Use the Harness MCP Server when an agent needs governed access to Harness pipelines, services, environments, feature flags, cost data, and related platform resources from an MCP…
Score 70/100
SRE patterns for production service reliability: SLOs, error budgets, postmortems, and incident response.
Score 70/100
Create comprehensive operational playbook documenting organizational structure, processes, meeting rhythms, communication protocols, OKRs, tools, onboarding, and culture.
Score 70/100
Expert operations management covering process optimization, operational efficiency, resource management, and continuous improvement.
Score 70/100
Evaluate internships, jobs, clubs, labs, fellowships, and prestige opportunities by learning density, leverage, truth, people quality, and artifact potential.
Score 70/100
Use when building or reviewing Apex triggers on the Opportunity object — stage-change detection, amount rollups to Account, OpportunityTeamMember sync, or OpportunitySplit…
Score 70/100
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss.
Score 70/100
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference.
Score 70/100
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens),…
Score 70/100
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from…
Score 70/100
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2%…
Score 70/100
Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization…
Score 70/100
Suggest concrete optimizations for Claude Code usage based on historical session data. Covers cost reduction, speed improvement, error prevention, and workflow efficiency.
Score 70/100
Improve interface performance across loading speed, rendering, animations, images, and bundle size. Makes experiences faster and smoother.
Score 70/100
Optimize CLAUDE.md based on actual usage patterns. TRIGGER ON: 'optimize CLAUDE.md', 'improve CLAUDE.md', 'make CLAUDE.md better', 'trim CLAUDE.md', 'what is unused in CLAUDE.md',…
Score 70/100
Otimiza código para melhor performance, eficiência de memória e velocidade. Use quando o usuário disser "este código está lento", "otimize isso", "reduza o consumo de memória".
Score 70/100
Iteratively optimizes prompts for token efficiency by maximizing information density - reduces verbosity, removes redundancy, tightens phrasing while preserving semantic content.
Score 70/100
Use when creating or refining SKILL.md-based skills, or diagnosing weak triggering (under/over-triggering, vague descriptions, bloated context, or missing workflow guidance).
Score 70/100
Use when the user wants to optimize a tweet for the X (Twitter) algorithm before posting. Scores drafts against engagement predictors, suggests rewrites, and compares variants.
Score 70/100
Analyse et améliore un prompt existant pour obtenir de meilleurs résultats avec un LLM. À utiliser quand l'utilisateur a un prompt qui ne donne pas les résultats voulus ou veut…
Score 70/100
Optimize deep learning models using Adam, SGD, and learning rate scheduling to improve accuracy and reduce training time.
Score 70/100
Find and compare DeFi yield opportunities across protocols with APY calculations, risk assessment, and optimization recommendations.
Score 70/100
Optimize blockchain gas costs by analyzing prices, patterns, and timing. Use when checking gas prices, estimating costs, or finding optimal windows.
Score 70/100
Analyzes and optimizes application performance across frontend, backend, and database layers. Use when diagnosing slowness, improving load times, optimizing queries, reducing…
Score 70/100
Compare and optimize staking rewards across validators, protocols, and blockchains with risk assessment.
Score 70/100
Automate Optimoroute tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Get option chain data including calls and puts with strikes, bids, asks, volume, open interest, and implied volatility.
Score 70/100
Analyze option volatility by combining vol surface data, option pricing with Greeks, and historical price data to assess implied vs realized volatility.
Score 70/100
Optuna integration skill for automated hyperparameter optimization with advanced search strategies, pruning, multi-objective optimization, and visualization capabilities.
Score 70/100
Optuna Study Creator - Auto-activating skill for ML Training. Triggers on: optuna study creator, optuna study creator Part of the ML Training skill category.
Score 70/100
Integrate ora spinners with consistent styling, promise handling, and status updates for CLI progress feedback.
Score 70/100
AI/ML design and evaluation specialist covering prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, and cost optimization.
Score 70/100
Diagnose and fix Oracle Cloud Infrastructure API errors with real error codes and proven fixes. Use when encountering OCI ServiceError exceptions, auth failures, SSL issues, or…
Score 70/100
Launch, manage, and scale OCI compute instances with capacity retry logic. Use when provisioning VMs, selecting instance shapes, or handling "out of capacity" errors.
