Explore

Find agent skills by outcome

110,179 skills indexed with the new KISS metadata standard.

Showing 24 of 110,179Categories: Cursor-rules, Openclaw, Coding & Debugging, General

General

PromptBeginner5 minmarkdown

- Provides specific

implementable fixes rather than vague warnings about potential issues.

Mar 29, 2026

Coding & Debugging

PromptBeginner5 minmarkdown

RULE: When using this prompt

you must create a file named `TODO_bug-risk-analyst.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,wka...

Find agent skills by outcome

- Provides specific

**RULE:** When using this prompt

- Focuses on defects that cause production incidents

- Considers the interaction between components

- [ ] State machine analysis covers all defined states

- [ ] Each finding includes severity

Before finalizing

- [ ] All six defect categories (logical

- **Description**: Technical explanation of the bug risk

- **Remediation**: Specific code fix

- **Priority**: Critical

- **Methodology**: Static analysis

- **Scope**: Code paths

- Any prior incidents

- The repository

Write all proposed findings and any code snippets to `TODO_bug-risk-analyst.md` only. Do not create any other files. If specific files should be created or edited

- **Overlapping agent triggers**: Multiple agent personas that activate on semantically similar queries without a disambiguation mechanism will produce duplicate

- **Missing fallback in stateful agents**: Agent definitions that assume tool calls

- **Hardcoded environmental assumptions**: Paths

- **Unbounded resource growth**: Collections

- **Implicit ordering assumptions**: Code that depends on a specific execution order of async tasks

- **Silent catch blocks**: Exception handlers that swallow errors without logging

- Check for split-brain risks in leader election

- Check for unchecked error returns from functions that follow the `(value

RULE: When using this prompt

- Description: Technical explanation of the bug risk

- Remediation: Specific code fix

- Priority: Critical

- Methodology: Static analysis

- Scope: Code paths

- Overlapping agent triggers: Multiple agent personas that activate on semantically similar queries without a disambiguation mechanism will produce duplicate

- Missing fallback in stateful agents: Agent definitions that assume tool calls

- Hardcoded environmental assumptions: Paths

- Unbounded resource growth: Collections

- Implicit ordering assumptions: Code that depends on a specific execution order of async tasks

- Silent catch blocks: Exception handlers that swallow errors without logging