be more ambitious

    1

    Upgrade basic tasks into expert-level prompts using Altitude, Depth, and Range axes for professional-grade AI outputs.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    be more ambitious

    Example session with this skill installed

    I need to update the performance numbers in my monthly engineering report. Be more ambitious with this prompt.

    • Read your context and instructions
    • Compiled the be more ambitious

    I have analyzed the task. You are currently looking to sync data for a monthly report, but the goal is likely to identify system bottlenecks and justify infrastructure spend for the next quarter.

    Upgraded Engineering Performance Prompt

    Analyze the raw Prometheus metrics and GitHub deployment logs from the last 30 days to identify the three most significant regressions in system latency. Instead of summarizing the dashboard, correlate latency spikes with specific PR merges and infrastructure changes. 
    
    Act as a Site Reliability Engineer, a Data Scientist, and a Forensic Architect. The SRE will map the causal link between deployments and SLO misses. The Data Scientist will test the assumption that 'database load' was the primary cause by running a correlation analysis against concurrent background jobs. The Forensic Architect will act as a red team, attempting to disprove the findings by finding alternative explanations in the network VPC logs.
    
    Deliver a report that identifies the 'goal beyond the goal': which three services require immediate refactoring to prevent a total outage, and what is the projected cost of inaction?
    

    Prerequisites

    • Access to raw Prometheus metrics and GitHub API logs.
    • A statistical tool (like a Python notebook) for correlation analysis.

    Outside Judge: Compare findings against the PagerDuty incident history to see if identified spikes actually resulted in pings.

    Risks and limits

    • Large-scale log analysis may hit rate limits or incur high token costs.
    • The model may misinterpret network noise as causal signals without clean data.

    Next steps

    1. Smallest first run: Run this prompt against a single 24-hour window where a known latency spike occurred.
    2. Data Check: Ensure you have the raw logs exported rather than just screenshots of Grafana charts.
    3. Approval: Confirm if you want the model to suggest specific budget reallocations based on the findings.

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

    About this skill

    Stop settling for shallow, template-driven AI outputs. This skill applies Felix Rieseberg's "How to be more ambitious" framework to your tasks, pushing your model to function as a field-leading expert rather than a basic assistant. It is designed for developers and power users who need their prompts to handle complex outcomes, deep technical analysis, and multi-disciplinary logic.

    What it does

    • Altitude Adjustment shifts the focus from literal tasks to high-level outcomes and the decisions they serve.
    • Expert Depth forces the model to use raw source material, professional methodologies, and specific technical instruments.
    • Range Integration identifies relevant cross-disciplinary techniques by translating nouns into functional verbs.
    • External Validation defines outside judges like test suites or held-out datasets to verify accuracy without self-grading.
    • Adversarial Red-Teaming incorporates roles specifically designed to challenge assumptions and break the result for better reliability.

    How it works

    1. Restate the task to confirm the core objective and intended use of the final result.
    2. Apply ambition axes by selecting the most relevant path: Altitude (outcome-driven), Depth (professional rigor), or Range (cross-field techniques).
    3. Assemble the framework including stretch goals, raw data requirements, and a crew of functional roles.
    4. Generate the upgrade providing a ready-to-paste prompt, a list of technical prerequisites, and a risk assessment.

    Frameworks & tools

    This skill is based on the ambition framework by Felix Rieseberg. It works best when the user can provide access to raw data, protocol analyzers, statistical simulators, and validation environments.

    Why this beats prompting it yourself

    Most manual prompts suffer from "template-fill" syndrome, leading to generic summaries. This skill systematically forces the model to ignore digested summaries in favor of raw data and professional-grade instrumentation. It replaces vague requests for "better quality" with concrete instructions for outside validation and adversarial testing.

    Use cases

    • Strategic Analysis: Transform a simple data request into a decision-support system that names urgent business tradeoffs.
    • Technical Audits: Upgrade a code review prompt to function like a forensic analyst checking raw logs against specific security protocols.
    • Product Strategy: Shift a feature list into a causal story that challenges internal churn assumptions using held-out datasets.

    Known limitations

    Does not work for quick factual lookups or minor text edits. Requires the user to provide or have access to the raw data and technical tools requested in the prerequisites.

    Not for factual Q&A or small edits. Requires manual approval for destructive actions or external spending. Effectiveness depends on user access to raw data and technical validation tools.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 29 days ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed29 days ago

    What's inside

    Frequently Asked Questions

    This skill solves the 'bland output' problem by using the Altitude, Depth, and Range framework to force AI models out of generic assistant mode and into high-level expert personas that prioritize raw data over summaries.

    This skill is compatible with all major LLMs (like GPT-4, Claude 3.5, and Gemini) and can be integrated into any AI agent or workflow that supports custom system instructions or complex multi-step prompting.

    You will receive the core framework instructions, a library of 'ambition axes' for different professional fields, and a guide on how to implement the external validation and red-teaming components.

    While it works with basic text, it performs best when you provide raw data (like logs, spreadsheets, or codebases) and have a way to run external validation, such as a test suite or a simulator.

    Setup is immediate; you simply import the provided logic into your agent's system prompt or use the step-by-step assembly guide to upgrade a specific task on the fly.

    This skill is designed for high-stakes, multi-disciplinary tasks; it is not recommended for simple factual queries, basic spell checking, or tasks where 'good enough' is preferred over deep technical rigor.

    New in Prompt & Skill Engineering