Loading...
Loading...
Found 52 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.
Reduce token waste by 40-60% through anti-sycophancy rules, tool-call budgets, one-pass coding, task profiles, and read-before-write enforcement. Inspired by drona23/claude-token-efficient.
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.
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.