Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Decision Memory Studio

    1

    Turns meetings and project chats into verified decisions, assigned actions, deadlines, risks, and follow-up drafts.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Decision Memory Studio

    Decision Memory Studio

    Example session with this skill installed

    Process these notes from the API V2 meeting held on October 12, 2026 in UTC: Sarah proposed Postgres. Mark preferred MongoDB. Jen, the technical lead and authorized decision owner, approved Postgres. Mark accepted the task to draft the schema by October 16, 2026. No review meeting was scheduled.

    • Read your context and instructions
    • Compiled the decision memory studio

    Executive Snapshot

    The authorized decision owner selected Postgres for API V2. One action is assigned to Mark for October 16, 2026. Mark’s earlier MongoDB preference remains recorded as context, not as an unresolved decision. No review meeting or additional commitment was documented.

    Decision Register

    IDDecisionStatusRationaleOwnerEffective dateEvidence
    D-01Use Postgres for the API V2 data layer.DecidedNot recordedJen2026-10-12“Jen…approved Postgres.”

    Action Tracker

    IDActionOwnerDueStatusDependencyEvidence
    A-01Draft the Postgres schema.Mark2026-10-16 UTCNot startedD-01“Mark accepted the task…”

    Open Questions

    • Who will review the draft schema?
    • Where should Mark deliver it?

    Risks and Dependencies

    • Review ownership is not recorded; this may delay feedback after delivery. Mitigation: Jen assigns a reviewer.
    • No technical risk was stated in the supplied notes; Mark’s earlier preference is not treated as resistance.

    Follow-up Draft

    Subject: API V2 decisions and actions — October 12

    Team, today Jen approved Postgres for the API V2 data layer. Mark owns the schema draft due October 16, 2026 UTC. We still need to confirm the reviewer and delivery location. Please reply with corrections before this record becomes the working decision log.

    Quality Audit

    Evidence is present for the decision and action. The deadline is absolute and grounded in the supplied timezone. No meeting, credential requirement, motivation, or agreement was invented. Completeness: 86%; reviewer and delivery location remain unknown.

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

    About this skill

    The problem

    Meeting summaries are often too vague to be useful. Teams lose track of who owns a task, what was actually agreed upon, and why specific choices were made.

    What it does

    • Extracts concrete decisions, actions, and risks from messy transcripts or chat logs.
    • Maps every fact to a specific source or timestamp to maintain a chain of evidence.
    • Normalizes relative deadlines (e.g., "by next Friday") into absolute dates.
    • Identifies conflicting statements and blocks provisional decisions until resolved.
    • Generates ready-to-send follow-up messages for stakeholders.

    Why this beats prompting it yourself

    Generic prompts often hallucinate agreement or ignore subtle disagreements in a transcript. This skill enforces a strict classification schema that preserves tension and identifies missing context, ensuring your project record is an accurate source of truth rather than a polite summary.

    Use cases

    • Converting hour-long Zoom transcripts into actionable project registers.
    • Consolidating scattered Slack threads into a formal decision log.
    • Tracking technical debt and architectural choices during engineering syncs.
    • Auditing project changes and owner handoffs over multiple sessions.

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

    Requires meeting dates to resolve relative deadlines. Cannot resolve conflicting claims without manual authority. Best suited for project-heavy or technical collaboration.

    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 1 month ago

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Decision Memory Studio supports standard text-based transcripts from platforms like Zoom, Microsoft Teams, and Google Meet, as well as exported chat logs from Slack or Discord. It functions best when provided with chronological dialogue where individual speakers are clearly identified.

    Unlike generic summaries, this skill uses a specialized schema to identify conflicting statements and relative dates (like "next Tuesday"), converting them into a verified, absolute project register. It prioritizes evidence-based tracking over simple paraphrasing, ensuring no action item is lost in a long transcript.

    When you purchase this skill, you receive the full Decision Memory Studio workflow, including the classification logic, date normalization tools, and templates for stakeholder follow-ups. You will also have access to any minor version updates and bug fixes released for this specific version.

    The skill flags "provisional decisions" where participants seem to disagree or where information is missing. These items are highlighted in your final report, allowing you to resolve the tension before the decision is officially committed to your project log.

    This skill is designed to be compatible with major LLM-based agents that support structured data processing. Once purchased, you can import the skill into your preferred AI agent environment via the marketplace's standard "Add to Agent" workflow.

    New in Business & Operations