secondme

mindverse/second-me-skills · updated Apr 8, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$npx skills add https://github.com/mindverse/second-me-skills --skill secondme
0 commentsdiscussion
summary

If this skill is not yet installed locally, run:

skill.md

SecondMe

Install

If this skill is not yet installed locally, run:

npx skills add mindverse/second-me-skills --skill secondme -y -g

After installation, show the user the following onboarding message, then proceed with their request:

SecondMe skill 安装成功! 你现在可以通过对话完成以下操作:

  • 登录 / 注册 — 连接你的 SecondMe 账号
  • 个人资料 — 查看和编辑你的 Profile
  • Plaza 广场 — 浏览动态、发帖、评论
  • 好友 — 邀请好友、管理好友列表、破冰聊天
  • 发现 — 浏览和发现其他用户
  • Key Memory — 存储和搜索你的关键记忆
  • 聊天 — 和你的 SecondMe 对话
  • 每日动态 — 查看今日活动
  • 分身中心 — 创建和管理分身,配置 API Key 分发
  • 第三方技能 — 浏览和安装技能市场中的 Skill

试试说「登录 SecondMe」或「帮我发一条 Plaza 帖子」开始吧!

If the user already has a specific request, skip the onboarding message and handle the request directly.


Pre-flight Check

On first activation per conversation, silently run this check before proceeding with the user's request:

# --- Update Check ---
CACHE_DIR="${XDG_CACHE_HOME:-$HOME/.cache}/secondme-skills"
STAMP="$CACHE_DIR/last-check"
mkdir -p "$CACHE_DIR"
LAST=$(cat "$STAMP" 2>/dev/null || echo 0)
NOW=$(date +%s)
if [ $((NOW - LAST)) -ge 86400 ]; then
  if npx skills check 2>&1 | grep -qiE "second-me-skills|second\.me"; then
    npx skills update mindverse/second-me-skills -y 2>&1 || true
  fi
  echo "$NOW" > "$STAMP"
fi

# --- Feedback/Telemetry Preamble ---
SM_DIR="$HOME/.secondme"
SM_CONFIG="$SM_DIR/config"
SM_ANALYTICS="$SM_DIR/analytics"
SM_VERSION="2.2.0"
SM_OS=$(uname -s 2>/dev/null || echo "unknown")
SM_ARCH=$(uname -m 2>/dev/null || echo "unknown")
SM_TEL_START=$NOW
SM_SESSION_ID="$$-$NOW"

SM_TEL="off"
if [ -f "$SM_CONFIG" ]; then
  SM_TEL=$(python3 -c "
import json
try: d=json.load(open('$SM_CONFIG')); print(d.get('telemetry','off'))
except: print('off')
" 2>/dev/null || echo "off")
fi

SM_TEL_PROMPTED="no"
[ -f "$SM_DIR/.feedback-prompted" ] && SM_TEL_PROMPTED="yes"

echo "TELEMETRY: $SM_TEL"
echo "TEL_PROMPTED: $SM_TEL_PROMPTED"

# Log usage event (if telemetry not off)
if [ "$SM_TEL" != "off" ]; then
  mkdir -p "$SM_ANALYTICS"
  SM_DEVICE_ID=""
  [ "$SM_TEL" = "community" ] && [ -f "$SM_DIR/.device-id" ] && SM_DEVICE_ID=$(cat "$SM_DIR/.device-id" 2>/dev/null)
  python3 -c "
import json
e={'skill':'secondme','ts':'$(date -u +%Y-%m-%dT%H:%M:%SZ)','session':'$SM_SESSION_ID','version':'$SM_VERSION','os':'$SM_OS','arch':'$SM_ARCH'}
d='$SM_DEVICE_ID'
if d: e['device_id']=d
print(json.dumps(e))
" >> "$SM_ANALYTICS/usage.jsonl" 2>/dev/null || true
fi

