技能检索
kimi-usage-monitor
Monitor Kimi K2.5 API usage and quota from the Kimi console. Use when the agent needs to (1) Check remaining usage percentage and reset timers, (2) Make autonomous decisions about task prioritization based on available quota, (3) Monitor rate limit status before starting intensive operations, (4) Log usage patterns over time for resource planning. Essential for self-managing agents operating under quota constraints.
context-compactor
Token-based context compaction for local models (MLX, llama.cpp, Ollama) that don't report context limits.
context-sentinel
Monitors session context and automatically manages model switching based on a cascading protocol. Use as part of a heartbeat or cron job to maintain session health and optimize token usage.
norman-tax-deduction-finder
Scan transactions for potentially missed tax deductions and suggest proper categorization. Use when the user asks about saving taxes, Steueroptimierung, deductible expenses, Betriebsausgaben, or wants to check if they are missing any write-offs.
argus-edge
Argus-style prediction market edge detection and betting strategy. Computes expected value from TA-implied probability vs market odds, sizes bets via Kelly criterion, and applies freshness/consensus guards. Validated at 77.8% win rate on primary (fresh) Polymarket bets. Use for prediction market betting, EV calculation, Polymarket strategy, or market making.
agent-mbti
AI Agent personality diagnosis and configuration system based on MBTI framework. Use when users want to (1) test/diagnose an Agent's personality type, (2) understand the gap between Agent's actual personality and user's desired personality, (3) generate configuration recommendations to adjust Agent behavior, (4) customize Agent's communication style, proactivity, reasoning approach, or execution patterns. Supports both free tier (quick assessment) and premium tier (full 93-question assessment with detailed diagnostics).
chitin
Personality persistence for AI agents. Remember how you think, not just what happened. Structured insights that survive session restarts.
consensus-interact
Use the open-source @consensus-tools/consensus-tools engine to run multi-LLM policy-based decision workflows: post jobs, collect submissions, cast votes, and resolve outcomes with customizable consensus logic gates. The engine is local-first by design; consensus.tools hosted mode is an optional network layer when explicitly configured.
hz-context-optimizer
This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.