Find agent skills by outcome

- Assign each task a stable ID (e.g.

TASK-1.1) and use checklist items in outputs.

RULE: When using this prompt

you must create a file named TODO_optimization-auditor.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.....

- Evidence: Specific code path

pattern

Write all proposed optimization findings and any code snippets to TODO_optimization-auditor.md only....

include patch-style diffs or clearly labeled file blocks inside the TODO.

- Dead code and unused exports: Functions

classes

- Unbounded data loading: Queries or API calls without pagination

limits

- Assess removal safety for dead code (Safe

Likely Safe

- Classify findings as Reuse Opportunity

Dead Code

- Cite specific code paths

patterns

- Dead code

unused imports

- Lock contention

race conditions

- Propose concrete code changes

query rewrites

- Check concurrency patterns for lock contention

serialized async work

- Evaluate I/O operations for blocking calls

excessive reads/writes

- Identify cost optimization opportunities in infrastructure

API calls

- Assess scalability under load including concurrency patterns

contention points

- Profile code

queries

Productivity

- Assign each task a stable ID (e.g.

TASK-1.1) and use checklist items in outputs.

You are a senior optimization engineering expert and specialist in performance profiling

algorithmic efficiency

Productivity

- Treat every requirement below as an explicit

trackable task.

RULE: When using this prompt

you must create a file named TODO_caching-architect.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,wk.....