Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIGitHub CopilotGitHub CopilotGemini CLIGemini CLI+17 more

    Blameless Incident Learning Review

    1

    Builds an evidence-based incident timeline, contributing-factor analysis, and corrective plan without blame or invented causality.

    Secure checkout via Stripe

    0 installsSecurity scanned

    See it in action

    You say

    Use incident-learning-review on these Slack logs and Datadog exports. Build the default package, cite every conclusion, and do not fill in missing timestamps.

    Your agent does

    Evidence Ledger

    [S1] Slack Log #ops-incidents (10:05-10:45) [S2] Datadog Export: Latency Spike (10:08)

    Verified Timeline

    • 10:08: [S2] Latency exceeds 5s threshold.
    • 10:12: [S1] @dev-1 reports 500 errors in US-East-1.
    • 10:15: [Inference] Possible DB lock initiated.

    Gaps

    • Exact time of DB lock initiation is unverified in logs.

    What you get

    Generate blameless post-mortems from fragmented chat and monitoring logs.Map systemic contributing factors without attributing individual fault.Create auditable timelines with strict source-to-fact traceability.Identify critical information gaps that require further investigation.

    About this skill

    The problem

    Post-mortems often suffer from hindsight bias, invented causality, and missing evidence that gets "smoothed over" during drafting. Manual incident reviews struggle to maintain a strict audit trail between raw logs and final reports.

    What it does

    • Builds an evidence ledger with unique source IDs and locators for every material claim.
    • Constructs a verified timeline that distinguishes between observations, hypotheses, and causal claims.
    • Identifies and preserves conflicting data points in a dedicated conflict log instead of forced reconciliation.
    • Generates an action register focused on systemic changes rather than individual blame.
    • Flags specific information gaps that require further evidence or human decision-making.

    Why this beats prompting it yourself

    Generic prompts tend to hallucinate missing timestamps or bridge gaps with plausible-sounding but unverified narratives. This skill enforces a rigorous quality gate system that prioritizes "no false completion," ensuring every conclusion is traceable to your specific logs and telemetry.

    Use cases

    • Writing blameless post-mortems after production outages or security incidents.
    • Synthesizing multiple chat logs, PagerDuty alerts, and CloudWatch metrics into a single source of truth.
    • Creating auditable incident reports for compliance or executive review.
    • Mapping contributing factors in complex system failures where a single "root cause" is insufficient.

    Known limitations

    Does not make legal conclusions or attribute individual fault. Requires structured source materials to generate a high-confidence timeline.

    How to install

    Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean today

    • One-time purchase, yours forever

    Listedtoday

    Frequently Asked Questions