716 skills · sorted by relevance
Monitor Power Automate across an organization's tenant using FlowStudio MCP's cached data. Review failure rates, run-health trends, flow and app inventories, and inactive owners to prepare health and compliance reports. Requires FlowStudio for Teams or MCP Pro+.
Browse registered trading strategies and compare evidence from backtests, which simulate trades on historical data. Filter by market conditions, trade counts, risk-adjusted returns, and cost feasibility, inspect evidence age, and rebuild the evidence cache from local runs.
Analyze Chrome, Edge, and other Chromium browser profiles with Hindsight to reconstruct web activity. Combine browsing history, downloads, cookies, and other stored records into a chronological timeline, with XLSX, JSON, or SQLite output for investigation.
Diagnose oh-my-codex installation and skill discovery problems by checking configuration, hooks, plugin caches, and optional Team runtime checks. Produce an evidence-based report and carry out confirmed repairs with user approval, then verify the results.
Helps choose and tune Cloud Storage FUSE mounts, which expose bucket objects through file paths. It covers cache sizing, training performance, checkpoint write safety, and cost diagnosis on GKE, Compute Engine, and Cloud Run.
Plan how an AI agent uses limited input space through reusable prompt prefixes, shorter tool outputs, summaries, and task splitting. Measure token use, response quality, and latency to choose optimizations that provide a net benefit.
Design how an AI agent edits its own working conversation history, choosing what to retain, rewrite, or remove. Covers safeguards, capacity monitoring, recovery after overflow, and the computing cost of changing earlier context.
Improve MNN's Vulkan backend by separating CPU scheduling bottlenecks from GPU computation costs. It guides operator and shader changes, new feature integration with compatibility fallbacks, and device testing to verify both correctness and end-to-end performance.
Estimate inference memory for models on Hugging Face Hub without downloading their weights. Check GPU capacity for Safetensors or GGUF files, with optional estimates for the KV cache, memory used to retain attention data during generation.
Build TypeScript services that fetch API data for display panels. Use a circuit breaker, which pauses calls after repeated failures, alongside caching and default values, while keeping API keys on the server through proxy endpoints.
Investigate how credentials can be exposed in CI/CD, the systems that build and deploy software. Covers environment variables, logs, credential stores, cloud trust settings, and runner tokens, with methods to assess access scope and defensive controls.
Configure how Dynamo routes requests to workers, then check model discovery and a chat response. Supports local and Kubernetes setups, including routing based on cached model data, with clear commands, results, and limitations.
Run builds, tests, code checks, and development servers in an Nx workspace. Choose one project, several projects, or projects affected by changes, with options for parallel execution, cached results, and failure handling.
Build GraphQL data queries and updates with separate operation files and generated types and hooks, reusable functions for React. Follow Apollo Client patterns for error messages, loading feedback, cache updates, and reusable field selections.
Explains how Squad CLI records its installed version and handles upgrades, including which files it replaces or preserves. It also covers checking npm release channels and using cached version information when assessing available updates.
Diagnose a Diverga installation by checking plugin registration, skill and cache synchronization, hooks, configuration, API key setup, and research project state. Receive pass, warning, or error results with suggested repair commands, without modifying files.
Improve the MCP server that connects claude-flow v3 to tools. It guides connection reuse, faster tool lookup, request distribution, and communication changes, with monitoring to evaluate response times, errors, memory use, and cache performance.
Search Unity's package registry and installed packages by name, ID, or description. Review available versions and installation status before adding a package, using cached results or online lookups for exact matches.
Update the NotFair plugin to its latest version by refreshing the marketplace repository, installing the release in the plugin cache, and updating installation records. Also handle update prompts raised when a skill starts.
Display a session dashboard showing Claude token usage, API costs, estimated savings from TLDR file summaries, cache reuse, and hook activity. Use it to compare compression results and check whether TLDR and automated hooks are running.
The reference agents' cache-stable request assembly, covering the static system and per-request context split, the fixed tool list, the rolling conversation breakpoint, which config fields are prompt bytes, and verification. Load when writing or reviewing a commerce agent's prompt assembly, when cache reads are zero, or when a turn's latency or cost is the question.
The English summary is being prepared. Showing the original description.
Tune Alchemy-backed reads with measured latency, cache semantics, batching, concurrency, and freshness SLOs. Use when an integration is slow or wasteful. Trigger with "optimize Alchemy performance", "cache Alchemy data", or "reduce Alchemy latency".
The English summary is being prepared. Showing the original description.
Diagnoses and safely reclaims macOS disk space: caches, logs, app remnants, large/duplicate files, Docker/OrbStack, Chromium code-sign clones, developer caches. Use when a Mac is low on storage, shows “Caching needs more space”, or before deleting anything to avoid data loss. Not for Windows/Linux or permission issues (use macos-permissions).
The English summary is being prepared. Showing the original description.
Plan a session's context window like the budget it is — what loads up front, what gets linked instead, what stays fetch-on-demand, and how to keep the stable prefix cache-friendly so repeated turns cost cents instead of dollars. Use when asked my agent keeps blowing its context, plan what to load into the session, why is every turn so expensive, or design the context for this workflow. Produces the load/link/fetch allocation, the cache-aware prefix layout, the per-turn cost shape, and the eviction rules for when the window fills anyway.
The English summary is being prepared. Showing the original description.