Score 70/100
Track OCI spend with the Usage API and set up budget alerts. Use when monitoring Oracle Cloud costs, creating budgets, analyzing spend by compartment or service, or optimizing…
Score 70/100
Manage OCI Object Storage — buckets, uploads, PARs, and lifecycle policies. Use when uploading objects, creating pre-authenticated requests, or configuring lifecycle rules.
Score 70/100
Self-service incident runbook for OCI outages — health probes, instance recovery, cross-AD/region failover.
Score 70/100
Set up a productive local OCI development workflow using CLI and SDK instead of the web console. Use when the OCI Console is too slow, setting up CLI profiles, or building shell…
Score 70/100
Set up programmatic monitoring, logging, and alarms for OCI resources. Use when configuring OCI Monitoring metrics, creating alarm rules, publishing custom metrics, or searching…
Score 70/100
Optimize OCI compute shapes, block volume tiers, and network throughput. Use when choosing instance shapes, configuring block volume performance, or benchmarking OCI…
Score 70/100
Wire up event-driven workflows with OCI Events, Notifications, and Functions. Use when building serverless event processing, subscribing to instance lifecycle changes, or routing…
Score 70/100
Orama is a full-text, vector, and hybrid search engine that runs in the browser, on a server, or at the edge in under 2KB.
Score 70/100
Autonomous loop runner for nexus-autoloop. Generates script sets from goals, designs operation contracts, audits live loops, and recovers state — delivering end-to-end runners…
Score 70/100
知识库 OrbitOS Obsidian Vault 共享配置。Vault 结构、格式规则、排版规范。被 orbit-* 系列 skill 自动引用；也可在知识库相关操作中直接调用以获取上下文。
Score 70/100
Use local Codex/Claude JSONL logs as evidence, then produce a human-written daily diary summary and write it into Obsidian.
Score 70/100
Classical orbital mechanics from Kepler to Hohmann. Covers the six orbital elements, Kepler's three laws, vis-viva, orbit types (circular, elliptical, parabolic, hyperbolic),…
Score 70/100
Apply the Workflow Orchestration methodology for complex, multi-step tasks — plan-first approach, subagent strategy, self-improvement loop, verification before done, elegant…
Score 70/100
Master orchestrator for cross-repo infrastructure with dependency graph dispatch
Score 70/100
Uses Git Town to keep a branch stack healthy by syncing with the main branch, rebasing dependent branches in order, opening or updating pull requests, and cleaning up after merge.
Score 70/100
Execute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.
Score 70/100
Execute orchestrate multi-agent systems with handoffs, routing, and workflows across AI providers. Use when building complex AI systems requiring agent collaboration, task…
Score 70/100
Spawns multiple AI coding agents to work on related GitHub issues concurrently using git worktrees. Use when breaking down a large feature into multiple issues, running parallel…
Score 70/100
Skills for orchestrating tasks across multiple AI providers and execution environments. Parent skill category containing native-invoke and related delegation patterns.
Score 70/100
Use when designing or reviewing Flow Orchestration for long-running, multi-user, or asynchronous business processes with stages, steps, work items, and monitoring needs.
Score 70/100
Invoke external AI CLIs via native Task agents (Claude, Codex, Gemini, Cursor). Primary mode for multi-provider orchestration with fork-terminal fallback for auth.
Score 70/100
Master coordinator for Unite-Hub workflows. Routes tasks to specialists, manages multi-agent pipelines, maintains context across runs, handles errors, and generates system…
Score 70/100
Manage user scripts and automated processes — start, stop, restart, monitor, view logs
Score 70/100
Foodora-only CLI for checking past orders and active order status (Deliveroo WIP). Use when the user asks to check food delivery orders, track a Foodora delivery, view order…
Score 70/100
Buffer and execute streaming tool calls with concurrency awareness so results appear in request order even when multiple runners overlap.
Score 70/100
Configure multi-tenant organizations, manage members and invitations, define custom roles and permissions, set up teams, and implement RBAC using Better Auth's organization…
Score 70/100