gtd
1
总安装量
1
周安装量
#51928
全站排名
安装命令
npx skills add https://github.com/majiayu000/claude-skill-registry --skill gtd
Agent 安装分布
replit
1
amp
1
trae-cn
1
opencode
1
kimi-cli
1
codex
1
Skill 文档
GTD Runner Skill
Autonomous task execution from GTD.md items.
Trigger
- Command:
/cyber-gtd - Default: plan-first (show before execute)
Workflow
- Read
@GTD.mdâ extract items from# Next - For each item:
- Classify â match pattern to workflow
- Lookup entities via database:
bun scripts/db/query.ts find-entity "<name>" - Plan actions
- Show plan â ask to execute
- Execute approved items sequentially (one at a time)
- Output:
~/CybosVault/private/content/work/MMDD-<slug>.md
Classification â Routing
| Pattern | Confidence | Workflow |
|---|---|---|
| “ask for call”, “message”, “email”, “reach out” | High | â workflows/outreach.md |
| “call with”, “meeting”, “X <> Y”, “sync” | High | â workflows/call-prep.md |
| “podcast” | High | â workflows/podcast.md |
| company name, “research”, “DD”, “look into” | Medium | â workflows/research.md |
| no match | Low | Best judgment â log to learnings.md |
Entity Lookup
Query database for entity context:
- Parse item for names (people, companies)
- Run:
bun scripts/db/query.ts find-entity "<name>" --json - If found, get full context:
bun scripts/db/query.ts entity <slug> --json - Entity context includes:
- Recent interactions (calls, emails, telegram)
- Deal associations
- Pending items
- If not found + confident it’s an entity:
- High confidence (company with domain) â auto-create stub
- Medium confidence â 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@example.com
- [ ] 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.