Today logo

Today

Community
kv0906
today

Guided daily workflow orchestrator. Multi-phase process (standup, team sync, review, focus, wrap-up). Use when user says "today", "start my day", or "daily workflow".

Overview

Publisherkv0906
Repositorypm-kit
Skill nametoday
Stars
140
Forks
35
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by kv0906 on GitHub. Read the source before you install it.

Installation

Install the Today AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/kv0906/pm-kit/tree/main/.claude/skills/today
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/kv0906/pm-kit.git /tmp/pm-kit
mkdir -p .claude/skills
cp -r /tmp/pm-kit/.claude/skills/today .claude/skills/today
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Today in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Today on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Today is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

/today — Daily Workflow Orchestrator

Guides PMs through a structured daily routine: standup → team sync → review → focus → wrap-up. Reuses existing skill logic (/daily, /meet, /progress) — does NOT duplicate it.

Context

Today's date: !date +%Y-%m-%d Existing daily: !ls daily/*.md 2>/dev/null | tail -5

Config: @_core/config.yaml Processing logic: @_core/PROCESSING.md Daily template: @_templates/daily.md

Reference skills (for reuse patterns):

  • @.claude/skills/daily/SKILL.md — keyword detection, blocker/decision logic
  • @.claude/skills/meet/SKILL.md — meeting note parsing
  • @.claude/skills/progress/SKILL.md — dashboard aggregation

Input

User input: $ARGUMENTS

Argument Handling

  • No args: Start from Phase 1, or resume current phase (detect via TaskList)
  • status: Show which phase is currently active
  • skip: Skip current phase, advance to next
  • wrap: Jump directly to Phase 5 (wrap-up)

Session Task Progress

Create all phase tasks upfront with dependencies:

TaskCreate: "Phase 1: Daily Standup"
  description: "Capture updates for all active projects"
  activeForm: "Running daily standup..."

TaskCreate: "Phase 2: Team Sync"
  description: "Process external context (Slack, meetings, Linear)"
  activeForm: "Processing team sync..."

TaskCreate: "Phase 3: Review"
  description: "Display cross-project health dashboard"
  activeForm: "Generating review dashboard..."

TaskCreate: "Phase 4: Focus"
  description: "Display priorities and pause for deep work"
  activeForm: "Setting focus priorities..."

TaskCreate: "Phase 5: Wrap-Up"
  description: "Summarize the day"
  activeForm: "Wrapping up the day..."

Set dependencies:

TaskUpdate: Phase 2, addBlockedBy: [phase-1-id]
TaskUpdate: Phase 3, addBlockedBy: [phase-2-id]
TaskUpdate: Phase 4, addBlockedBy: [phase-3-id]
TaskUpdate: Phase 5, addBlockedBy: [phase-4-id]

Resume Logic (Same Session Only)

Before creating tasks, check TaskList for existing /today phase tasks:

  • If tasks exist with in_progress status → resume from that phase
  • If Phase 4 was completed → start Phase 5 (wrap-up)
  • If all phases completed or no tasks exist → start fresh from Phase 1

No persistent state files. The file system is the state — daily notes exist or they don't.


Phase 1: DAILY STANDUP (Interactive)

Purpose: Capture updates for all active projects.

Steps

  1. Read _core/config.yaml → get active projects list

  2. For each active project, prompt the user:

    {project_name}: What's your update? (shipped/wip/blocked)
  3. Parse each response using keyword detection (from /daily skill):

    • Shipped: shipped, done, completed, finished, merged, deployed, released
    • WIP: wip, working on, in progress, continuing, started, ongoing
    • Blocked: blocked, stuck, waiting on, waiting for, need from, dependency
    • Decided: decided, going with, chose, selected, agreed
  4. Create or update daily/{date}.md:

    • If file exists: update each project's ## {Project Name} section
    • If new: create from template with all project sections
  5. Auto-detect blockers (per /daily logic):

    • For each blocked item: search blockers/{project}/*.md for similar open blockers
    • If similar exists: link to it
    • If NEW: prompt user — "Blocker detected: '{text}'. Create blocker note? (y/n/details)"
      • y: Create with severity=medium at blockers/{project}/{date}-{slug}.md
      • details: Prompt for severity, owner, due date
      • n: Skip
  6. Auto-detect decisions:

    • For each decision keyword: suggest creating a decision note
    • Link to daily if user confirms

Output

✓ Updated daily/{date}.md ({count} projects)
  - Shipped: {count} items
  - WIP: {count} items
  - Blockers: {count} (linked/created)
  - Decisions: {count} (detected)

Phase 2: TEAM SYNC (Interactive)

Purpose: Process external context (Slack threads, Linear updates, meeting notes).

