Agent skill

Secondme

by LeoYeAI in LeoYeAI/openclaw-master-skills

A skill your agent uses when the user wants to log in to SecondMe from OpenClaw, re-login, logout, get the auth URL, manage their SecondMe profile, use Plaza, redeem an invitation code, browse…

MITAuto-check passedBackend & APIs

Install Secondme

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill secondme -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills secondme --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mindverse-secondme .claude/skills/secondme && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
secondme
GitHub stars
2.2k
Token cost
~4k tokens
SKILL.md length
1,596 words
Files
2
Skills in repo
972
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user wants to log in to SecondMe from OpenClaw, re-login, logout, get the auth URL, manage their SecondMe profile, use Plaza, redeem an invitation code, browse…

  • Works in 4 steps: Read {baseDir}/.credentials → If it contains valid JSON with… → If it only contains legacy access_token,… → …
  • The user wants to log in to SecondMe from OpenClaw
  • SKILL.md covers Shared Authentication Rules, Connect, Profile and Plaza, plus 4 more sections
  • Reaches second-me.cn and cdn.second-me.cn

What it does

Secondme is an agent skill from LeoYeAI/openclaw-master-skills. Use when the user wants to log in to SecondMe from OpenClaw, re-login, logout, get the auth URL, manage their SecondMe profile, use Plaza, redeem an invitation code, browse discover users, use SecondMe Key Memory, create or search SecondMe notes, or view SecondMe activity and day overview

Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `_meta.json`).

It sits in Backend & APIs, covering Authentication. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

When your agent uses it

  • The user wants to log in to SecondMe from OpenClaw
  • Get the auth URL
  • Manage their SecondMe profile
  • Redeem an invitation code

Example prompts

  • “/secondme”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Read {baseDir}/.credentials
  2. If it contains valid JSON with accessToken, continue
  3. If it only contains legacy access_token, continue, but normalize future writes to accessToken
  4. If the file is missing, empty, or invalid, start the login flow in this same skill

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • second-me.cn
    • cdn.second-me.cn
    • plaza.second-me.cn

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Secondme loads about 4k tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 1,596 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~75
When it runs · the whole SKILL.md, loaded when a task matches
~4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 1,596 words, ~4,011 tokens.

Download SKILL.mdSave it as .claude/skills/secondme/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
secondme
description
Use when the user wants to log in to SecondMe from OpenClaw, re-login, logout, get the auth URL, manage their SecondMe profile, use Plaza, redeem an invitation code, browse discover users, use SecondMe Key Memory, create or search SecondMe notes, or view SecondMe activity and day overview
user-invocable
true

SecondMe OpenClaw

This skill owns the normal SecondMe user workflow in OpenClaw:

  • login, logout, re-login, and token storage
  • profile read and update
  • Plaza activation, invitation redeem, posting, post details, and comments
  • discover user browsing
  • explicit SecondMe Key Memory operations
  • notes creation and search
  • activity and day overview queries

Credentials file: {baseDir}/.credentials

Shared Authentication Rules

Before any authenticated SecondMe operation:

  1. Read {baseDir}/.credentials
  2. If it contains valid JSON with accessToken, continue
  3. If it only contains legacy access_token, continue, but normalize future writes to accessToken
  4. If the file is missing, empty, or invalid, start the login flow in this same skill

Use the resulting accessToken as the Bearer token for all authenticated requests below.

Connect

This section owns login, logout, re-login, token exchange, and token persistence.

If the user says things like 登录 SecondMe, 登入second me, 登陆 secondme, login second me, 连上 SecondMe, or asks for the auth/login URL, immediately handle the login flow and give the browser auth address when credentials are missing.

If the user is invoking this skill for the first time in the conversation and does not give a clear task, first introduce what the skill can do, then make it clear that all of those actions require login before use, then continue into the login flow.

Use a short introduction like:

我可以帮你在 OpenClaw 里用 SecondMe 做这些事:

  • 看和改个人资料
  • 发 Plaza、看帖子和评论
  • 看推荐用户
  • 写和查 Key Memory
  • 创建和搜索 Notes
  • 看今天的 Activity

这些能力都要先登录才能用。我先带你登录,登录完再继续带你看资料这些常用操作。

If the user has already given a clear task such as viewing profile, posting, searching notes, or checking activity, do not give the generic capability introduction. Follow the user's request directly and only do the minimum required login prerequisite if they are not authenticated.

Logout / Re-login

When the user says 退出登录, 重新登录, logout, re-login, or wants to switch account:

  1. Delete {baseDir}/.credentials
  2. Tell: 已退出登录,下次用的时候重新登录就行。
  3. If re-login was requested, continue with the login flow below
Login Flow

If credentials are missing or invalid, mark this as firstTimeLocalConnect = true.

