用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/duclm1x1/Dive-Ai --skill vikunja-fast命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
正在显示 SKILL.md
基于 SOC 职业分类
| name | vikunja-fast |
| description | Manage Vikunja projects and tasks (overdue/due/today), mark done, and get quick summaries via the Vikunja API. |
| homepage | https://vikunja.io/ |
| metadata | {"clawdbot":{"emoji":"📋","requires":{"bins":["curl","jq"],"env":["VIKUNJA_URL"],"optionalEnv":["VIKUNJA_TOKEN","VIKUNJA_USERNAME","VIKUNJA_PASSWORD"]},"primaryEnv":"VIKUNJA_TOKEN"}} |
Use Vikunja as the source of truth for tasks and completions, and interact with it from Clawdbot.
You can provide credentials either via environment variables or via Clawdbot’s skills config.
Set these environment variables in the same environment where the gateway runs:
export VIKUNJA_URL="https://vikunja.xyz"
# Recommended: use a JWT (starts with "eyJ")
export VIKUNJA_TOKEN="<jwt>"
# Alternative: login with username/password (the helper CLI will request a JWT)
export VIKUNJA_USERNAME="<username>"
export VIKUNJA_PASSWORD="<password>"
Edit ~/.clawdbot/clawdbot.json:
{
skills: {
entries: {
"vikunja-fast": {
enabled: true,
env: {
VIKUNJA_URL: "https://vikunja.xyz",
VIKUNJA_TOKEN: "<jwt>"
}
}
}
}
}
Notes:
VIKUNJA_URL can be the base URL; the helper normalizes to /api/v1.Authorization: Bearer <jwt>).tk_...), use /login to obtain a JWT.curl -fsS -X POST "$VIKUNJA_URL/login" \
-H "Content-Type: application/json" \
-d '{"username":"YOUR_USERNAME","password":"YOUR_PASSWORD","long_token":true}' | jq
curl -fsS "$VIKUNJA_URL/user" \
-H "Authorization: Bearer $VIKUNJA_TOKEN" | jq
curl -fsS "$VIKUNJA_URL/projects" \
-H "Authorization: Bearer $VIKUNJA_TOKEN" | jq '.[] | {id, title}'
This skill ships with a tiny helper CLI:
{baseDir}/vikunja.shExamples:
# Overdue across all projects
{baseDir}/vikunja.sh overdue
# Due today
{baseDir}/vikunja.sh due-today
# Arbitrary filter (Vikunja filter syntax)
{baseDir}/vikunja.sh list --filter 'done = false && due_date < now'
# Show / complete a task
{baseDir}/vikunja.sh show 123
{baseDir}/vikunja.sh done 123
Notes:
<EMOJI> <DUE_DATE> - #<ID> <TASK>🔨Mon/D (time + year removed)GET /tasks/all to fetch tasks across all projectsTASK_ID=123
curl -fsS -X POST "$VIKUNJA_URL/tasks/$TASK_ID" \
-H "Authorization: Bearer $VIKUNJA_TOKEN" \
-H "Content-Type: application/json" \
-d '{"done": true}' | jq