trendproof
Query TrendProof (trendproof.dev) for keyword trend velocity scores. Returns velocity score, trend direction (rising/stable/falling), monthly search volume, CPC, peak window, and action hint. Supports single keyword analysis, batch comparison (up to 5 keywords ranked by velocity), and related keyword discovery. Use when a user asks about keyword trends, whether a topic is rising or falling, content timing, wants to compare niches, or needs similar keyword suggestions.
Best use case
trendproof is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Query TrendProof (trendproof.dev) for keyword trend velocity scores. Returns velocity score, trend direction (rising/stable/falling), monthly search volume, CPC, peak window, and action hint. Supports single keyword analysis, batch comparison (up to 5 keywords ranked by velocity), and related keyword discovery. Use when a user asks about keyword trends, whether a topic is rising or falling, content timing, wants to compare niches, or needs similar keyword suggestions.
Teams using trendproof should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/trendproof/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How trendproof Compares
| Feature / Agent | trendproof | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Query TrendProof (trendproof.dev) for keyword trend velocity scores. Returns velocity score, trend direction (rising/stable/falling), monthly search volume, CPC, peak window, and action hint. Supports single keyword analysis, batch comparison (up to 5 keywords ranked by velocity), and related keyword discovery. Use when a user asks about keyword trends, whether a topic is rising or falling, content timing, wants to compare niches, or needs similar keyword suggestions.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for ChatGPT
Find the best AI skills to adapt into ChatGPT workflows for research, writing, summarization, planning, and repeatable assistant tasks.
AI Agent for Product Research
Browse AI agent skills for product research, competitive analysis, customer discovery, and structured product decision support.
SKILL.md Source
# TrendProof
**Trend velocity intelligence for AI agents.** Check whether a keyword is rising, stable, or falling before you create content, run ads, or build a product.
Live at **[trendproof.dev](https://trendproof.dev)**
---
## Setup (API key)
**Before doing anything else** — check if the API key is already configured:
```bash
python3 skills/trendproof/scripts/trendproof.py configure --show
```
**If no key is found**, stop and tell the user exactly this (do not attempt any API calls):
> "To use TrendProof, you need a free API key.
> 1. Open **https://trendproof.dev/dashboard#keys** (sign up if needed — 5 free trial credits included)
> 2. Copy your key (starts with `TRND_`) and send it to me"
Once the user provides the key, save it:
```bash
python3 skills/trendproof/scripts/trendproof.py configure --api-key TRND_xxxxx
```
Or set the environment variable:
```bash
export TRENDPROOF_API_KEY=TRND_xxxxx
```
---
## Analyze a single keyword
```bash
python3 skills/trendproof/scripts/trendproof.py analyze "AI agents"
```
Example output:
```
Keyword ai agents
Velocity [████████████░░░░░░░░] +87
Direction 🚀 RISING
Volume 8,100 / mo
CPC $2.45 CPM $6.13
Competition 0.38
Peak window 2026-02-10 — 2026-03-03
Hint 🚀 Strong momentum — act now before peak. High CPC = strong intent.
Took 1243ms
```
### With location (UK example):
```bash
python3 skills/trendproof/scripts/trendproof.py analyze "rust programming" --location 2826
```
### Raw JSON output:
```bash
python3 skills/trendproof/scripts/trendproof.py analyze "prompt engineering" --json
```
---
## Batch analysis (ranked)
Compare multiple keywords and get them ranked by velocity:
```bash
python3 skills/trendproof/scripts/trendproof.py batch "AI agents" "LLM fine-tuning" "RAG pipeline" "vector search"
```
Output (sorted by velocity score):
```
Keyword Score Direction Volume CPC
---------------------------------------------------------------------------
AI agents +87 🚀 rising 8,100 $2.45
RAG pipeline +34 🚀 rising 2,400 $1.80
LLM fine-tuning +8 📊 stable 5,500 $3.20
vector search -12 📉 falling 3,300 $1.10
Total cost: $0.3360
```
### From a file:
```bash
python3 skills/trendproof/scripts/trendproof.py batch-file keywords.txt
```
File format (one keyword per line, `#` for comments):
```
# AI keywords
AI agents
LLM fine-tuning
RAG pipeline
```
---
## Velocity score interpretation
| Score | Meaning |
|-------|---------|
| > 50 | 🚀 Strong uptrend — act now |
| 10–50 | 🚀 Rising — good timing window |
| -10 to +10 | 📊 Stable — safe but no momentum |
| -10 to -50 | 📉 Declining — consider alternatives |
| < -50 | 📉 Sharp decline — avoid |
Score formula: `((last 4 weeks avg − prior 4 weeks avg) / prior 4 weeks avg) × 100`, capped at [-100, +200].
---
## Related keywords
Discover similar keywords with volume and CPC:
```bash
python3 skills/trendproof/scripts/trendproof.py related "AI agents"
```
Output:
```
Similar to: AI agents
Keyword Volume CPC
─────────────────────────────────────────────────────────
ai agent tools 2,400 $3.10
autonomous ai agents 1,900 $4.20
...
```
---
## API reference (direct HTTP)
For advanced use, call the API directly:
```bash
# Analyze
curl -s https://trendproof.dev/api/analyze \
-H "Authorization: Bearer TRND_xxxxx" \
-H "Content-Type: application/json" \
-d '{"keyword": "AI agents"}'
# Related keywords
curl -s https://trendproof.dev/api/related \
-H "Authorization: Bearer TRND_xxxxx" \
-H "Content-Type: application/json" \
-d '{"keyword": "AI agents"}'
# Public leaderboard (no auth)
curl -s "https://trendproof.dev/api/leaderboard?limit=10&sort=velocity"
```
Response fields:
- `velocity_score` — -100 to +200; positive = rising
- `trend_direction` — `rising` | `stable` | `falling`
- `volume` — monthly search volume
- `cpc` — cost-per-click (USD)
- `cpm` — estimated CPM (cpc × 2.5)
- `competition` — 0–1 (DataForSEO competition index)
- `peak_window` — date range of highest trend activity
- `monthly_searches` — last 12 months of volume data
- `trend_data` — 12-week Google Trends graph (0–100 values)
- `action_hint` — human-readable recommendation
---
## Agent tool call pattern
When used as an AI agent tool, format results like:
> **"AI agents"** — velocity +87 🚀 rising, 8,100/mo, CPC $2.45. Peak: Feb–Mar 2026. **Act now before peak.**
For batch comparisons, present as a ranked list with winner highlighted.
---
## Troubleshooting
- **No key configured**: Run `configure --show`. If empty → ask user to get key at https://trendproof.dev/dashboard#keys
- **401 / unauthorized**: Key is set but invalid or revoked. Ask user to rotate at trendproof.dev/dashboard → API Keys → Rotate.
- **429 / credits exhausted**: Upgrade at trendproof.dev/dashboard → Billing.
- **Slow response (>5s)**: DataForSEO live API — expected for uncached keywords.
- **score = 0 + stable**: Likely very low-volume keyword; check `trend_data` array.Related Skills
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。
小红书长图文发布 Skill
## 概述