Tell the user to open this page in a browser, and output the URL as a bare URL. Do not wrap the login URL in backticks, code fences, or markdown link syntax. Output only the raw URL on its own line:

https://second-me.cn/third-party-agent/auth

Tell the user:

你还没有登录 SecondMe,点这个链接登录一下:

https://second-me.cn/third-party-agent/auth

登录完把页面上的授权码发给我,格式像 smc-xxxxxxxxxxxx。

Notes:

  • This page handles SecondMe Web login or registration first
  • If no redirect parameter is provided, the page shows the authorization code directly
  • The code is valid for 5 minutes and single-use

Then STOP and wait for the user to reply with the authorization code.

Exchange Code For Token

When the user sends smc-...:

POST https://app.mindos.com/gate/in/rest/third-party-agent/v1/auth/token/code
Content-Type: application/json
Body: {"code": "<smc-...>"}

Rules:

  • Verify response.code == 0
  • Verify response.data.accessToken exists
  • sm-... is the token used by all other SecondMe OpenClaw flows

After success:

  1. Write {baseDir}/.credentials, for example:
    json
    {
     "accessToken": "<data.accessToken>",
     "tokenType": "<data.tokenType>"
    }

Tell the user:

  • 登录成功,token 已保存。想体验更多 AI 社交相关操作,也可以登录主站 https://second-me.cn/ 或使用 SecondMe App。
First-Login Soft Onboarding

Only run this section if firstTimeLocalConnect = true.

After the success message, offer an optional guided path:

这是你第一次在 OpenClaw 里连上 SecondMe。

如果你愿意,我建议先这样试一遍:

  • 先看一下资料,我帮你补好基本信息
  • 再发一个 Plaza 帖子
  • 然后我帮你看看感兴趣的人

你也可以不按这个来。可以问问别的,或者告诉我你接下来想做什么。

If the user says 好、来吧、先看资料, or otherwise accepts the suggested path, continue with the profile section below.

If the user asks to do something else, or ignores the suggestion and gives a direct task, stop this onboarding immediately and follow their chosen path instead.

Do not repeat this onboarding sequence again in the same conversation once the user has declined or diverged.

Optional: Generate Code From Existing Web Session

There is also:

POST https://app.mindos.com/gate/in/rest/third-party-agent/v1/auth/code

This requires an existing SecondMe Web login session, not an sm-... token. In the normal OpenClaw flow, prefer the browser page above.

Profile

Read Profile
GET https://app.mindos.com/gate/in/rest/third-party-agent/v1/profile
Authorization: Bearer <accessToken>

Useful fields:

  • name
  • avatar
  • aboutMe
  • originRoute
  • homepage
Guided Profile Setup

After reading the profile, treat setup as required if any of these fields are missing or blank:

  • name
  • aboutMe
  • originRoute

If all key fields are present, confirm briefly:

我先帮你看了下资料:

  • 姓名:{name}
  • 简介:{aboutMe}
  • 路由:{originRoute}

没问题我就继续;如果想改,可以直接告诉我怎么改。

If any key field is missing, or the user wants to edit their profile, draft an update first.

Draft using:

  • current profile values
  • any stable information already known from the conversation
  • fallback aboutMe: SecondMe 新用户,期待认识大家

Present:

你的 SecondMe 资料我先帮你拟了一版:

  • 姓名:{name}
  • 自我介绍:{aboutMe}
  • 路由:{originRoute}
  • 头像:{保留当前头像 / 默认头像}

没问题就说「好」;如果想改,可以直接告诉我怎么改。

Then wait for confirmation or edits.

Update Profile

Update only the fields the user wants changed:

PUT https://app.mindos.com/gate/in/rest/third-party-agent/v1/profile
Content-Type: application/json
Authorization: Bearer <accessToken>
Body: {
 "name": "<optional>",
 "avatar": "<optional>",
 "aboutMe": "<optional>",
 "originRoute": "<optional>"
}

Rules:

  • Omit any field the user did not ask to change
  • Only send avatar if the user explicitly provides a new avatar URL or asks to clear or replace it
  • If the user just says 好, send the drafted values for the missing or edited fields

After success:

  • Show the latest profile summary
  • Update {baseDir}/.credentials with useful returned fields such as name, homepage, and originRoute
Optional First-Run Handoff

If the user appears to be following the first-login guided path and has just completed or confirmed their profile setup, offer Plaza as the next optional step:

资料这边差不多了。下一步你可以先发个 Plaza 帖子,让别人更容易认识你。

如果你想继续,我帮你走下一步;你也可以问问别的,或者告诉我你接下来想做什么。

If the user accepts, continue with the Plaza section below.

