Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Certified Internet-Research Employee

    1

    Cookie-free, zero-script research SKILL pack. Every brief ships with a source ledger and a Certification verdict. Runs in Claude Code, OpenCode, OpenClaw, Gemini CLI. BYOK. 7-day money-back.

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Certified Internet-Research Employee

    Certified Internet-Research Employee

    Example session with this skill installed

    Vet the AI-coding-assistant market: demo real demand, list 3 pricing tiers with evidence, and flag agent-safe monetization. Deliver a source ledger + Certification verdict.

    • Read your context and instructions
    • Compiled the certified internet-research employee

    Summary

    vet-market.sh avoided — this is a zero-script skill.

    Demand: solo founder + dev-tools signals, steady buy pressure on research packs (reported 2026).

    TierPriceEvidence
    Quick Sprint$9single-question fast path
    Core$19Researcher mode + 5 recipes
    Pro$29+ Auditor mode

    Next steps

    • Open the source ledger in briefs/DUMP.md
    • The brief carries a CERTIFIED stamp (3/3 domains reconciled)

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem Managing research manually leads to hours wasted on documentation hunting, scattered bookmark tabs, forgotten insights, and inconsistent brief quality across different projects. Most AI research agents either leak browsing data through cookies and extensions or bypass safety by running as hidden autonomous scripts — violating platform policies and risking bans.

    What it does An instruction-led SKILL.md pack (fits Claude Code, OpenCode, OpenClaw, Gemini CLI) that turns your AI agent into a compliance-safe, cookie-free internet-research employee.

    • Researcher mode: plan, approve, gather, ledger, brief. Every outward call shows the exact command and waits for your approval — no silent autonomous sweeps.
    • Quick Sprint mode: single-question fast path for quick answers.
    • Auditor mode: adversarial re-review that re-opens cited sources, verifies quotes verbatim, grades source types, and reconciles claims across 3 or more domains before a brief is CERTIFIED.
    • 5 documented CLI recipes you run yourself: Jina Reader, Exa search, RSS via feedparser, YouTube captions via yt-dlp, GitHub search. Ships zero executables.

    Why it exists Independent security audits find about 26% of community skills carry a vulnerability, and script-bundled skills are roughly 2x more likely — so this pack ships instructions, not code. Solo founders are a primary buyer for AI employee/research packs (Sintra AI positioning, dedicated marketplaces — reported 2026).

    How it stays honest

    • Cookie-free by design: no account scraping, no ban risk.
    • Human-in-the-loop: every call waits for your approval.
    • Source-ledger discipline: every claim maps to a ledger row (source, type, retrieval date, quote). Ungrounded claims are marked PENDING SOURCE, never asserted.
    • Certification verdict: Auditor mode verifies, grades, and certifies before a brief ships.
    • No earnings/revenue guarantees, ever. AI assistance fully disclosed.

    What you get (tiers)

    • $9: Quick Sprint (single-question sprint + Jina/Exa recipes + brief template)
    • $19: Core Certified Research Employee (Researcher mode + 5-recipe toolkit + contracts + templates + LICENSE)
    • $29: Certified Pro (Core + Auditor mode + compliance posture + license index)

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.

    No autonomous execution. No scraping of cookie-gated sites like LinkedIn or X. Requires users to manually run commands from a toolkit.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 2 months ago

    Accounts
    GitHubJina
    Software
    mcporterNode.js

    Permissions

    Network Access

    Allowed Hosts

    r.jina.ai
    api.github.com
    Listed2 months ago
    Updated1 month ago

    What's inside

    Frequently Asked Questions

    Unlike autonomous agents that run hidden scripts, this skill uses a "Human-in-the-Loop" workflow where every search and data retrieval command must be approved by you, ensuring no hidden browsing or data leaks.

    The pack is designed as a set of standardized instruction files (.md) compatible with any CLI-based AI environment, including Claude Code, OpenCode, OpenClaw, and Gemini CLI.

    The Certification verdict is a secondary 'Auditor mode' that re-verifies every claim against the source ledger, checks quotes for verbatim accuracy, and grades source reliability before finalizing a report.

    No, this is a 'Bring Your Own Key' (BYOK) skill; it provides the CLI recipes and architecture for Jina, Exa, RSS, YouTube, and GitHub, but you use your own existing API credentials.

    You receive the SKILL.md instruction files, five CLI research recipes, a source-ledger template, and a professional brief template, with the Pro tier adding the Auditor mode and compliance posture documents.

    The skill ships as pure instructions and recipes rather than compiled code to avoid security vulnerabilities; you simply add the SKILL.md to your agent's directory and follow the recipe setup for your preferred tools.

    New in Research & Analysis