Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Relationship Reality Check

    1

    A grounded relationship analyzer that identifies behavioral patterns, emotional burdens, and whether repair leads to real change.

    Free

    7 usesSecurity scanned
    Relationship Reality Check

    Relationship Reality Check

    Example session with this skill installed

    My partner forgot our anniversary again, apologized profusely with flowers, but then got angry when I said I was still hurt. Is this just a mistake or a pattern?

    • Read your context and instructions
    • Compiled the relationship reality check

    The sequence is: neglect -> repair theater (flowers) -> deflection (anger at your reaction). The 'repair' failed because it lacked space for your impact. Watch if the anger is used to end the discussion without changing future behavior. The next move is to observe if the behavior repeats.

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

    About this skill

    The problem

    Relationship conflict can become difficult to read when emotion, interpretation, blame, and repeated patterns get mixed together. Users may end up seeking validation, replaying the same argument, or trying to explain the other person instead of looking clearly at what actually happened and what keeps repeating.

    What it does

    • Identifies recurring behavioral sequences such as pursuit-withdrawal, blame-shifting, repeated rupture, or apology-without-change.
    • Traces the emotional and practical burden to see who is carrying the work of maintaining the relationship.
    • Distinguishes between genuine repair and temporary relief, such as promises, affection, or apologies that do not lead to changed behavior.
    • Separates observable events from the interpretations built around them.
    • Tests whether accountability is real by looking at follow-through, changed behavior, boundaries, and what happens when the same pressure returns.
    • Flags signs of coercion, intimidation, or safety risk where outside professional support may be more appropriate than further analysis.

    Why use this skill

    This skill is designed to avoid automatic validation, false symmetry, unsupported psychological labeling, and armchair diagnosis. Instead, it stays close to behavior, recurrence, consequence, burden, and repair. It also makes uncertainty visible by asking what evidence would weaken or change the current interpretation.

    Use cases

    • Analyzing mixed signals by comparing what someone says with what they repeatedly do.
    • Evaluating whether a recurring conflict is being repaired or simply reset.
    • Understanding whether one person is carrying most of the emotional or practical labor.
    • Separating the original action from the reaction that followed it.
    • Testing whether blame is being shifted away from the issue that started the conflict.
    • Preparing for a difficult conversation by identifying what specific change would count as meaningful repair.
    • Making sense of breakups, trust issues, friendship conflicts, family tension, or recurring relationship patterns without diagnosing the other person.

    Known limitations

    This skill works from the information provided by the user and cannot independently verify events, motives, or the other person's perspective. It does not provide clinical diagnosis and is not a substitute for therapy, crisis support, or professional help in situations involving abuse, danger, or serious mental health concerns.

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

    Relies on one-sided accounts. Cannot provide clinical diagnoses. Not a substitute for professional therapy or crisis support.

    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

    7 uses

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 3 months ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    Unlike typical AI that offers generic validation, this skill uses behavioral analysis to identify specific patterns like pursuit-withdrawal or 'apology-without-change' to help you see the relationship's objective reality.

    This skill is designed for use with advanced LLMs that support complex reasoning, such as GPT-4 or Claude 3.5 Sonnet, and can be integrated into most major AI agent platforms.

    The skill focuses on observable actions and consequences, avoiding psychological labels or armchair diagnoses to ensure the analysis remains grounded in facts rather than speculation.

    You receive the full system configuration and behavioral logic set, which can be imported into your preferred AI agent builder or used as a system prompt immediately after purchase.

    Yes, purchasers receive lifetime access to any logic refinements or updates to the behavioral analysis framework as we improve its ability to detect complex interpersonal patterns.

    If the AI detects signs of coercion, intimidation, or safety risks, it is programmed to prioritize safety by flagging these patterns and recommending external professional support.

    New in Productivity

    Free