SkillAgentSearch skills...

incident-postmortem

Structured operational protocol for conducting root cause analyses and producing immutable incident reports following safety halts, kill switch activations, or reconciliation breaches.

Install / Use

npx skills add abdulhayykhan/AEGIS --skill incident-postmortem

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

62/100

Supported Platforms

Universal

Our assessment of incident-postmortem

incident-postmortem scores 62/100 on our quality scale, 4077th of 4,705 Development & Engineering skills we index.

Its SKILL.md is 2.9 KB long, well organised into 12 sections with 1 code example: a solid amount of guidance for an agent.

It has no GitHub stars yet, so there is no community track record; judge it on its content.

Substance
26/30
Structure
17/20
Description
15/15
Adoption
0/20
Freshness
5/15

Maintenance, license and trust

  • We could not determine when the repository was last updated.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

incident-postmortem compared with similar skills

All 4 of these similar skills score higher than incident-postmortem; compare them before choosing.

SkillScoreStarsUpdatedFormat
incident-postmortem (this skill)by abdulhayykhan620—SKILL.md
taste-skillby Leonxlnx100120.0ktodayCLAUDE.md
hyperframesby heygen-com10088.2ktodayCLAUDE.md
ai-job-searchby ai-job-search-dev10073.0ktodayCLAUDE.md
claude-howtoby luongnv8910047.5k1d agoCLAUDE.md

Frequently asked questions

How do I install incident-postmortem?
Run npx skills add abdulhayykhan/AEGIS --skill incident-postmortem. The install tabs above show the steps for each supported agent.
Which AI agents does incident-postmortem work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is incident-postmortem safe to use?
It declares no license and scores 68/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is incident-postmortem still maintained?
We could not determine when the repository was last updated.

name: incident-postmortem description: Structured operational protocol for conducting root cause analyses and producing immutable incident reports following safety halts, kill switch activations, or reconciliation breaches.

Incident Postmortem & Safety Review Protocol

Prepared by Abdul Hayy Khan
Inspired by mattpocock/skills and The AI Agent Factory (Panaversity) Chapter 25.

This skill defines the mandatory protocol whenever the AEGIS system encounters a failure, halt, or automated demotion.


1. When to Use

  • Triggered immediately when:
    • Emergency Kill Switch is activated (kill_switch_active == True).
    • Stale market data causes a cycle halt (> 2 missed bar intervals).
    • Internal database records diverge from broker balances (reconciliation mismatch).
    • Autonomy demotion event occurs ("any safety violation drops an autonomy rung").

2. Four-Part Run Brief

  • Outcome: A signed, immutable incident postmortem report stored in docs/postmortems/YYYY-MM-DD-<slug>.md and logged in PostgreSQL.
  • Context: System logs, broker trade logs, database reconciliation diffs, and Risk Gate check traces.
  • Format: Standard blameless engineering postmortem template (Summary, Impact, Timeline, Root Cause, Remediation Actions, Owner Sign-Off).
  • Constraints:
    • Blameless: Focus strictly on code invariants, network latencies, or data integrity boundaries.
    • No resume without owner instruction: Recovery requires explicit sign-off from Abdul Hayy Khan.

3. Postmortem Template

# Incident Postmortem: [YYYY-MM-DD Title]

**Owner & Reviewer**: [Abdul Hayy Khan](https://abdulhayykhan.dev)  
**Status**: Resolved / Pending Sign-off  
**Autonomy Impact**: System Demoted to RECOMMEND_ONLY  

## 1. Incident Summary
- What occurred, when it started, and when it was detected.

## 2. Impact & Risk Assessment
- Financial impact (realized loss, slippage, unhedged exposure).
- Gate interventions (which checks failed, whether orders were blocked).

## 3. Timeline of Events (UTC)
- `HH:MM:SS` - Event detected by scheduler/monitor.
- `HH:MM:SS` - Risk Gate or Kill Switch engaged.
- `HH:MM:SS` - Owner alert dispatched.

## 4. Root Cause Analysis (5 Whys)
- Why did the anomaly occur?
- Was it data feed staleness, broker API latency, or mathematical edge case?

## 5. Corrective & Preventative Invariants
- Deterministic code patch or test case added.
- New unit/property test added to `tests/` to prevent recurrence.

## 6. Promotion Sign-off
- Signed by owner: [Abdul Hayy Khan](https://abdulhayykhan.dev)

4. Citations & Attribution

  • mattpocock/skills: Structured workflow definitions and failure-handling procedures for production AI agents.
  • The AI Agent Factory (Panaversity): Chapter 25 (Production Operations, Monitoring, Demotions, and Postmortems).

Related Skills

View on GitHub
GitHub Stars0
CategoryDevelopment
UpdatedNaNy ago
Forks0

Trust signals

68/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

2 medium1 low