agentleFS
KubementatKubementat/ai_agent_skills/skills/gtd-assistant/SKILL.md

gtd-assistant

Skill2 starsChanged 8 months agoMITView on GitHub

A GTD-style productivity assistant that combines open loop collection with intelligent brainstorming to generate actionable next steps, priorities, and refinement suggestions for your Obsidian vault.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When the quest-system briefing completes, it can offer:

    line 54
  2. Distinctive:

    Follow the three-pass workflow:

    line 62
  3. Distinctive:

    Consider context: time available, energy level, upcoming commitments

    line 111
  4. Distinctive:

    After presenting the unified report, offer these follow-up actions:

    line 187
  5. Distinctive:

    When the user asks for a focus session after the GTD report, produce:

    line 191
  6. Distinctive:

    Ask the user whether he wants to save the report.

    line 206

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

GTD Assistant

A unified productivity agent that doesn't just collect your open loops—it helps you make sense of them. By combining systematic data collection with embedded GTD analysis patterns, this assistant generates comprehensive reports with actionable recommendations tailored to personal productivity contexts.

What Makes This Different?

Traditional GTD tools tell you what's unfinished. The GTD Assistant tells you:

  • What to tackle first (context-aware priority suggestions)
  • What can be combined or eliminated (pattern recognition across loose ends)
  • What needs clarification before action (identifying vague items that need more thought)
  • How to convert ideas into actionable tasks (turning dangling thoughts into concrete steps)

Vault Configuration

SettingValue
Vault path$HOME/main_vault
Obsidian CLIAlways use obsidian

The vault layout follows the standard structure:

  • 00-Tasks/ — all task files organized by domain
  • Subfolders like Work/, Privat/, etc. for project-specific tasks

When to Use

Activate when the user says:

  • "Run a GTD sweep" / "Full GTD review"
  • "Help me understand my backlog"
  • "What's really unfinished in my vault?"
  • "Open loops sweep"
  • "Weekly review" / "Monthly review"
  • "I feel overwhelmed — what do I have open?"
  • "Deeper analysis" (after morning briefing)

Relationship to Other Skills

Captain's Log Integration (quest-system)

The GTD Assistant provides strategic, comprehensive analysis of all open loops in your vault. For daily tactical planning (what to focus on TODAY), use the quest-system skill (Captain's Log briefing — goal-first, with calendar and task collection):

# For deep dive: GTD assistant
gtd review / help me understand my backlog / open loops sweep

# For daily kickoff: quest-system Captain's Log
good morning / captain's log / what to focus on today?

When the quest-system briefing completes, it can offer:

  • "Deeper analysis?" — call gtd-assistant for comprehensive view including dangling thoughts and stub notes
  • "Weekly review?" — recommend full GTD sweep instead of daily briefing

Workflow Overview

Phase 1: Comprehensive Collection

Follow the three-pass workflow:

Pass 1 — Open Tasks

# Get total count
obsidian tasks todo total=true

# Get all open tasks grouped by file (JSON format for parsing)
obsidian tasks todo verbose=true format=json

Parse JSON output. Group tasks by domain:

  • Inbox / Urgent: files in 00-Tasks/
  • Work: files in Work/ or with #work tag
  • Music / Creative: files in 03-denkfabrik/ or tagged #music
  • House / Personal: 06 - Tasks - Haus, Privat/, etc.
  • Projects: everything else

Show top items per group (max 5–7 per group). Skip recurring tasks (🔁) in the main list — note them separately.

**Pass 2 — Dangling Thoughts **(keyword search)

obsidian search query="TODO" format=json limit=30
obsidian search query="idea" format=json limit=30
obsidian search query="later" format=json limit=20
obsidian search query="?" format=json limit=20

Filter out:

  • Files already in 00-Tasks/ (covered in Pass 1)
  • Files in copilot-conversations/, ZZ-Archiv/, Evernote Import/
  • Lyrics files (03-denkfabrik/Lyrics/)

Present as a deduplicated list of notes with dangling content. For each, read a snippet to show what is dangling.

