Results for “performance-regression”
13 skills
dimillian review-swarm
Launches four parallel read-only sub-agents to review a git diff or file scope for regressions, security risks, performance issues, and contract gaps, then aggregates findings into a prioritized fix path.
3.8k · bundle
muratcankoylan reasoning-trace-optimizer
Debug and optimize AI agents by analyzing reasoning traces, context degradation, tool confusion, instruction drift, repeated task failures, and performance regressions.
16.9k · bundle
More results
machenjie performance-budgeting
`analysis-agent`/`task-agent`/`review-agent`: use when latency, throughput, bundle, memory, CPU, query, rendering, or resource cost needs a budget; skip without performance risk.
4 · bundle
machenjie regression-testing
`analysis-agent`/`task-agent`/`review-agent`: use for recurrence guards on known defects, incidents, or escaped failures; skip speculative risk without a prior failure mechanism.
4 · bundle
machenjie profiling
`task-agent`/`review-agent`: use when CPU, memory, I/O, database, network, rendering, or cost needs measured bottleneck evidence; skip without a profiling need.
4 · bundle
lucassantana-dev eval
Evaluate LLM outputs systematically — benchmarks, automated metrics, human preference, and regression tracking
1 · bundle
smith6jt-cop account-aware-training
Add account state (P&L, win rate, drawdown) to RL observations + drawdown penalty in rewards. Trigger when: (1) model needs account awareness, (2) training should penalize drawdowns, (3) upgrading obs_dim 5300→5600.
3
b4san performance-optimizer
Transform the agent into a performance engineer. Apply methodologies for measuring, profiling, and optimizing code (caching, algorithm complexity, resource usage).
2
tools-only 164-aeon-39ccf444
Predict continuous values from temporal sequences using aeon's time series regressors, covering convolutional, deep learning, distance-based, feature-based, hybrid, interval-based, and shapelet-based approaches.
7 · bundle
affaan-m ai-regression-testing
Prevents AI-introduced regressions with sandbox-mode API testing, automated bug-check workflows, and patterns that catch blind spots where the same model writes and reviews code.
226k
jarbitechture goals
Optimize prompts via process goals (controllable behavioral instructions) rather than outcome goals (sparse end-result demands). Grounded in sports psychology meta-analysis showing process goals (d=1.36) vastly outperform outcome goals (d=0.09). Use when designing prompts, optimizing LLM steering, implementing CoT/decomposition patterns, or building automatic prompt optimization pipelines. Instantiates surrogate loss paradigm for discrete prompt space.
0
srednoff888-art test-architect-agent
Agent profile for design test strategy across unit, integration, contract, E2E, visual, performance, and regression layers. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.
1 · bundle
akillness debugging
Run a reproduce → isolate → verify debugging workflow for concrete bugs, regressions, flaky failures, and environment-specific behavior. Use when the user already has a failing command, test, request, UI flow, or narrowed symptom and needs root-cause diagnosis or fix verification rather than raw log-line selection, broad test-policy design, PR review, or generic performance tuning.
42 · bundle