More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Afterlog: blameless post-mortems that change something

    1

    Turns an incident or a wasted afternoon into a one-screen, blameless post-mortem with a root cause and owned, dated action items, then brings the lesson back later.

    Free

    1 useSecurity scanned
    Afterlog: blameless post-mortems that change something

    Afterlog: blameless post-mortems that change something

    Example session with this skill installed

    post-mortem for the failed staging migration that just happened

    • Read your context and instructions
    • Compiled the afterlog

    I have analyzed the session logs and the failed migration script. I need a few more details: What was the total time QA was blocked, and who should own the fix for the deploy script?

    2024-05-22: Staging database migration failure (severity: medium)

    Summary: A schema migration failed to apply to the staging environment due to a syntax error in the SQL generated by the ORM. The staging environment was unavailable for 45 minutes.
    Impact: 4 developers and 2 QA engineers blocked for 45 minutes; no production impact.

    Timeline

    • 10:15: npm run migrate:staging executed by CI/CD
    • 10:16: Migration failed with SQLITE_ERROR: near "MODIFY": syntax error
    • 10:30: Issue identified as incompatible syntax for the staging DB engine
    • 11:00: Migration manually rolled back and environment restored

    Root cause: The ORM was configured to generate MySQL-compatible SQL, but the staging environment uses a different database engine version that does not support the MODIFY keyword.
    Trigger: Pushing a schema change that altered a column type without verifying engine compatibility.

    What helped: CI/CD logs clearly showed the specific SQL string that caused the failure.
    What hurt: Lack of a local dry-run check against a production-parity container.

    Action items

    • Add a pre-migration dry-run step to the CI pipeline: @dev-ops, 2026-10-25
    • Update staging environment to match production engine version: @infra-lead, 2026-10-30
    • Document engine-specific migration limitations in CONTRIBUTING.md: @lead-dev, 2026-10-24

    Lesson (one line): Always verify generated migration SQL against the target engine version before merging.

    Next steps

    • I have appended this entry to docs/post-mortems.md.
    • I will remind you of this lesson the next time you modify a migration file.
    • Ensure the owners are notified of their action items.
    engine-specific migration limitations in CONTRIBUTING.md

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

    About this skill

    When a production deploy fails or a migration wipes a table, the post-mortem often gets skipped because it feels like extra work. This skill drafts the timeline and root cause from what your session already shows: commands, errors and commits. It forces a blameless analysis that focuses on system improvements rather than human error.

    What it does

    • Incident extraction pulls timestamps, error messages, and commands from your current session to build a factual timeline.
    • Root cause analysis uses iterative questioning to move past "human error" to specific process or system gaps.
    • Action item tracking generates specific, testable tasks with assigned owners and due dates.
    • Project logging appends every incident to a centralized markdown file for permanent record keeping.
    • Contextual reminders surfaces lessons from past failures when you start work in a related area of the codebase.

    How it works

    1. Use the command post-mortem or respond to a prompt after a detected failure.
    2. Review the timeline and impact stats extracted from your environment.
    3. Answer specific questions to drill down from the trigger to the underlying root cause.
    4. Approve the generated action items and lesson summary.

    Frameworks & tools

    This skill works with any codebase using a standard file structure and is optimized for projects that store documentation in Markdown. It writes to docs/post-mortems.md or the project's existing incident folder.

    Why this beats prompting it yourself

    Writing blameless reports is psychologically difficult and often results in vague action items like "be more careful." This skill enforces a strict format that requires numbers, specific owners, and system-level fixes, ensuring failures actually lead to changes.

    Use cases

    • Failed deployments where a rollback was required or a service went down.
    • Data loss incidents such as corrupted migrations or accidental table drops in staging or production.
    • Security slips like accidental secret commits or exposed API keys.
    • Wasted time when a development approach hit a dead end after hours of work.

    Known limitations

    Saves each post-mortem to a Markdown file in the repo. It cannot automatically pull external logs from cloud providers unless they are piped into the current session or accessible via local files.

    Requires file system access to write to docs/. Cannot access external cloud logs (AWS/GCP) unless logs are visible in the session or local files.

    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 27 days ago

    • Free with an Agensi account

    Permissions

    Write Files
    Listed29 days ago
    Updated27 days ago

    What's inside

    Frequently Asked Questions

    The skill builds the timeline from facts already in your session (commands, errors, commits), then prompts you with iterative questions to identify system-level gaps rather than blaming individual actions.

    This skill is compatible with any AI agent or IDE that supports markdown-based documentation and has access to your local terminal session or log files.

    No. It needs no integrations: it writes to docs/post-mortems.md (or your existing incident folder) and works from errors and logs that are in the session or that you paste.

    One SKILL.md: the post-mortem format, the steps from timeline to root cause, the rules for action items and the lesson reminder. It is free.

    Yes, the skill is designed to search your existing incident logs and surface relevant 'lessons learned' whenever you begin working in a related area of the codebase.

    New in DevOps & Cloud