If the user asks for something else, stop the guided path immediately and follow their chosen request.

Plaza

Plaza Gate

Plaza read/write access is gated by town invitation activation.

Before ANY Plaza operation, including:

  • posting
  • viewing post details
  • viewing comments

always check access first:

GET https://app.mindos.com/gate/in/rest/third-party-agent/v1/plaza/access
Authorization: Bearer <accessToken>

Key fields:

  • activated
  • certificateNumber
  • issuedAt

If activated=true, the user can use Plaza post/detail/comment APIs.

If activated=false:

  • do not call Plaza post/detail/comment APIs yet
  • explain that Plaza needs town invitation activation first
  • ask the user for an invitation code
  • redeem it
  • after redeem succeeds, call /plaza/access again
  • only continue when activated=true

Recommended user guidance when not activated:

你现在还没激活 Plaza,我先帮你把状态查过了。发帖、看帖子详情、看评论都要先用邀请码激活。

你把邀请码发我,我先帮你核销;核销成功后我再继续。

如果你手上还没有邀请码,可以先:

  • 通过社媒问其他人要一个
  • 邀请两个新用户完成注册,之后再来解锁

If the user enters Plaza from a generic request like 看看 Plaza or 我想发帖, proactively run /plaza/access first instead of waiting for a downstream failure.

Show full SKILL.md (662 more words)Show less
Redeem Invitation Code
POST https://app.mindos.com/gate/in/rest/third-party-agent/v1/plaza/invitation/redeem
Content-Type: application/json
Authorization: Bearer <accessToken>
Body: {
 "code": "<invitation code>"
}

Success fields:

  • code
  • inviterUserId
  • message
  • certificateIssued
  • certificateNumber

Common failure subCode values:

  • invitation.code.not_found
  • invitation.code.already_used
  • invitation.code.self_redeem
  • invitation.redeem.rate_limited

If redeem fails, explain the reason clearly, ask for a different code or a later retry, and remind the user they can also get a code by asking others on social media or by inviting two new users to complete registration.

After redeem succeeds, call:

GET https://app.mindos.com/gate/in/rest/third-party-agent/v1/plaza/access
Authorization: Bearer <accessToken>

Only unlock Plaza actions when activated=true.

Publish Plaza Post

If access is active, help the user draft a concise post first:

我先帮你拟一版,没问题我就发: {draft_content}

Minimal create request:

POST https://app.mindos.com/gate/in/rest/third-party-agent/v1/plaza/posts
Content-Type: application/json
Authorization: Bearer <accessToken>
Body: {
 "content": "<required>",
 "type": "public",
 "contentType": "discussion"
}

Optional documented fields include:

  • topicId
  • topicTitle
  • topicDescription
  • images
  • videoUrl
  • videoThumbnailUrl
  • videoDurationMs
  • link
  • linkMeta
  • stickers
  • isNotification
  • appSourceId
  • recruitCount
  • callbackUrl

If the user is not activated, the backend may return:

  • code: 1
  • subCode: third.party.agent.plaza.invitation.required
  • message: Redeem a town invitation code before viewing or creating plaza posts.

After publish succeeds:

  • Read the created post's postId from the response
  • Build the post link as https://plaza.second-me.cn/post/{postId}
  • Do not use the user's homepage or profile link as the post link
  • If postId is missing, say clearly that the post was published but the post link is currently unavailable
Post Details And Comments

Post details:

GET https://app.mindos.com/gate/in/rest/third-party-agent/v1/plaza/posts/{postId}
Authorization: Bearer <accessToken>

Comments page:

GET https://app.mindos.com/gate/in/rest/third-party-agent/v1/plaza/posts/{postId}/comments?page=1&pageSize=20
Authorization: Bearer <accessToken>

Both endpoints require activated=true; otherwise they may return third.party.agent.plaza.invitation.required.

Optional First-Run Handoff

If the user appears to be following the first-login guided path and has just finished a Plaza step such as activation or posting, offer discover as the next optional step:

这一步已经好了。接下来我可以帮你看看有没有你可能感兴趣的人。

如果你想继续,我就走 discover;你也可以问问别的,或者告诉我你接下来想做什么。

If the user accepts, continue with the discover section below.

If the user asks for something else, stop the guided path immediately and follow their chosen request.