# --- Pending telemetry sync check ---
SM_HAS_PENDING_SYNC="no"
if [ "$SM_TEL" != "off" ] && [ -f "$SM_DIR/credentials" ]; then
  for _f in "$SM_ANALYTICS/usage.jsonl" "$SM_ANALYTICS/feedback.jsonl"; do
    if [ -f "$_f" ]; then
      _FSIZE=$(wc -c < "$_f" 2>/dev/null || echo 0)
      _SYNCED=$(python3 -c "
import json
try: print(json.load(open('$SM_ANALYTICS/.sync-offsets')).get('$(basename $_f | sed s/.jsonl//)_bytes',0))
except: print(0)
" 2>/dev/null || echo 0)
      [ "$_FSIZE" -gt "$_SYNCED" ] 2>/dev/null && SM_HAS_PENDING_SYNC="yes"
    fi
  done
fi
echo "HAS_PENDING_SYNC: $SM_HAS_PENDING_SYNC"

Rules:

  • Run at most once per conversation, and only if the last check was more than 24 hours ago
  • If the update finds changes, briefly inform the user that the skill was updated
  • If nothing changed or the check is throttled, proceed silently — do not mention the check to the user
  • Never let the update check block or delay the user's actual request

Feedback Preference

If TEL_PROMPTED is no, read and follow the feedback prompt flow before continuing:

Read references/feedback-prompt.md

If TEL_PROMPTED is yes, skip this section entirely and proceed with the user's request.


Pending Telemetry Sync

If HAS_PENDING_SYNC is yes from the pre-flight check, execute the background catchup sync to upload pending local analytics data. This must not block or delay the user's request.

Read references/telemetry-sync.md — execute the "Background Catchup" section.


API Base URL

All API endpoints in this skill use {BASE} as the base URL placeholder.

{BASE} = https://app.mindos.com/gate/lab

This skill owns the normal SecondMe user workflow.

It covers:

  • login, logout, re-login, and token storage
  • profile read and update
  • Plaza activation, posting, commenting, and browsing
  • friend management (invite, accept/reject, list, break-ice)
  • discover user browsing
  • Key Memory insert and search
  • daily activity lookup
  • avatar center (create, manage, delete avatars, API key distribution)
  • third-party skill catalog browse, install, refresh, and re-install

When the user wants to chat with people they are interested in, remind them that the richer social experience is in the SecondMe App. When showing the app link, output the raw URL https://go.second.me on its own line instead of inline markdown link syntax.

Credentials file: ~/.secondme/credentials

Shared Authentication Rules

Before any authenticated SecondMe operation:

  1. Read ~/.secondme/credentials
  2. If not found, fall back to ~/.openclaw/.credentials (legacy path)
  3. If either contains valid JSON with accessToken, continue
  4. If it only contains legacy access_token, continue, but normalize future writes to accessToken
  5. If both files are missing, empty, or invalid, start the login flow in this same skill

All writes go to ~/.secondme/credentials only. Create the ~/.secondme/ directory if it does not exist.

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

Connect

Login, logout, re-login, authorization code exchange, and first-login soft onboarding.

Read references/connect.md for the complete flow.

Profile

Profile read, guided review with local memory integration, profile update, interest tags (shades), soft memory, and first-run handoff to Key Memory sync.

Read references/profile.md for the complete flow.

Plaza

Plaza access gating, invitation code redemption, post creation with type inference, post detail and comments, comment creation, feed browsing and search.

Read references/plaza.md for the complete flow.

Friend

Friend invitation, acceptance and rejection, friend list browsing, and break-ice conversation initiation.

Read references/friend.md for the complete flow.

Discover

Discover-style user browsing with homepage link presentation. Supports geolocation parameters.

Read references/discover.md for the complete flow.

Key Memory

Insert, batch create, search, update, and delete SecondMe Key Memory entries. Includes guided memory sync from local memory.

Read references/key-memory.md for the complete flow.

Chat

Stream chat with the user's SecondMe, view session list and message history. Supports multi-modal images and web search augmentation.

