Loading...
Loading...
Found 2,026 Skills
gate-dex CLI market & token data skill: K-line, liquidity, trading stats, token info, security audit, rankings, new listings, chain config, and raw RPC. Read-only; no signing. Use this skill whenever the user asks for on-chain market data, token info, or security audits via the gate-dex CLI. Trigger phrases include K-line, token price, market cap, token risk, honeypot check, token rankings, new tokens, liquidity, tx stats, chain config, rpc.
Layer agentic capabilities onto a full-stack Eve app — agents, teams, memory, events, chat, and coordination. Use when designing an app where agents are primary actors, not afterthoughts.
Interviews the user one question at a time about a feature or large change, then writes a Product Requirements Document (PRD) to docs/prd/<feature>.md. The PRD captures the product-level what and why — problem, goals, user stories, acceptance criteria, constraints, risks — and avoids implementation details like class names, routes, libraries, or code paths. Invoked explicitly by name (/brainstorm-prd).
Make research code runnable and repeatable for artifact review by auditing README, dependencies, seeds, entrypoints, data instructions, result commands, and smoke tests with repro_check.py. Use for smoke tests, seed pinning, environment capture, reproducibility checks, or works-on-my-machine cleanup.
ECS Health Inspection - Perform comprehensive health inspection on Alibaba Cloud ECS instances. Checks CPU usage, system load, memory usage, disk IO (BPS and IOPS), network traffic, disk capacity, and GPU metrics (when applicable). Generates a structured HTML inspection report with findings and recommendations. Use when users request ECS health inspection, instance health check, performance inspection, resource usage report, or system health status of an ECS instance.
Audit MEMORY.md against the memory discipline — oversized sections, settled multi-session patterns that belong in knowledge/concepts/, stacked chronicle blocks, stale entries. Produces a move plan as a table for approval, then executes the approved moves atomically. Use when the SessionStart hook reports a tripped cap, when PreCompact blocks on an oversized cache, or when the user says "/memory-kit:memory-audit", "audit memory", "проверь память", "почисти память". Refuses only when no cap is tripped AND no settled-pattern candidate exists.
Map triaged findings to the correct Azure DevOps work item types for the TARGET project's process, and emit backlog_input.json ready for creation. Use this AFTER triage and BEFORE creating items — when the user asks "what type should these be", "make these into work items / tickets", "turn these findings into a backlog", "classify these for ADO", or "build the backlog input". The type you choose MUST exist on the target board: a Basic-process project has no Bug or User Story, so picking those silently fails at creation time. This skill discovers the project's process first, applies industry typing rules (defect vs new capability vs grouping parent), maps severity to Priority, builds the per-type fields (titles, tags, repro/description as escaped HTML), carries each finding's `key` through, and hands off to ado-create-work-items.
Use the HTTP client with sensible timeouts, retries, and backoff; capture context and handle failures explicitly
Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
Guide for setup Serena MCP server for semantic code retrieval and editing capabilities
Unified learning-and-memory system: confidence-scored instincts (observe-hypothesize-confirm, stored in .claude/instincts.md), user corrections captured as permanent rules in MEMORY.md, and organic discoveries logged to .claude/learning-log.md. Includes status, export, and import modes. Load this skill when you notice a recurring pattern, a user corrects your output, or you discover something non-obvious. Triggers: "show instincts", "what have you learned", "list instincts", "export instincts", "share instincts", "import instincts", "load instincts from", "learn this", "I think they always", "notice a pattern", "instinct", "hypothesis", "confidence", "learn from mistakes", "remember this", "don't do that again", "log this", "document this finding", "gotcha", "what did we learn", "learnings", "discoveries", or at session start (to load existing knowledge).
Run bounded, evidence-driven training research through W&B Launch: assess project readiness, establish launchable code and queue capacity, smoke-test real jobs, execute serial trials, compare metrics, and persist resumable research state. Use when a coding agent is asked to autonomously test training hypotheses or tune a real W&B-tracked workload.