Menu
Roll up daily/weekly data into period summaries.
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.
Render brief from template and deliver to configured targets (email, GitHub issue, terminal).
Read and write memory JSON files in the user's dayarc folder.
Generate structured talking points for performance reviews, 1:1s, and self-assessments from accumulated monthly summaries.
Check for and apply updates to the Dayarc agent package from GitHub.
Extract corrections from user's reply to a brief email.
Conversationally configure a new signal source connector (Jira, ADO, Linear, Slack, etc.), generate a custom COLLECT skill, and register it in config.json.
Basé sur la classification professionnelle SOC
| name | Summarize Period |
| description | Roll up daily/weekly data into period summaries. |
For weekly: all daily profiles + previous weekly. For monthly: all weekly summaries + previous monthly.
{
"themes": [{ "label": "auth migration", "effort_share": 0.6, "progress": "Completed token refresh." }],
"accomplishments": ["Merged PR #1234"],
"stuck": [{ "description": "ARM CI pipeline flaky", "days_or_weeks": 4 }],
"focus_next": ["Finish auth rollout"]
}
feedback field across all input daily profiles. For each profile with a feedback entry, tally rated (count), positive (count where sentiment == "positive"), negative (count where sentiment == "negative"), and collect all distinct negative detail strings into themes. Emit as brief_quality: { rated, positive, negative, themes }. If no daily profiles had a feedback field, omit brief_quality.rated, positive, and negative across all input weekly brief_quality fields. Merge themes arrays and deduplicate. Emit as brief_quality. If no weekly summaries had brief_quality, omit the field.