Loading...
Loading...
Found 51 Skills
Token optimization best practices for cost-effective Claude Code usage. Automatically applies efficient file reading, command execution, and output handling strategies. Includes model selection guidance (Opus for learning, Sonnet for development/debugging). Prefers bash commands over reading files.
Compressed communication using symbols and abbreviations. Use when context is limited or brevity is needed.
Guides research engineering and science on LLM tokens—hypotheses about context use, tokenization, compression, and inference efficiency; rigorous benchmarks (tokens per task, quality–cost Pareto); ablation design; instrumentation and reproducible logs; and research memos that inform product decisions. Use when designing token-efficiency experiments, measuring context utilization, comparing compression or routing methods, analyzing tokenizer effects, or writing technical reports on token/cost trade-offs—not for phased cost roadmaps and owners (ai-token-improvement-plan-engineer), production context pipeline implementation (ai-context-engineer), single-prompt edits (prompt-engineer), general non-token AI research (ai-researcher), or shipping features (ai-engineer).
Creates or updates professional-grade agent skills (SKILL.md + optional scripts/references/assets) with strict validation and an iterative generator↔critic workflow. Use when: you want a new skill, want to refactor an existing skill for clarity/token-efficiency, or want to reach an A-grade rubric score.
Guides ML/research engineering for safeguards—safety classifier development, harm benchmarks and eval suites, labeled dataset design, fine-tuning and ablations, calibration and slice analysis, attack-surface research memos, and promotion criteria for new moderation models. Use when building or evaluating guardrail models, designing safety benchmarks, measuring precision/recall on policy categories, comparing mitigation techniques, or writing research reports on classifier improvements—not for production inference gateways (ml-infrastructure-engineer-safeguards), PII/leakage privacy research (privacy-research-engineer-safeguards), red-team attack campaigns (ai-redteam), AI governance policy (ai-risk-governance), general non-safety research (ai-researcher), or token-efficiency studies (research-engineer-scientist-tokens).
Ultra-compressed Chinese communication mode. Express complete technical information with fewer Chinese characters, while retaining code, terminology, original error messages and key constraints. Supported intensity levels: lite, full (default), ultra. Applicable when users mention "Chinese caveman", "caveman mode", "shorter", "fewer words", "use Chinese caveman", or call /caveman-cn. Also applicable to Chinese conversations where token saving is explicitly required.
ROOT ORCHESTRATOR ONLY. Explicit-use token-aware Codex workflow with leaf workers, DAG gating, state ledger, retry policy, and no nested delegation.
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra, ru-lite, ru-full, ru-ultra, ru-notes. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Russian mode: "пещерный режим", "режим пещерного", "/caveman ru", "/caveman-ru". Also auto-triggers when token efficiency is requested.
Preserve critical session state when compacting context. Use when context window is filling up and you need to summarize/reduce while keeping essential debugging information.
balancing accuracy with token efficiency.
Advanced context engineering techniques for AI agents. Token-efficient plugins improving output quality through structured reasoning, reflection loops, and multi-agent patterns.
Token-efficient codebase exploration using RepoPrompt CLI. Use when user says "use rp to..." or "use repoprompt to..." followed by explore, find, understand, search, or similar actions.