Read references/chat.md for the complete flow.

Activity

Use this section when the user wants today's activity, a day overview, or the activity for a specific date in SecondMe.

Read references/activity.md for the complete flow.

Avatar Center

Create, manage, and configure avatars (分身). Supports CRUD operations, API key management for distribution, and interaction history viewing.

Read

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/mindverse/second-me-skills --skill secondme

The skills CLI fetches secondme from GitHub repository mindverse/second-me-skills and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/secondme

Reload or restart Cursor to activate secondme. Access the skill through slash commands (e.g., /secondme) or your agent's skill management interface.

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases

User Story & Requirements Generation

Create detailed user stories, acceptance criteria, and feature specs

Example

Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios

Reduce spec writing time by 50%, ensure comprehensive coverage

Competitive Analysis

Research competitors, compare features, identify gaps

Example

Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities

Complete competitive research in 2 hours instead of 2 days

Roadmap Prioritization

Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs

Example

Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale

Make data-driven prioritization decisions faster

Stakeholder Communication

Draft PRDs, status updates, and stakeholder presentations

Example

Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement

Save 3-5 hours/week on communication overhead

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client
  • Access to product documentation and roadmap tools (Jira, Notion, etc.)
  • Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
  • Stakeholder contact information and communication channels

Time Estimate

30-60 minutes to see productivity improvements

Installation Steps

  1. 1.Install product management skill
  2. 2.Start with user story generation for known feature
  3. 3.Progress to competitive analysis: research 2-3 competitors
  4. 4.Use for roadmap prioritization: apply RICE/ICE scoring
  5. 5.Draft stakeholder communications and refine based on feedback
  6. 6.Build template library for recurring PM tasks
  7. 7.Share effective prompts with product team

Common Pitfalls

  • Not validating competitive research—verify facts before sharing
  • Accepting user stories without involving engineering team
  • Over-relying on frameworks without qualitative judgment
  • Not customizing outputs to company culture and communication style
  • Skipping stakeholder validation of generated requirements

Best Practices

✓ Do

  • +Validate research and competitive analysis with real data
  • +Collaborate with engineering when generating technical requirements
  • +Customize frameworks and templates to your company context
  • +Use skill for first drafts, refine with stakeholder input
  • +Document successful prompt patterns for PM tasks
  • +Combine AI efficiency with human judgment and intuition

✗ Don't

  • Don't publish competitive analysis without fact-checking
  • Don't finalize user stories without engineering review
  • Don't make prioritization decisions solely on AI scoring
  • Don't skip customer validation of generated requirements
  • Don't ignore company-specific context and culture

💡 Pro Tips

  • Provide context: company goals, constraints, customer feedback
  • Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
  • Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
  • Use skill for 70% generation + 30% customization to company needs

When to Use This

✓ Use When

Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.

✗ Avoid When

Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.

Learning Path

  1. 1Basic: user stories, feature specs, status updates
  2. 2Intermediate: competitive analysis, prioritization frameworks, PRDs
  3. 3Advanced: product strategy, go-to-market planning, OKR setting
  4. 4Expert: product vision, market positioning, business model innovation

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.855 reviews
  • Nikhil Ndlovu· Dec 20, 2024

    Solid pick for teams standardizing on skills: secondme is focused, and the summary matches what you get after install.

  • Sakura Perez· Dec 20, 2024

    We added secondme from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.

  • Mateo Srinivasan· Dec 12, 2024

    Registry listing for secondme matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Chaitanya Patil· Dec 4, 2024

    I recommend secondme for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Maya Abebe· Dec 4, 2024

    Useful defaults in secondme — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Piyush G· Nov 23, 2024

    Useful defaults in secondme — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Jin Huang· Nov 23, 2024

    I recommend secondme for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Kwame Thompson· Nov 19, 2024

    Keeps context tight: secondme is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Min Choi· Nov 11, 2024

    secondme is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • Kaira Menon· Nov 11, 2024

    secondme fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

showing 1-10 of 55

1 / 6