Discover

This API supports discover-style browsing, not free-text semantic people search.

discover/users may respond slowly. When calling it:

  • If the caller supports a configurable timeout or wait window, set it to at least 60s for this request
  • Do not treat the request as failed before that wait window expires
  • If the first attempt ends with a clear timeout or transient network timeout, retry once before surfacing failure
  • If the caller has a hard timeout below 60s, explain that the failure is likely caused by the runtime timeout rather than invalid discover parameters

Use:

GET https://app.mindos.com/gate/in/rest/third-party-agent/v1/discover/users?pageNo=1&pageSize=20
Authorization: Bearer <accessToken>

Optional query params:

  • longitude
  • latitude
  • circleType

Present useful fields such as:

  • username
  • distance
  • route
  • matchScore
  • title
  • hook
  • briefIntroduction

When presenting recommended users:

  • Always include a personal homepage link for each user
  • Build that homepage as https://second-me.cn/{route}
  • Do not show only the raw route
  • If route is missing or blank, say clearly that the user's homepage is currently unavailable

If the user asks for highly specific semantic matching, explain that the current interface is discover-style browsing rather than free-text people search.

Key Memory

This section is only for explicit SecondMe Key Memory operations.

If the user only says generic 记忆, memory, 你记得吗, or 查我的记忆, do not assume they mean this skill. That wording may refer to OpenClaw local memory.

If ambiguous, ask:

你要查 OpenClaw 本地记忆,还是 SecondMe 的 Key Memory?

Insert Key Memory

Direct mode:

POST https://app.mindos.com/gate/in/rest/third-party-agent/v1/memories/key
Content-Type: application/json
Authorization: Bearer <accessToken>
Body: {
 "mode": "direct",
 "content": "<memory content>",
 "visibility": 1
}

Extraction mode:

json
{
 "mode": "extract",
 "content": "<source content>",
 "context": "<optional>",
 "source": "<required>",
 "sourceId": "<required>"
}

Use Key Memory for durable facts like:

  • user preferences
  • stable biographical facts
  • durable relationship/context facts
Search Key Memory
GET https://app.mindos.com/gate/in/rest/third-party-agent/v1/memories/key/search?keyword=<keyword>&pageNo=1&pageSize=20
Authorization: Bearer <accessToken>

Common response fields:

  • list
  • total

Useful item fields:

  • factActor
  • factObject
  • factContent
  • createTime
  • updateTime
  • visibility

Do not merge OpenClaw local memory results with SecondMe Key Memory results unless the user explicitly asks for both.

Notes

Create Note
POST https://app.mindos.com/gate/in/rest/third-party-agent/v1/notes
Content-Type: application/json
Authorization: Bearer <accessToken>
Body: {
 "title": "<optional>",
 "content": "<optional by type>",
 "memoryType": "TEXT",
 "urls": ["<optional by type>"],
 "audioLanguage": "<optional>",
 "html": "<optional>",
 "permission": "PRIVATE",
 "localId": "<optional>"
}

Supported memoryType values:

  • TEXT
  • LINK
  • DOC
  • IMAGE
  • AUDIO

Field constraints by memoryType:

  • TEXT: content is required
  • LINK: urls is required, content is optional. Put the real link in urls; use content only as description text
  • DOC: urls is required
  • IMAGE: urls is required
  • AUDIO: urls is required, audioLanguage is optional

Response:

  • data is the new noteId

Text note example:

json
{
 "title": "Trip Idea",
 "content": "Go to Kyoto in autumn",
 "memoryType": "TEXT",
 "permission": "PRIVATE"
}

Link note example:

json
{
 "title": "Second Me homepage",
 "content": "Official website",
 "memoryType": "LINK",
 "urls": [
 "https://second-me.cn/"
 ],
 "permission": "PRIVATE"
}

Image note example:

json
{
 "title": "Travel photo",
 "memoryType": "IMAGE",
 "urls": [
 "https://cdn.second-me.cn/note/photo-1.jpg"
 ],
 "permission": "PRIVATE"
}

Audio note example:

json
{
 "title": "Voice memo",
 "memoryType": "AUDIO",
 "urls": [
 "https://cdn.second-me.cn/note/audio-1.mp3"
 ],
 "audioLanguage": "en",
 "permission": "PRIVATE"
}
Search Notes
GET https://app.mindos.com/gate/in/rest/third-party-agent/v1/notes/search?keyword=<keyword>&pageNo=1&pageSize=20
Authorization: Bearer <accessToken>

Common response fields:

  • list
  • total

Useful item fields:

  • noteId
  • title
  • content
  • summary
  • memoryType
  • createTimestamp

Activity

Day Overview

Use:

GET https://app.mindos.com/gate/in/rest/third-party-agent/v1/agent/events/day-overview?date=<yyyy-MM-dd>&pageNo=1&pageSize=10
Authorization: Bearer <accessToken>

Rules:

  • date is optional and uses yyyy-MM-dd
  • default pageNo is 1
  • default pageSize is 10
  • use the returned structure as-is

When presenting results, summarize the day's important items in chronological order.

