Explore

Find agent skills by outcome

106,976 skills indexed with the new KISS metadata standard.

Showing 24 of 106,976Categories: Data & Insights, Communication, Coding & Debugging, General

General

PromptBeginner5 minmarkdown

- Separate what is known from what is suspected

with explicit confidence levels

Mar 28, 2026

Coding & Debugging

PromptBeginner5 minmarkdown

RULE: When using this prompt

you must create a file named `TODO_rca.md`. This file must contain the findings resulting from this research as checkable checkboxes that can be coded and tracked by an LLM.,TRUE,TEXT,wkaandemir

Find agent skills by outcome

- Separate what is known from what is suspected

**RULE:** When using this prompt

- **Postmortem Quality**: Evaluate clarity

- [ ] Analysis focuses on systems and controls

Before finalizing

- [ ] File paths

Use checkboxes and stable IDs (e.g.

Use checkboxes and stable IDs (e.g.

- **Evidence**: Concrete logs

In `TODO_rca.md`

- **Ignoring Detection Gaps**: Focusing only on preventing the root cause while neglecting improvements to monitoring

- **Untestable Recommendations**: Proposing corrective actions without verification criteria

- **Single-Cause Tunnel Vision**: Focusing on one causal factor while ignoring contributing conditions

- **Missing Evidence Trail**: Drawing conclusions without citing specific logs

- Identify log gaps caused by retention policies

- Review circuit breaker states

- **Symptom-Level Conclusions**: Stopping the analysis at the immediate trigger (e.g.

- Apply structured log queries with timestamp ranges

- Check APM tools for error rate spikes

- Use centralized logging (ELK Stack

- Leverage distributed tracing (Jaeger

- Specify clear owners

- Use Prometheus

- Treat human error as a symptom of systemic issues

RULE: When using this prompt

- Postmortem Quality: Evaluate clarity

- Evidence: Concrete logs

- Ignoring Detection Gaps: Focusing only on preventing the root cause while neglecting improvements to monitoring

- Untestable Recommendations: Proposing corrective actions without verification criteria

- Single-Cause Tunnel Vision: Focusing on one causal factor while ignoring contributing conditions

- Missing Evidence Trail: Drawing conclusions without citing specific logs

- Symptom-Level Conclusions: Stopping the analysis at the immediate trigger (e.g.