Agent skill

prod-end-of-day

End-of-day consolidation — analyzes agent memory, ADW logs, meetings, tasks, and learnings to generate a complete daily log. Trigger when user says 'end of day', 'wrap up', 'done for today', 'goodnight', 'shutdown', or anything that signals finishing a work session.

Stars 211
Forks 54

Install this agent skill to your Project

npx add-skill https://github.com/EvolutionAPI/evo-nexus/tree/main/.claude/skills/prod-end-of-day

SKILL.md

End of Day — Daily Consolidation

End-of-day routine that consolidates everything that happened during the day: agent memory, ADW logs, meetings, tasks, and learnings.

Always respond in English.

Step 1 — Collect data for the day (silently)

Read all available sources without narrating each step:

1a. Agent memory

Read recent memory files from each agent in .claude/agent-memory/:

  • flux-finance/ — financial decisions of the day
  • atlas-project/ — project updates
  • kai-personal-assistant/ — if there is anything relevant
  • Any other agent that was used

1b. ADW logs

Read today's JSONL log at ADWs/logs/YYYY-MM-DD.jsonl to see which routines ran, duration, and status.

1c. Meetings of the day

Check workspace/meetings/summaries/ and workspace/meetings/fathom/ for today's synced meetings.

1d. Tasks

Run todoist today to see completed and pending tasks for the day.

1e. Git changes of the day

Run git diff --stat and git log --oneline --since="today 00:00" to see:

  • Files created, modified, or deleted today
  • Commits made (messages and authors)
  • Uncommitted changes (working tree)

This gives the real overview of what changed in the workspace — more accurate than reading the conversation.

1f. Current session

Review the current session conversation — what was discussed, decided, and done.

Step 2 — Consolidate learnings

Analyze everything that was collected and identify:

  • Decisions made — what was decided and why
  • Learnings — patterns, corrections, feedback that should be remembered
  • People — new context about team members
  • Real pending items — things that truly remain open (do not fabricate)

Step 3 — Save memory

If there are relevant decisions, learnings, or feedback, save to persistent memory in memory/ following the workspace memory system (see prod-memory-management).

Do not duplicate — check if similar memory already exists before creating.

Step 4 — Generate daily log

Read the template at .claude/templates/end-of-day-log.md and fill with the consolidated data.

Save to:

workspace/daily-logs/[C] YYYY-MM-DD.md

The log should include:

  • What was done (projects, tasks, meetings)
  • Files created or modified
  • ADW routines that ran (with status)
  • Pending items (only if real)
  • Where to resume tomorrow

Step 5 — Organize tasks

Run /prod-review-todoist to ensure tasks created during the day are categorized and translated.

Step 6 — Confirm

Present a short summary:

## Day closed

**Log:** workspace/daily-logs/[C] YYYY-MM-DD.md
**ADW Routines:** {N} executed ({status})
**Tasks:** {completed}/{total} completed
**Memories:** {N} created/updated
**Learnings:** {N} recorded

**Tomorrow:** {sentence about where to resume}

Notify via Telegram

Upon completion, send a short summary via Telegram to the user:

  • Use the Telegram MCP: reply(chat_id="YOUR_CHAT_ID", text="...")
  • Format: emoji + routine name + main result (1-3 lines)
  • If the routine had no updates, send anyway with "no updates"

Expand your agent's capabilities with these related and highly-rated skills.

EvolutionAPI/evo-nexus

data-create-viz

Cria visualizações de dados de qualidade profissional com Python no tema Evolution (fundo escuro, acento

211 54
Explore
EvolutionAPI/evo-nexus

cs-customer-escalation

Empacota uma escalação para Devs, Produto ou Davidson com contexto completo. Use quando um bug precisa de atenção além do suporte normal, vários clientes reportam o mesmo problema, um cliente está ameaçando cancelar, ou um problema ficou sem resolução além do SLA. / Package an escalation for engineering, product, or leadership with full context. Use when a bug needs engineering attention beyond normal support, multiple customers report the same issue, a customer is threatening to churn, or an issue has sat unresolved past its SLA.

211 54
Explore
EvolutionAPI/evo-nexus

mkt-draft-content

Draft blog posts, social media, email newsletters, landing pages, press releases, and case studies with channel-specific formatting and SEO recommendations. Use when writing any marketing content, when you need headline or subject line options, or when adapting a message for a specific platform, audience, and brand voice.

211 54
Explore
EvolutionAPI/evo-nexus

gog-tasks

Create, manage, and prioritize tasks and todo items. Convert emails to tasks, set priorities (P0-P3) and categories (Work/Personal/Errands/Admin), review daily priorities, track blocked and overdue tasks. Use when user mentions tasks, todos, action items, or wants to convert emails to tasks. Requires confirmation before creating or deleting tasks.

211 54
Explore
EvolutionAPI/evo-nexus

discord-get-messages

Retrieve messages from Discord channels via the Discord API. Use this skill when the user wants to read, search, or analyze messages from a Discord channel.

211 54
Explore
EvolutionAPI/evo-nexus

cs-customer-research

Pesquisa multi-fonte sobre pergunta ou tópico de cliente com atribuição de fontes. Use quando um cliente pergunta algo que precisa ser verificado, investigando se um bug foi reportado antes, verificando o que foi dito anteriormente a uma conta específica, ou coletando contexto antes de redigir uma resposta. / Multi-source research on a customer question or topic with source attribution. Use when a customer asks something you need to look up, investigating whether a bug has been reported before, checking what was previously told to a specific account, or gathering background before drafting a response.

211 54
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results