Audit the fixed context overhead every session starts with — system prompt, MCP tools, agents, CLAUDE.md, memory — measured from real transcript usage
原文语言:英语
菜单
SkillsMP 已收集 egorfedorov/claude-context-optimizer 中的 22 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 22 / 22 个已收集 Skill。
Audit the fixed context overhead every session starts with — system prompt, MCP tools, agents, CLAUDE.md, memory — measured from real transcript usage
原文语言:英语
Share learned file patterns across a team — export an anonymized digest of what's usually waste/useful/co-edited, and import a teammate's so a fresh clone benefits day one
原文语言:英语
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses
原文语言:英语
View and tune CCO's behavior thresholds — re-read warnings, cache staleness, prompt-coach length bands, and the /cco-pack budget cap
原文语言:英语
Show ContextShield status and waste protection stats; suggest or apply .contextignore rules from historical waste
原文语言:英语
Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Opus 4.8 default, full 1M context at standard price)
原文语言:英语
Health check for the context-optimizer plugin install — verifies versions, hooks, data dir, model config, and reports any issues
原文语言:英语
Build an optimal context pack for the user's task — ranked file list with offset/limit suggestions, based on git state, mentioned paths, and historical patterns
原文语言:英语
Context Control Center — one screen for budget, $ spent, tokens saved, waste, last prompt grade, the active task, and ready-to-run optimization actions
原文语言:英语
Organize work by task and track tokens/cost per task — start a task, list tasks, or mark the active one done. Pairs with /cco-pack to load minimal context per task.
原文语言:英语
Analyze the user's last prompt for clarity, scope and specificity — give a quality score and concrete suggestions to make the next prompt produce better results
原文语言:英语
Calculate monthly token savings and ROI by model
原文语言:英语
Show recent session summaries for quick context recovery
原文语言:英语
Generate a compact project map so Claude understands the codebase without opening every file
原文语言:英语
Clean up old tracking data and reset statistics
原文语言:英语
Show weekly/daily efficiency digest with score and trends
原文语言:英语
Export context report as Markdown or HTML
原文语言:英语
Manage context templates for common task types
原文语言:英语
Analyze CLAUDE.md files for token bloat and suggest optimizations
原文语言:英语
Show git-aware context suggestions for current working directory
原文语言:英语
Show detailed token ROI report across all tracked sessions
原文语言:英语
Automatically suggests optimal files to preload based on the user's task description and historical context patterns. Activates when the user starts a new task, mentions reading files, or when session context is being set up.
原文语言:英语