Steps

  1. Prompt the user:

    Any team updates, Slack threads, or meeting notes to process? (paste or 'skip')
  2. If skip → mark phase complete, advance to Phase 3

  3. If content provided:

    • Classify content type using keyword detection:
      • Meeting signals → route as meeting note (use /meet patterns)
      • Blocker signals → route as blocker
      • Decision signals → route as decision
      • General → route to inbox
    • Create appropriate notes with links
    • After processing, ask: "More to process? (paste or 'done')"
    • Loop until user says 'done' or 'skip'

Output

✓ Team sync complete
  - Meeting notes: {count}
  - Blockers: {count}
  - Items routed: {count}

Phase 3: REVIEW (Auto-generated, Read-only)

Purpose: Display a cross-project health dashboard. No files created.

Steps

  1. Scan vault and aggregate:

    • Open blockers: Glob blockers/{project}/*.md for each active project, read frontmatter for severity/due
    • Critical items: Blockers with due date < 2 days from today (per defaults.blocker_critical_days)
    • Active docs: Glob docs/{project}/*.md, filter status != shipped
    • Recent decisions: Glob decisions/{project}/*.md from last 3 days
  2. Display formatted dashboard to terminal:

┌─────────────────────────────────────┐
│  TODAY'S DASHBOARD — {date}         │
└─────────────────────────────────────┘

BLOCKERS (by severity)
  🔴 High ({count})
    • [{project}] {title} — due {date}

  🟡 Medium ({count})
    • [{project}] {title}

  🟢 Low ({count})
    • [{project}] {title}

  (None) — if no blockers exist

ACTIVE DOCS
  • [{project}] {title} — {status}

  (None) — if no active docs

RECENT DECISIONS (last 3 days)
  • [{project}] {title} — {date}

  (None) — if no recent decisions

Output

Dashboard displayed to terminal. No files created.


Phase 4: FOCUS (Display & Pause)

Purpose: Show priorities and let the user do deep work.

Steps

  1. Extract priorities from today's daily note:

    • Top 3 WIP items across all projects
    • Critical blockers to address (from Phase 3 data)
    • Pending decisions (if any detected)
  2. Display priority list:

TODAY'S PRIORITIES
━━━━━━━━━━━━━━━━━━━━━━━━

1. [{project}] {wip item}
2. [{project}] {wip item}
3. [{project}] {wip item}

⚠ NEEDS ATTENTION
  • {critical blocker or pending decision}

━━━━━━━━━━━━━━━━━━━━━━━━
Focus time — run /today again when ready to wrap up
  1. Mark Phase 4 as complete. Exit workflow. User returns when ready.

Phase 5: WRAP-UP (Auto-generated, Read-only)

Purpose: Summarize the day. No files created.

Steps

  1. Re-read today's daily note (daily/{date}.md)

  2. Scan for blockers created/resolved today

  3. Scan for decisions made today

  4. Display summary:

TODAY'S SUMMARY — {date}
━━━━━━━━━━━━━━━━━━━━━━━━

SHIPPED ({count})
  • [{project}] {item}

IN PROGRESS ({count})
  • [{project}] {item}

BLOCKERS
  Created: {count}
  Resolved: {count}

DECISIONS MADE ({count})
  • [{project}] {title}

━━━━━━━━━━━━━━━━━━━━━━━━
Run /push to commit today's updates

Edge Cases

  • No projects configured: Display error — "No active projects in config.yaml. Run /onboard to set up your first project."
  • Empty vault (no daily note): Create fresh daily note in Phase 1
  • No blockers/decisions/docs: Display "(None)" in dashboard sections
  • User exits mid-phase: Session tasks preserve progress for same-session resume
  • /today wrap with no daily note: Display message — "No daily note for today. Run /today to start your day first."

Graceful Degradation

  • Linear MCP not connected: Skip auto-fetch, continue with paste-only in Team Sync
  • QMD not available: Not needed (direct file scans only)
  • Obsidian not running: No impact (terminal-only output)

Integration

Works with:

  • /daily — Reuses keyword detection and blocker/decision logic
  • /meet — Routes meeting content in Team Sync phase
  • /progress — Similar dashboard pattern in Review phase
  • /push — Suggested at wrap-up for committing changes
  • /block — Blocker creation follows same patterns
  • /decide — Decision creation follows same patterns

Frequently asked questions

What does the Today AI skill do?

Guided daily workflow orchestrator. Multi-phase process (standup, team sync, review, focus, wrap-up). Use when user says "today", "start my day", or "daily workflow".

Why use Today on TypingMind?

Because you install it once and use it with any model. Today is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Today in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kv0906/pm-kit/tree/main/.claude/skills/today. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Today?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Today?

As many as you like. As long as a model supports skills, you can use Today with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Today AI skill free?

Yes. It is published on GitHub by kv0906 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