How do I install the Vajra skill?

Run npx skillmds@latest add dvcrn/vajra in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Vajra safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Vajra?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Vajra free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

dvcrn (@dvcrn) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Vajra by dvcrn — Agent Skill

Name: Vajra
Rating: 4.2 (5 reviews)
Author: dvcrn

Vajra

Analyze URLs, YouTube videos, tweets, or text for quality, bias, and reliability using the Vajra API (vajra.to). Use when the user asks to fact-check, analyze, evaluate, score, or assess the quality/bias/reliability of any web content, article, video, tweet, or text. Also use when asked to "vajra" something or run content through a signal filter.

dvcrn Updated Sep 8, 2026 32 repo stars

File contents

Vajra - Signal Filter for the Internet

Vajra is a content-analysis API by Humanity Labs. It scores content for epistemic quality (1-10), detects bias, extracts key takeaways, flags questionable claims, and produces structured verdicts.

Privacy and Data Handling

Important: This skill sends content to the Vajra API at https://www.vajra.to. Before using it:

Content you submit (URLs, text) is transmitted to Vajra's servers for analysis.
Analyzed content is cached server-side. If another user submits the same URL, they receive the cached result (0 credits). The original text you submit is not stored -- only the analysis output.
Every analysis generates a public permalink (e.g. vajra.to/a/ID). These are shareable and publicly accessible.
Do not submit private, proprietary, or personally identifiable content unless you understand and accept this behavior.
Vajra's privacy policy and terms are available at vajra.to.

Setup

An API key is required. Get one free at vajra.to/dashboard (Connections tab).

The key must be stored as the environment variable VAJRA_API_KEY. The agent will be prompted to set this during installation.

Analyze Content

curl -s -X POST https://www.vajra.to/api/analyze \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $VAJRA_API_KEY" \
  -d '{"content": "URL_OR_TEXT", "type": "url"}'

Set type to "text" for raw text (max 50,000 chars). Default is "url".

Supported content: articles, YouTube videos, X/Twitter posts, and raw text.

Parse the Response

The response JSON contains:

success        - boolean
cached         - boolean (0 credits if true)
credits_used   - 0 or 1
url            - permalink to full report (e.g. https://www.vajra.to/a/UUID)
analysis.title - content title
analysis.quality_score - 1-10 rating
analysis.bias_level    - bias assessment
analysis.markdown      - full report in markdown
analysis.metadata.tldr - one-sentence summary
analysis.metadata.verdict      - reliability assessment
analysis.metadata.key_takeaways - array of takeaways
analysis.metadata.warnings      - array of warnings

Present Results

When showing results to the user, format as:

**Title** - Quality: X/10
TLDR: [tldr]
Verdict: [verdict]
Key takeaways: [list]
Warnings: [list if any]
Full report: [permalink url]

Retrieve Existing Analysis

Fetch a previously completed analysis by ID (no auth needed, public endpoint):

curl -s https://www.vajra.to/api/analysis/ANALYSIS_ID

Credits and Pricing

Cached results cost 0 credits (same URL already analyzed by any user)
Free tier: 5 analyses/month
Pro: 100 analyses/month ($12/mo or $79/yr)
Analyses take 10-60 seconds depending on content length

---name: vajradescription: Analyze URLs, YouTube videos, tweets, or text for quality, bias, and reliability using the Vajra API (vajra.to). Use when the user asks to fact-check, analyze, evaluate, score, or assess the quality/bias/reliability of any web content, article, video, tweet, or text. Also use when asked to "vajra" something or run content through a signal filter.---# Vajra - Signal Filter for the InternetVajra is a content-analysis API by [Humanity Labs](https://humanitylabs.org). It scores content for epistemic quality (1-10), detects bias, extracts key takeaways, flags questionable claims, and produces structured verdicts.## Privacy and Data Handling**Important:** This skill sends content to the Vajra API at `https://www.vajra.to`. Before using it:- Content you submit (URLs, text) is transmitted to Vajra's servers for analysis.- Analyzed content is **cached server-side**. If another user submits the same URL, they receive the cached result (0 credits). The original text you submit is **not stored** -- only the analysis output.- Every analysis generates a **public permalink** (e.g. `vajra.to/a/ID`). These are shareable and publicly accessible.- **Do not submit private, proprietary, or personally identifiable content** unless you understand and accept this behavior.- Vajra's privacy policy and terms are available at [vajra.to](https://www.vajra.to).## SetupAn API key is required. Get one free at [vajra.to/dashboard](https://www.vajra.to/dashboard) (Connections tab).The key must be stored as the environment variable `VAJRA_API_KEY`. The agent will be prompted to set this during installation.## Analyze Content```bashcurl -s -X POST https://www.vajra.to/api/analyze \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $VAJRA_API_KEY" \ -d '{"content": "URL_OR_TEXT", "type": "url"}'```Set `type` to `"text"` for raw text (max 50,000 chars). Default is `"url"`.Supported content: articles, YouTube videos, X/Twitter posts, and raw text.## Parse the ResponseThe response JSON contains:```success - booleancached - boolean (0 credits if true)credits_used - 0 or 1url - permalink to full report (e.g. https://www.vajra.to/a/UUID)analysis.title - content titleanalysis.quality_score - 1-10 ratinganalysis.bias_level - bias assessmentanalysis.markdown - full report in markdownanalysis.metadata.tldr - one-sentence summaryanalysis.metadata.verdict - reliability assessmentanalysis.metadata.key_takeaways - array of takeawaysanalysis.metadata.warnings - array of warnings```## Present ResultsWhen showing results to the user, format as:```**Title** - Quality: X/10TLDR: [tldr]Verdict: [verdict]Key takeaways: [list]Warnings: [list if any]Full report: [permalink url]```## Retrieve Existing AnalysisFetch a previously completed analysis by ID (no auth needed, public endpoint):```bashcurl -s https://www.vajra.to/api/analysis/ANALYSIS_ID```## Credits and Pricing- Cached results cost 0 credits (same URL already analyzed by any user)- Free tier: 5 analyses/month- Pro: 100 analyses/month ($12/mo or $79/yr)- Analyses take 10-60 seconds depending on content length

Frequently asked questions