Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    recon

    0

    Research + connect. Find fully funded masters/PhD opportunities worldwide, identify who to actually contact, and write outreach that does not smell synthetic.

    Free

    Security scanned
    recon

    recon

    Example session with this skill installed

    I want to apply for a funded PhD in AI in Germany. Here is my CV and a short writing sample. What are my chances and what should I do first?

    • Read your context and instructions
    • Compiled the recon

    I have processed your CV and writing sample into your recon.json inventory. Based on the German DAAD and DFG funding models, I have identified your current eligibility status and the immediate gaps you need to address.

    Research & Connection Audit: Germany (AI)

    CategoryStatusDetailsPriority
    Structural EligibilityPASSYour 4-year Bachelor + Master meets the 300 ECTS equivalent for German PhD entry.-
    Language RequirementsGAPMost programs are English-taught, but some DAAD scholarships require A2 German by the deadline.Medium
    Funding SignalLIVE3 PIs at TU Munich and TU Berlin recently secured DFG grants (6-18 months ago).High
    Lead Time RiskCRITICALUni-assist credential evaluation for your non-EU transcripts takes ~8 weeks.High
    Voice MatchREADYWriting sample analyzed. Outreach drafts will match your technical register.-

    Target Shortlist & Next Steps

    Verify Credentials: Start the VPC (Vorprüfungsdokumentation) process immediately via Uni-assist; this is your primary bottleneck.
    2.

    Contact PIs: I have prepared a draft for Prof. Dr. Schmidt at TU Munich regarding their recent "Robust RL" grant.
    3.

    Download State: Save the attached recon.json to your project folder to maintain your evidence inventory for the next stage.

    Next steps

    • Run /recon:roadmap to see the backwards-planned timeline for the Winter intake.
    • Review the outreach draft for Prof. Dr. Schmidt in the outreach/ directory.
    • Confirm if you have a German A2 certificate or need to schedule a test.

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

    About this skill

    Researching and applying for funded graduate programs is a minefield of invisible disqualifiers and generic outreach that gets ignored. recon is a structured multi-skill package for developers and students to navigate global Masters and PhD funding without the marketing fluff. It moves you from a raw evidence-based profile to a deadline-backwards roadmap and personalized outreach that actually gets replies from supervisors and admissions committees.

    What it does

    • Profile Building: Audits transcripts, publications, and eligibility fields to build a JSON-based evidence inventory.
    • Structural Gap Analysis: Identifies disqualifying bars like degree duration or age caps versus improvable thresholds like test scores.
    • Global Scouting: Maps funding systems across countries, comparing real stipend-to-cost-of-living ratios and post-study visa rights.
    • Target Identification: Locates specific PIs with fresh grant money and recurring scholarship programs using live award databases.
    • Tailored Outreach: Generates cold email drafts based on your actual writing samples, passing the find-and-replace test for authenticity.
    • Backwards Roadmapping: Calculates start-by dates for tasks with long lead times, like credential evaluation or apostilles.

    How it works

    1. Use /recon:profile to ingest CVs and transcripts into a standardized recon.json file.
    2. Run /recon:gaps to compare your inventory against specific program requirements and calculate lead times for missing items.
    3. Trigger /recon:outreach to draft emails that mirror your natural voice, verified against source documents.

    Frameworks & tools

    This skill operates on a recon.json schema, integrating with external databases like NSF Award Search, CORDIS, and UKRI Gateway to Research for live funding signals.

    Why this beats prompting it yourself

    Generic prompts produce "hallucinated" eligibility and academic outreach that sounds like spam. This skill enforces a "find-and-replace" test to ensure your emails are uniquely tied to the recipient's work and your own verified evidence.

    Use cases

    • Identify why a 3-year bachelor's degree blocks specific US or Japanese funding.
    • Find professors who just received multi-year grants and have headcount to fill.
    • Calculate if a stipend in Munich covers local rent better than a larger award in London.
    • Draft a PhD inquiry that doesn't trigger "AI-generated" filters in a faculty inbox.

    Known limitations

    Does not automate the sending of emails; a human must review and send. Requires at least 200 words of original user writing to generate a voice-matched outreach draft.

    Does not send emails automatically. Requires a 200-word writing sample for outreach. Calculations depend on the accuracy of provided transcripts and current funding cycle data.

    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 any payment.

    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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 19 days ago

    • Free with an Agensi account

    Requires

    Claude
    Git

    Permissions

    Network Access
    Read Files
    Write Files
    Browser
    Terminal / Shell
    Listed19 days ago

    What's inside

    Frequently Asked Questions

    recon creates a persistent `recon.json` evidence inventory that cross-references your specific academic history against real-time funding databases like NSF and CORDIS, preventing the 'hallucinations' and generic outreach common with standard prompting.

    The package includes the full multi-skill set, the `recon.json` schema for profile standardization, and access to the integrated live award database connectors for real-time funding searches.

    While recon works for most global programs, its specialized gap analysis is particularly effective for navigating the complex eligibility requirements of the US, UK, EU (including DAAD and Campus France), and Japan (MEXT).

    No, the skill generates high-quality drafts based on your verified evidence and writing style, but a human must review and manually send all communications to ensure academic integrity and personal connection.

    To accurately mirror your academic voice and avoid AI-detection filters, recon requires at least 200 words of your original writing (such as a prior essay or research abstract) to calibrate its outreach engine.

    Yes, recon includes a cost-of-living calculator that compares real stipend amounts against local market data in university cities, helping you determine the actual purchasing power of a funding offer.

    New in Research & Analysis