All skills
agent-eval
Compares coding agents head-to-head on your own tasks, measuring pass rate, cost, time, and consistency.
- Part of affaan-m/ECC
- 6.3k installs
- AI Engineering · Evals and monitoring
More Evals and monitoring skills
See all- caveman-learn133kReviews a Caveman learn report, applies cost-lowering fixes with your consent and reports the savings.
- caveman-optimize132kTurns a Caveman optimization observation into a candidate with a baseline comparison, needing your approval.
- prompt-engineering-patterns24.8kDesigns, debugs and improves prompts using templates, chain-of-thought and few-shot patterns.
- llm-evaluation13.8kSets up automated metrics, human feedback and benchmarks to measure how well your LLM application performs.
Also in this pack
- video-editing11kCuts, structures and polishes real footage into vlogs and videos using FFmpeg, Remotion and other tools.
- docker-patterns8.7kApplies Docker and Docker Compose patterns for local development, container security, networking, and multi-service orchestration.
- security-review8.6kReviews code for authentication, user input, secrets, API endpoints and payment flows against a security checklist.
- rust-testing8.5kWrites Rust unit, integration, async and property-based tests with mocking and coverage following TDD.