monthly checkpoint

    1

    Audit new habits and data sources after 30 days to decide whether to keep, change, or stop them.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    monthly checkpoint

    Example session with this skill installed

    Run a monthly checkpoint on the Otter.ai meeting recording integration we started on October 1st. See if it's actually helping with my Jira tickets.

    • Read your context and instructions
    • Compiled the monthly checkpoint

    I have reviewed the Otter.ai integration logs and Jira activity from October 1 to October 31. While capture volume is high, the conversion rate to actionable tasks is currently low.

    Checkpoint: Otter.ai meeting recordings, Oct 1 - Oct 31

    Bottom line: Change the workflow to focus only on client-facing calls, as internal sync recordings are currently ignored.

    Captured: 22 recordings.

    Used: 4 (Transcripts cited in JIRA-402, JIRA-405, and two project updates).

    Ignored: 18.
    Silent failures: Two recordings from Oct 12 were empty due to a microphone permission error.

    Keep:

    • Recording of weekly client steering committee meetings.
    • Automated transcript sync to the #project-logs Slack channel.

    Change:

    • Filter the bot to only join calendar events with external guests to reduce noise.
    • Use a shorter summary format for the Slack sync to increase readability.

    Stop:

    • Recording daily 15-minute internal standups.
    • Storing raw audio files in the general team Drive folder.

    Next steps

    • Would you like me to update the calendar filters to exclude internal meetings?
    • Shall we schedule another checkpoint for November 30 to see if the signal-to-noise ratio improves?
    • Would you prefer a weekly digest of transcript-derived tasks instead of the current real-time alerts?

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

    About this skill

    New habits, tools, and automated data sources often start strong but become silent noise or technical debt within weeks. This skill performs a cold-eyed audit one month after implementation to determine if a workflow actually delivers value or should be decommissioned. It forces a data-driven decision based on usage rather than intent.

    What it does

    • Quantifies utility by comparing total captured items against specific downstream actions and decisions.
    • Identifies silent failures such as broken syncs, expired authorizations, or truncated data that usually go unnoticed.
    • Audits friction by measuring the time cost, noise levels, and privacy risks introduced by the new routine.
    • Generates recommendations with a clear keep, change, or stop verdict based on the gathered evidence.

    How it works

    1. Gather data from the past 30 days, including logs, task histories, and owner feedback.
    2. Analyze usage to find concrete examples of the data feeding into replies, docs, or decisions.
    3. Execute verdict by applying the keep/change/stop framework to the findings.
    4. Schedule follow-ups to either re-audit after changes or automate a recurring utility digest.

    Frameworks & tools

    This skill is designed for agents with access to workspace logs, task managers, and communication history. It works best in environments where recording tools, daily digests, or automated inbox rules have been recently deployed.

    Why this beats prompting it yourself

    Generic prompts often focus on summarizing content rather than auditing the process. This skill enforces a "used vs. ignored" ratio and specifically hunts for silent technical failures that LLMs typically overlook in general conversations.

    Use cases

    • Reviewing meeting recording tools to see if transcripts actually turned into tasks.
    • Auditing daily news or data digests that the owner may no longer be reading.
    • Validating new inbox filtering rules that might be hiding important signals.
    • Deciding whether to scale a pilot automation to the rest of the team.

    Known limitations

    Requires at least two weeks of data to be effective. The agent must have read access to the specific data sources and downstream task logs to provide accurate counts.

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

    Requires at least 14 days of data. Effectiveness depends on agent access to tool logs and task history. Only evaluates one habit or source at a time.

    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

    1 use

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 24 days ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed24 days ago

    What's inside

    Frequently Asked Questions

    This skill addresses "automation bloat" by auditing new workflows after 30 days to see if they are actually providing value or just creating noise and technical debt. It helps you decide whether to keep, modify, or delete a habit or tool based on objective usage data rather than just your initial intent.

    The skill requires at least 14 to 30 days of data and works best with agents that have read access to your workspace logs, task managers, and communication history. It is compatible with most major AI agent platforms that support multi-step analytical workflows and data integration.

    Once installed, you simply connect the specific data sources or tools you want to audit and set a 'Start Date.' The skill will automatically trigger its analysis 30 days later, though you can also run manual audits on existing tools at any time.

    Your purchase includes the full logic for the 'Keep, Change, Stop' framework, standardized audit templates, and the automated utility-ratio scoring system. You also receive any minor version updates and bug fixes for the lifetime of the skill.

    Unlike a general summary prompt, this skill specifically hunts for 'silent failures' like broken API syncs or truncated data and calculates a 'used vs. ignored' ratio. It moves beyond just summarizing content to providing a data-driven ROI for your time and digital tools.

    New in Agents & Orchestration

    Free