looplia/user-profile.json
{
"userId": "string",
"topics": [
{ "topic": "string", "interestLevel": 1-5 }
],
"style": {
"tone": "beginner" | "intermediate" | "expert" | "mixed",
"targetWordCount": 100-10000,
"voice": "first-person" | "third-person" | "instructional"
}
}
Calculate score.relevanceToUser (0-1):
1. For each user topic:
- weight = interestLevel / 5
- matched = content tags/themes contain topic (case-insensitive)
2. Calculate score:
- matchedWeight = sum of weights for matched topics
- totalWeight = sum of all topic weights
- score = matchedWeight / totalWeight
3. If no user topics defined:
- score = 0.5 (neutral)
User profile:
{
"topics": [
{ "topic": "AI", "interestLevel": 5 },
{ "topic": "productivity", "interestLevel": 3 },
{ "topic": "cooking", "interestLevel": 2 }
]
}
Content tags: ["AI", "safety", "alignment"]
Calculation:
When content-documenter needs relevance score:
score.relevanceToUser fieldnpx claudepluginhub memorysaver/looplia-core --plugin looplia-writerBuilds personalized reader persona from Readwise Reader data using highlights searches, document lists, tags, and Python/Bash parsing for triage, quiz skills.
Distills user profiles from prompt history or local agent chat logs, extracting personality, work traits, and communication preferences. Opt-in for explicit requests with privacy safeguards.
Manages user preferences and corrections across sessions, learning from past corrections to adapt communication style, technical preferences, and workflow defaults.