linkwarden
Skill6 starsChanged 3 months agoApache-2.0View on GitHub
Manage a Linkwarden instance through its official HTTP API: check configuration, search and inspect bookmarks, collections, tags and highlights, and perform controlled link, collection or tag changes with explicit confirmation for destructive actions.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- Alpha-Park/openclaw-skillstheir own version, first seen Mar 22, 2026
- alphaparkinc/openclaw-skillstheir own version, first seen Mar 22, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- alphaparkinc/openclaw-skills★ 9same name
- Alpha-Park/openclaw-skills★ 8same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository27 other files it gives its agents.
- baidu-netdiskSkill
- barkSkill
- cloudsaverSkill
- code-debriefSkill
- codex-usageSkill
- desktopSkill
- douban-marksSkill
- douyin-hotSkill
- find-skills-skillSkill
- grill-meSkill
- grok-quotaSkill
- meituan-coupon-assistantSkill
- multi-agent-orchestrationSkill
- ntfySkill
- openlistSkill
- personal-dev-guardSkill
- poke-apiSkill
- qinglongSkill
- rsshubSkill
- spotify-web-apiSkill
- telegram-officialSkill
- triliumSkill
- vaultwarden-cliSkill
- vitapulseSkill
- volcengine-ark-quotaSkill
- wallosSkill
- weread-skillsSkill
The file
Files
Linkwarden Skill
通过 Linkwarden 官方 HTTP API 查询和管理书签、集合、标签与高亮。Skill 使用 Bearer Token,只依赖 Python 标准库,不包含 Linkwarden 源码或服务端组件。
适用场景
使用本 Skill 处理:
- 检查 Linkwarden 实例版本、连通性和鉴权配置;
- 搜索书签,按集合、标签、置顶状态筛选;
- 查看书签详情、归档状态和高亮;
- 创建或修改书签;
- 查看、创建或修改集合;
- 查询标签;
- 在明确确认后删除书签、集合或标签,以及重新生成归档。
不要使用本 Skill 处理用户注册、密码重置、管理员用户管理、文件上传、Token 创建/吊销、批量删除或任意 API 透传。这些能力不属于当前安全边界。
环境变量
| 变量 | 类型 | 必填 | 说明 |
LINKWARDEN_URL | config | 是 | Linkwarden 实例根地址,例如 https://links.example.com |
LINKWARDEN_TOKEN | secret | 是* | API Bearer Token;除公开状态检查外均必填 |
LINKWARDEN_INSECURE_TLS | config | 否 | 仅自签名证书调试时设为 1;会跳过 TLS 证书校验 |
环境变量缺失时,脚本返回结构化错误,不会尝试读取浏览器 Cookie、配置文件或宿主私有目录。
安全约束
- 服务地址只允许
http或https,禁止在 URL 中嵌入用户名、密码、查询参数或片段。 - Token 只从当前进程环境读取,不通过参数传递,也不会出现在输出和错误信息中。
- 查询统一使用
/api/v1/search;不使用已废弃的GET /api/v1/links。 - 修改书签或集合前先读取当前对象,再构造 Linkwarden 要求的完整请求体,避免未提供字段被意外清空。
delete-link、delete-collection、delete-tag和rearchive-link必须收到confirm: true。- 删除集合还必须提供与当前集合名称完全一致的
confirm_name。 - 删除标签还必须提供与当前标签名称完全一致的
confirm_name,以及与当前关联书签数量完全一致的confirm_link_count。 rearchive-link会删除现有归档文件并触发重新归档,属于有数据影响的操作。- 不开放批量操作和任意路径请求,避免扩大误操作范围。
执行方式
在 Skill 包根目录运行:
printf '%s' '{"skill_action":"status"}' | python3 run.py输入必须是 JSON 对象,动作字段为 skill_action。输出始终为 JSON;HTTP 响应保持在 response 字段中。
动作
| 动作 | 类型 | 主要输入 | 说明 |
status | 只读 | 无 | 检查环境配置;已配置 URL 时调用公开 /api/v1/config |
search | 只读 | query?, sort?, cursor?, collection_id?, tag_id?, pinned_only? | 搜索或分页读取书签 |
get-link | 只读 | id | 获取单条书签完整信息 |
get-highlights | 只读 | id | 获取书签高亮 |
create-link | 写入 | url, name?, description?, collection_id? 或 collection_name?, tags? | 创建 URL 书签 |
update-link | 写入 | id 以及需要修改的字段 | 读取现状后合并更新;支持名称、URL、描述、样式、集合、标签和置顶用户 ID |
rearchive-link | 破坏性写入 | id, confirm: true | 清除当前归档并触发重新归档 |
delete-link | 删除 | id, confirm: true | 删除单条书签 |
list-collections | 只读 | 无 | 获取当前用户可访问的集合 |
get-collection | 只读 | id | 获取集合详情 |
create-collection | 写入 | name, description?, color?, icon?, icon_weight?, parent_id? | 创建集合或子集合 |
update-collection | 写入 | id 以及需要修改的字段 | 读取现状并保留成员关系后更新 |
delete-collection | 删除 | id, confirm: true, confirm_name | 名称匹配后删除集合 |
list-tags | 只读 | search?, sort?, cursor? | 查询标签,默认按名称升序 |
delete-tag | 删除 | id, confirm: true, confirm_name, confirm_link_count | 名称与当前关联数量均匹配后删除单个标签 |
tags 推荐传字符串数组:
{
"skill_action": "create-link",
"url": "https://example.com",
"collection_id": 42,
"tags": ["reference", "ai"]
}修改书签时只提供需要变化的字段:
{
"skill_action": "update-link",
"id": 101,
"name": "新的标题",
"tags": ["reference", "reviewed"]
}脚本会先读取书签 101,保留未指定字段,再提交 Linkwarden 所需的完整更新对象。
删除标签前必须确认当前名称和影响数量:
{
"skill_action": "delete-tag",
"id": 77,
"confirm": true,
"confirm_name": "legacy-tag",
"confirm_link_count": 0
}脚本会先读取标签 77;只要名称或关联数量已经变化,就拒绝删除。
操作流程
- 首次使用先执行
status,确认 URL、Token 和实例连通性。 - 涉及集合或标签名称时,先用
list-collections或list-tags解析真实 ID。 - 更新和删除前读取目标对象并向用户复述关键字段;删除标签时还要复述当前关联书签数量。
- 写操作完成后再次读取目标对象,验证最终状态。
- HTTP 失败时返回状态码、端点和服务端响应;不要用猜测替代真实失败证据。
接口和字段依据见 references/api.md。
AgentDock 适配
在 AgentDock 中,把环境值配置到该 Skill 的独立环境,再通过绑定当前激活 Skill 的命令执行能力运行 python3 run.py。不要手工拼接已安装版本目录,也不要把真实 Token 写入 Skill 包、源码仓库或 Recall。
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
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.

