Automatically executes tasks listed in your GTD.md file, including research, meeting prep, and outreach flows.

Install

mkdir -p .claude/skills/gtd && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11871" && unzip -o skill.zip -d .claude/skills/gtd && rm skill.zip

Installs to .claude/skills/gtd

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Autonomous task execution from GTD.md items. Use when processing GTD tasks, call prep, outreach, or podcast preparation.
120 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Extract tasks from GTD.md
  • Classify tasks to match workflows
  • Look up entities via a database for context
  • Plan and execute actions for approved items

How it works

The skill reads tasks from GTD.md, classifies them, queries a database for entity context, plans actions, and then executes approved items sequentially.

Inputs & outputs

You give it
Items from GTD.md under '# Next'
You get back
Structured markdown files in `~/CybosVault/private/content/work/MMDD-<slug>.md`

When to use gtd

  • Process pending GTD tasks
  • Prepare for upcoming meetings
  • Perform research on new entities
  • Automate outreach communications

About this skill

GTD Runner Skill

Autonomous task execution from GTD.md items.

Trigger

  • Command: /cyber-gtd
  • Default: plan-first (show before execute)

Workflow

  1. Read @GTD.md → extract items from # Next
  2. For each item:
    • Classify → match pattern to workflow
    • Lookup entities via database: bun scripts/db/query.ts find-entity "<name>"
    • Plan actions
  3. Show plan → ask to execute
  4. Execute approved items sequentially (one at a time)
  5. Output: ~/CybosVault/private/content/work/MMDD-<slug>.md

Classification → Routing

PatternConfidenceWorkflow
"ask for call", "message", "email", "reach out"High→ workflows/outreach.md
"call with", "meeting", "X <> Y", "sync"High→ workflows/call-prep.md
"podcast"High→ workflows/podcast.md
company name, "research", "DD", "look into"Medium→ workflows/research.md
no matchLowBest judgment → log to learnings.md

Entity Lookup

Query database for entity context:

  1. Parse item for names (people, companies)
  2. Run: bun scripts/db/query.ts find-entity "<name>" --json
  3. If found, get full context: bun scripts/db/query.ts entity <slug> --json
  4. Entity context includes:
    • Recent interactions (calls, emails, telegram)
    • Deal associations
    • Pending items
  5. If not found + confident it's an entity:
    • High confidence (company with domain) → auto-create stub
    • Medium confidence → ask: "Create entity file for X?"

Output Format

All outputs to ~/CybosVault/private/content/work/MMDD-<slug>.md:

# Task: [Task Description]

**Status:** Pending Approval | Completed | Incomplete
**Created:** YYYY-MM-DD HH:MM
**GTD Item:** [Original text from GTD.md]
**Workflow:** [Which workflow handled this]

---

## Context

**Entity:** [Name]
- Type: [person/org]
- Deal: [link if exists]
- Previous calls: [N calls found]

**Key Info:**
[Relevant context from calls, deals, entity files]

---

## Draft

[Message/agenda/questions/etc]

---

## Pending Actions

- [ ] Send via Gmail to [email protected]
- [ ] Alternative: Telegram @handle

---

## Execution Log

- HH:MM - [action taken]

Staged Execution

Agent completes what it can autonomously:

  • Research and context gathering
  • Draft creation
  • Preparation work

Then queues actions requiring approval:

  • Sending messages (Gmail, Telegram)
  • Scheduling meetings
  • Any external action

Suggestions

When processing tasks, if you notice 3+ similar patterns that don't have a dedicated workflow, suggest: "I've seen '[pattern]' multiple times. Want me to create a workflow for it?"

Self-Improvement

Log all task executions to @learnings.md for pattern analysis.

When not to use it

  • When tasks do not originate from GTD.md
  • When entity lookup is not required
  • When manual execution of all steps is preferred

Limitations

  • Tasks must be extracted from GTD.md under '# Next'.
  • Entity lookup relies on a specific database script.
  • Execution of items requires user approval.

How it compares

This skill automates the entire GTD task processing workflow, including classification, entity lookup, and structured output generation, which is more efficient than manual task management.

Compared to similar skills

gtd side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
gtd (this skill)06moNo flagsIntermediate
notion-knowledge-capture109moNo flagsIntermediate
slack-memory-store15moReviewIntermediate
diary03moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

notion-knowledge-capture

makenotion

Transforms conversations and discussions into structured documentation pages in Notion. Captures insights, decisions, and knowledge from chat context, formats appropriately, and saves to wikis or databases with proper organization and linking for easy discovery.

10115

slack-memory-store

krafton-ai

Comprehensive memory storage system for AI employees in IT companies who communicate via Slack. Automatically classifies and stores diverse information types (Slack messages, Confluence docs, emails, meetings, projects, decisions, feedback) in an organized folder structure with efficient indexing and retrieval. Use when managing or searching employee memory, storing conversations, documenting decisions, tracking projects, or organizing any work-related information.

13

diary

Anhvu1107

ALWAYS use this when the request matches Diary: Unified Diary System: A context-preserving automated logger for multi-project development.

00

session-review

philoserf

Wraps up a session with two outputs — a sweep into the auto-memory system to preserve reusable insights for future Claude sessions, and a human-readable recap saved to the Obsidian notes vault. Use for retrospectives, debriefs, post-mortems, or end-of-session reflection.

00

nextcloud-cli-deck

NicholaiVogel

Work with the Nextcloud Deck app through Nextcloud CLI. Use when an agent needs to list boards and cards, create boards or stacks, create or update cards, move cards, archive or delete cards safely, validate Deck availability, or perform dry-run protected project-board workflows with nxc.

00

notion-pilot

1000ssam

Notion API 통합 스킬. DB/페이지/블록 CRUD, 마크다운 읽기/쓰기, 파일 업로드, 이미지 커버 설정, upsert, 코멘트, 페이지 이동 등 모든 Notion 작업을 notion-api.mjs 모듈로 처리합니다. Use when: (1) 노션에 추가/수정/조회, (2) 노션 DB 생성, (3) 노션 이미지 업로드, (4) 노션 커버 설정, (5) 노션 파일 업로드, (6) Notion API 작업. 트리거: '노션', 'Notion', '노션에', '노션 DB', '노션 페이지', '노션 업로드'.

00

Search skills

Search the agent skills registry