Loading...
Loading...
Found 458 Skills
Analyze and transform messy, prototype, overgrown, slop-prone, or hard-to-maintain software repositories into maintainable product-shaped codebases while preserving existing product behavior. Use when the user asks to antislop a codebase, clean up a messy repo, run a maintainability migration, write a refactor plan, modernize structure, improve TypeScript/type boundaries, harden tests, reduce large files, clean architecture, coordinate subagent-driven refactors, or produce a final migration audit/report/microsite. Do not use for broader production-readiness specialties such as security audits, observability/logging programs, compliance hardening, SRE/runbook work, or reliability engineering unless the user explicitly scopes those as part of the maintainability refactor.
Alibaba Cloud Elasticsearch instance diagnosis skill. Use for cluster health checks, troubleshooting, and performance analysis on Elasticsearch instances. Triggers (English): Elasticsearch diagnosis, ES instance issues, slow search, write failures, cluster Red/Yellow, unassigned shards, node disconnected, load imbalance, thread pool 429, JVM/OOM/circuit breaker, disk watermark / read-only index, instance activating / change stuck, service avalanche / all shards failed. 触发词（中文）: ES诊断、阿里云ES、Elasticsearch诊断、ES集群/实例故障排查、ES健康检查、集群红灯/变红/黄灯/变黄、集群异常、分片未分配、主分片未分配、节点掉线/离线、负载不均衡、搜索/查询变慢、慢查询、写入失败/变慢/拒绝、线程池打满、HTTP 429、内存过高、OOM、断路器、磁盘满/水位、索引只读、实例激活中/activating、变更卡住/未完成、雪崩、服务不可用、all shards failed。
Optimize Harness CI/CD pipeline performance via MCP. Configure parallel test execution with Test Intelligence, design multi-layer caching strategies, analyze pipeline bottlenecks with stage-level timing breakdowns, optimize cache hit rates, and design monorepo CI pipelines with selective builds. Use when asked to speed up pipelines, improve cache hit rates, set up parallel testing, optimize build times, or configure monorepo builds. Do NOT use for creating new pipelines (use create-pipeline instead) or debugging failures (use debug-pipeline instead). Trigger phrases: pipeline speed, slow pipeline, cache hit rate, parallel tests, test intelligence, build optimization, caching strategy, monorepo pipeline, pipeline bottleneck, build speed.
Diagnose Harness pipeline executions via MCP. Analyzes any execution (failed or successful) to produce structured reports with stage/step breakdown, timing, bottlenecks, failure details, chained pipeline drill-down, and execution logs. Use when asked to debug a pipeline, investigate a failure, find out why a build failed, analyze pipeline errors, check execution logs, review execution performance, or find bottlenecks. Trigger phrases: debug pipeline, pipeline failed, why did my build fail, analyze failure, pipeline error, execution logs, fix pipeline, execution bottleneck, slow pipeline.
Incident response and analysis via Harness MCP. Correlate incidents with recent deployments, assess blast radius and downstream service impact, and generate comprehensive postmortem documents. Use when asked to investigate an incident, determine if a deployment caused an issue, assess blast radius, or create a postmortem. Do NOT use for pipeline debugging (use debug-pipeline instead) or SLO management (use manage-slos instead). Trigger phrases: incident, deployment correlation, blast radius, postmortem, root cause, service impact, outage analysis, rollback decision, incident timeline, deployment caused, which deploy.
Configure Harness AI-powered operations (AIDA) via MCP. Set up predictive failure analysis with ML models for memory leaks, disk exhaustion, connection pool saturation, and latency degradation. Configure intelligent alert correlation and noise reduction to reduce alert volume. Use when asked to set up predictive failure analysis, configure AI-powered alerting, reduce alert noise, or enable ML-based anomaly detection. Do NOT use for pipeline debugging (use debug-pipeline instead) or SLO management (use manage-slos instead). Trigger phrases: AIDA, predictive failure, alert correlation, noise reduction, anomaly detection, AI ops, predictive analysis, alert fatigue, ML alerting, intelligent alerting.
Redis client and connection guidance covering connection pooling, multiplexing, pipelining, client-side caching with RESP3, avoiding slow commands (KEYS, SMEMBERS, HGETALL), and tuning socket timeouts. Use when configuring a Redis client (redis-py, Jedis, Lettuce, NRedisStack), batching commands for throughput, eliminating per-request connection creation, iterating large keyspaces with SCAN, enabling client-side caching for read-heavy workloads, or setting connect and read timeouts.
Rules and worked examples for writing prose that does not read like AI-generated slop. Consult before writing or editing any prose.
Detect whether U.S. inflation pressure is entering a slowdown or reversal phase through the cycle turning points of the CASS Freight Index. It is used to judge whether 'inflation is cooling down' and verify whether the market's macro narrative of interest rate cuts and inflation decline is supported by real economic data.
Generate or remediate documentation with human-quality writing and style adherence. Use when creating new documentation, rewriting AI-generated content, or applying style profiles. Do not use for slop detection only (use slop-detector) or learning styles (use style-learner).
Comprehensive patterns and techniques for removing AI-generated verbosity and slop
Compose UIs with Blade components, slots, and layouts; keep templates pure and testable