**Pass 3 — Stub Notes **(incomplete / abandoned)

# Run the stub collection script
bash skills/obsidian-open-loops-collector/scripts/collect_stubs.sh $HOME/main_vault

This returns lines like: 3\tSome Note.md (line count, filename).

Group stubs by folder/domain. Highlight any stubs that look like project or idea notes (not just reference stubs). Read the content of interesting-looking ones.

Phase 2: GTD Analysis Workflow

Apply the following analysis patterns directly to the collected data:

Priority Assessment

Given [X] open tasks, [Y] dangling thoughts, and [Z] stub notes across domains like work, music production, house maintenance, and personal projects:

  • Identify 3–5 concrete next actions that would give the highest satisfaction return
  • Consider context: time available, energy level, upcoming commitments
  • Factor in urgency (deadlines visible in task descriptions)
  • Balance quick wins with meaningful challenges based on user's stated goals

Phase 3: Unified Report Generation

Present a structured output that combines both perspectives:

## 📊 GTD Assistant Report — [Date]

---

### 🎯 Quick Summary
- **[N] Open Tasks** across [M] domains
- **[P] Dangling Thoughts** in [Q] notes  
- **[R] Stub Notes** requiring attention

---

### 🔥 Suggested First Actions (Top 3-5)

Based on context, urgency, and effort assessment:

1. **Action Item** — *Why:* [brief reasoning]
   - Related to: [domain/file]
   - Estimated effort: [Quick/Medium/Long]
   - Context needed: [work/home/focus time/etc.]

2. ...

---

### 📋 Full Breakdown

#### Open Tasks by Domain
[Grouped list with counts and highlights]

#### Dangling Thoughts
[Notes containing TODOs, ideas, later items, questions]

#### Stub Notes
[Incomplete notes with line counts and recommendations]

---

### 💡 GTD Analysis Insights

**Consolidation Opportunities:**
- Identify tasks that could be combined into single actions
- Flag items suitable for delegation or elimination
- Suggest breaking down complex items into smaller sub-tasks
- Mark items appropriate for intentional deferral

**Clarification Needed:**
- Highlight vague or incomplete open loops
- Suggest specific questions to make each item actionable

**Pattern Recognition:**
- Identify recurring themes across domains
- Note areas with unusually high accumulation
- Surface potential bottlenecks (e.g., too many pending reviews, unprocessed inbox items)

---

### 🛠️ Available Actions

1. **"Dive in"** — Read any specific note in full
2. **"Close it"** — Mark tasks as done, move notes to archive
3. **"Capture it"** — Turn a dangling thought into a proper task
4. **"Save report"** — Write the report as a vault note
5. **"Focus session"** — Generate a focused 25-min task list from top priorities

Interaction Patterns

After presenting the unified report, offer these follow-up actions:

Focus Session Generator

When the user asks for a focus session after the GTD report, produce:

  • One concrete next step to start immediately
  • Estimated time: 25 minutes (one Pomodoro)
  • Context needs: tools, environment, prerequisite info

Format:

"Your next 25 minutes: [specific action] in [file/tool]. Start by [first micro-step]."

Task Creation from Ideas

obsidian create name="Task: [Description]" content="[task details]"

Report Saving (Optional)

Ask the user whether he wants to save the report.

obsidian create name="GTD Report — $(date +%Y-%m-%d)" content="[full report markdown]"

Example Usage

Initial Request:

"Run a full GTD sweep and give me actionable next steps."

Follow-up Options the User Can Ask:

  • "What's the quickest thing I can complete right now?"
  • "Can you break down that big project task into smaller steps?"
  • "Which of these are actually urgent vs. just important?"
  • "Generate a focus session plan for my next 25 minutes"
  • "Save this report to my vault so I can reference it later"

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.