Total 56,744 skills, AI & Machine Learning has 9437 skills
Showing 12 of 9437 skills
Adaptive exploration pipeline that integrates /brainstorm, /think, and /red-team with intelligent pivoting. Unlike /deepthink (which takes a fixed idea and iterates), /prospect starts with divergent brainstorming, picks the most promising vein, runs deep analysis, and — crucially — can PIVOT back to divergent thinking when: the idea dies under red-team, an adjacent opportunity surfaces during analysis, or the research reveals the real opportunity is elsewhere. Produces a prospecting report: the landscape explored, veins assayed, pivots taken, and the final stake with conviction. Use when the user says "prospect", "explore this space", "find opportunities", "what should I build", "explore and analyze", or has a domain/trend they want to both explore AND evaluate.
Ecosystem self-evolution orchestrator. Detects project lifecycle phases, evaluates agent relevance, synthesizes cross-agent knowledge, and proposes evolution actions (health checks, fitness scoring, evolution proposals).
Use when a complex MEL/SRHR task requires deep evidence synthesis before planning begins. Triggered by Ann between PHASE 1 and PHASE 2 for COMPLEX tasks, or directly by Ane for standalone literature reviews.
Interview the user relentlessly about whatever they want to work on — a plan, task, design, idea, feature, architecture decision, or anything else — until reaching shared understanding. Walk the decision tree one branch at a time, resolving dependencies between decisions. Use when the user says "grill me", wants to stress-test a plan or idea, wants to be interviewed about a design, or wants to flesh out an under-specified task.
ALWAYS invoke this command when creating, editing, or improving any CLAUDE.md file
Use when adding or configuring an MCP (Model Context Protocol) server in a Claude Code plugin. Triggers on "add mcp", "setup mcp", "configure mcp server", "add mcp.json to plugin", or any request to wire up an external MCP tool server to a plugin in this repository.
Configure human-in-the-loop gating for AI agent review actions in Claude Code. Use when setting up a project where an agent may post PR reviews, comments, merges, or edit CI configuration, and you want a cryptographically auditable approval trail with Cedar-enforced gates.
GANG entry skill. When a user types /gang, it indicates that they want to upgrade the current pane to a GANG orchestrator and start the GANG closed-loop. The skill content = run `hive gang init`, move the current pane to a new window, set up the board + skeptic, and automatically dispatch /gang-orch to take over the duty.
Set up orq.ai observability for LLM applications. Use when setting up tracing, adding the AI Router proxy, integrating OpenTelemetry, auditing existing instrumentation, or enriching traces with metadata.
Generate and curate evaluation datasets — structured generation via dimensions-tuples-NL, quick from description, expansion from existing data, plus dataset maintenance through deduplication, rebalancing, and gap-filling. Use when creating eval data, expanding test coverage, or cleaning datasets. Do NOT use when sufficient real production data exists (use analyze-trace-failures instead). Do NOT use for evaluator creation (use build-evaluator).
Explore and investigate ideas before committing to a change. Trigger: When the orchestrator launches you to think through a feature, investigate the codebase, or clarify requirements.
Explicitly save important knowledge to auto-memory with timestamp and context. Use when a discovery is too important to rely on auto-capture.