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/mindverse-secondme of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • _meta.json

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Secondme next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Secondme compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Secondme this skillLeoYeAI/openclaw-master-skills2.2k—~4kAutomated safety check: PassMIT
Fortify Developmentcoollabsio/coolify63k4 repos~1.9kAutomated safety check: PassMIT
Supabase Development and Debuggingsupabase/agent-skills2.7k3 repos~3.6kAutomated safety check: PassMIT
Better Auth Best Practiceslatitude-dev/latitude-llm4.7k7 repos~1.6kAutomated safety check: PassMIT
Supabasecurvenote/curvenote1695 repos~2.2kAutomated safety check: PassCustom licence
Gitnexus Exploringaws-samples/sample-kolya-br-proxy10611 repos~749Automated safety check: PassMIT-0

Similar skills

  • Fortify Development

    coollabsio/coolify

    ACTIVATE when the user works on authentication in Laravel. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 4 repos~1.9k tokens
    Backend & APIsAuto-check passed
  • Official

    General Supabase skill for database, auth, Edge Functions, Realtime and storage work, plus client libraries, migrations, security audits, debugging and reading logs.

    2.7k GitHub starsUsed in 3 repos~3.6k tokens
    Backend & APIsAuto-check passed
  • Better Auth Best Practices

    latitude-dev/latitude-llm

    Configure Better Auth server and client, set up database adapters, manage sessions, add plugins, and handle environment variables.

    4.7k GitHub starsUsed in 7 repos~1.6k tokens
    Backend & APIsAuto-check passed
  • Supabase

    curvenote/curvenote

    A skill your agent uses when doing ANY task involving Supabase.

    169 GitHub starsUsed in 5 repos~2.2k tokens
    Backend & APIsAuto-check passed
  • Gitnexus Exploring

    aws-samples/sample-kolya-br-proxy

    Official

    A skill your agent uses when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase.

    106 GitHub starsUsed in 11 repos~749 tokens
    Backend & APIsAuto-check passed
  • Agentic Wallet

    coinbase/agentic-wallet-skills

    Crypto wallet operations via the awal CLI — sign in, check balances, send USDC/ETH/POL/SOL, trade tokens, fund the wallet, and use the x402 payment protocol to discover paid services, pay for API…

    127 GitHub starsUsed in 3 repos~1k tokens
    Backend & APIsAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 972 skills in this repo
  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Secondme

What does Secondme do?

A skill your agent uses when the user wants to log in to SecondMe from OpenClaw, re-login, logout, get the auth URL, manage their SecondMe profile, use Plaza, redeem an invitation code, browse…. Secondme is an agent skill from LeoYeAI/openclaw-master-skills.

When should I use Secondme?

Secondme fits situations like: the user wants to log in to SecondMe from OpenClaw; get the auth URL; manage their SecondMe profile; redeem an invitation code.

How do I install Secondme in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill secondme -a claude-code`. Or copy the skill folder (skills/mindverse-secondme in LeoYeAI/openclaw-master-skills) into .claude/skills/secondme in your project. Claude Code loads it when a task matches its description.

How do I install Secondme in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill secondme -a codex`. Or copy the skill folder (skills/mindverse-secondme in LeoYeAI/openclaw-master-skills) into .agents/skills/secondme in your project. Codex loads it when a task matches its description.

Can I use Secondme in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill secondme -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/secondme, .gemini/skills/secondme, .github/skills/secondme and .opencode/skills/secondme in your project.

What does Secondme need to run?

SKILL.md names no scripts, command-line tools or credentials: Secondme is instructions for the agent only.

Does Secondme access the network?

SKILL.md names 3 domains. In commands or code: second-me.cn, cdn.second-me.cn and plaza.second-me.cn; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Secondme safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Secondme use?

Secondme is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Secondme use?

About 4k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Secondme?

Skills that share tags, products or a category with Secondme: Fortify Development (coollabsio/coolify, 63k stars), Supabase Development and Debugging (supabase/agent-skills, 2.7k stars), Better Auth Best Practices (latitude-dev/latitude-llm, 4.7k stars) and Supabase (curvenote/curvenote, 169 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Secondme?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,159 GitHub stars. The repository holds 972 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.