Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

Commencer

learn-user-profile

Étoiles2

Forks2

Mis à jour17 mars 2026 à 06:38

Update the user's daily profile by learning from outgoing signals.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

YuiZhou

YuiZhou/dayarc-agent

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Assistants en ressources humaines (sauf paie et pointage)Bureau et soutien administratif·SOC 43-4161

SKILL.md

readonly

name	Learn User Profile
description	Update the user's daily profile by learning from outgoing signals.

Input

Outgoing signals (sent emails, Teams messages sent, commits, PRs authored), previous daily profile (or empty on bootstrap).

Output

Updated DailyProfile JSON — see memory-schemas.md for exact schema.

Instructions

Read previous profile (if exists).
For each outgoing signal, extract topics, contacts, threads.
Update focus_areas: bump confidence + last_seen for matches, add new at 0.5, decay unseen by -0.1 (remove if <0.1).
Update learning_interests: detect topics from content (blog links, docs, exploratory code), set trajectory.
Update key_contacts: increment interaction_count for people in today's signals.
Update active_threads: add new, update status, increment days_open.
Set priorities_today from infer_priorities output.
Set unfinished from items lacking completion signal. Each must have source_breadcrumb.
Bootstrap: if no previous profile, build fresh from today's signals.
VALIDATE output against memory-schemas.md before returning.

Plus depuis ce dépôt

même dépôt

deliver-brief

YuiZhou/dayarc-agent

Render brief from template and deliver to configured targets (email, GitHub issue, terminal).

2026-05-282

dayarc-memory

YuiZhou/dayarc-agent

Read and write memory JSON files in the user's dayarc folder.

2026-05-082

review-prep

YuiZhou/dayarc-agent

Generate structured talking points for performance reviews, 1:1s, and self-assessments from accumulated monthly summaries.

2026-05-082

dayarc-upgrade

YuiZhou/dayarc-agent

Check for and apply updates to the Dayarc agent package from GitHub.

2026-04-302

parse-reply

YuiZhou/dayarc-agent

Extract corrections from user's reply to a brief email.

2026-04-092

dayarc-add-connector

YuiZhou/dayarc-agent

Conversationally configure a new signal source connector (Jira, ADO, Linear, Slack, etc.), generate a custom COLLECT skill, and register it in config.json.

2026-04-062

name	Learn User Profile
description	Update the user's daily profile by learning from outgoing signals.

Input

Outgoing signals (sent emails, Teams messages sent, commits, PRs authored), previous daily profile (or empty on bootstrap).

Output

Updated DailyProfile JSON — see memory-schemas.md for exact schema.

Instructions

Read previous profile (if exists).
For each outgoing signal, extract topics, contacts, threads.
Update focus_areas: bump confidence + last_seen for matches, add new at 0.5, decay unseen by -0.1 (remove if <0.1).
Update learning_interests: detect topics from content (blog links, docs, exploratory code), set trajectory.
Update key_contacts: increment interaction_count for people in today's signals.
Update active_threads: add new, update status, increment days_open.
Set priorities_today from infer_priorities output.
Set unfinished from items lacking completion signal. Each must have source_breadcrumb.
Bootstrap: if no previous profile, build fresh from today's signals.
VALIDATE output against memory-schemas.md before returning.