kimi
Call the Kimi API (kimi-k3, kimi-k2.7-code, kimi-k2.6, kimi-k2.5) through RunAPI using OpenAI-compatible Chat Completions. Use for Kimi text chat, streaming,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,650 results
Hooks Automation
Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks,…
ReasoningBank with AgentDB
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and…
V3 MCP Optimization
MCP server optimization and transport layer enhancement for claude-flow v3. Implements connection pooling, load balancing, tool registry optimization, and…
V3 Memory Unification
Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid…
cross-host-federation
Join and operate a signed cross-host agentbbs federation, and coordinate work claims across nodes. Use when: connecting ruflo agents across machines, sharing…
agent-output-parsing
Parsing JSON envelope output from Configurator CLI commands. Use whenever processing exit codes, JSON envelopes, drill-down workflows, or building automation…
sales-callminer
CallMiner platform help — enterprise conversation analytics (Eureka) with omnichannel interaction capture, automated QA scoring, agent coaching, real-time…
trading-signals-skill
Expert trading partner for Options, Stocks, Crypto, Commodities, Gold, Silver, Oil, VIX, and Forex. Covers technical analysis (Elliott Wave, Wyckoff,…
interview
Ask clarifying questions before implementing. Only trigger on `/interview`.
jev-cli
Use the `jev` command-line tool (an unofficial, open-source CLI for TypeSafe AI's Jev model) to get calibrated probabilities for typed questions about text or…
use-codex
Delegate a coding task to the OpenAI Codex CLI: codebase Q&A, well-specified implementation, mechanical edits at scale, adversarial second opinions, or bugs…
llm-friendly-context
Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or…
AgentBroPet
Create, repair, validate, visually QA, and package AgentBro/Codex-compatible animated pet spritesheets from concepts, brand cues, generated images, or visual…
setup-pstack
Configure which host-supported roles or models pstack uses per workflow role. Detects the live host inventory and writes portable project-local configuration.…
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
codex-subagent
Launch Codex CLI as an isolated subagent for bounded coding, review, or verification tasks.
research-prompt
Turn vague research needs into one precise deep-research prompt with context and output criteria.
unsloth-finetuning
Fine-tune and post-train LLMs with Unsloth Core on a single consumer GPU: VRAM sizing, LoRA/QLoRA, GRPO/DPO, chat-template correctness, and GGUF export.
subagent-driven
Use when executing implementation plans with independent tasks in the current session
cortex-agents-with-custom-tools-tutorial
Advanced tutorial teaching Snowflake Cortex Agents with custom tools. Extends the base tutorial by adding stored procedure-based tools (inventory lookup, price…
soia-dev-agent-cli-dispatch
Controlled dispatch of external AI Agent CLIs, selecting verified models, isolating working directories, and returning model, usage, cost, and verification evidence. Triggers: "assign work to external AI", "call DeepCode/Pi/agy", "multi-CLI dispatch"
soia-meta-find-skill
Retrieve and load SOIA ecosystem skills on demand—web clipping/cloud drive/knowledge distillation/new media publishing/code review and terminal operations/design diagrams/product PRD/software testing/software release/office collaboration/education courses/environment setup/ecosystem management. Just state your need to retrieve, locate, and read in the corresponding skill as needed.
reflect
Analyze session history for learnings and persist to skills. Solves "memory zero" - correct once, never again.