Skills tagged: token-optimization

• session-retro - Review sessions to analyze errors and extract improvements

  session-retroretrospectiveroot-cause-analysisprocess-improvement

  ★ 149 · Updated 2026-09-23

  Reviews conversation history to analyze error root causes, propose process fixes, extract successful patterns, and evaluate token efficiency.

  ⚙ Scan conversation for correction signals⚙ Classify session outcomes⚙ Analyze error root causes
• context-engineering - Context Engineering for Token Optimization

  context-engineeringtoken-optimizationcontext-windowprogressive-disclosure

  ★ 2 · Updated 2026-09-20

  Maximizes agent output quality while minimizing token expenditure through relevance scoring, context compression, budget allocation, and context reclamation.

  ⚙ Score relevance of context sources⚙ Compress conversation history via summarization⚙ Enforce context token budget limits
• code-mode - Add code mode tool to existing MCP servers

  mcpcode-modesandboxcontext-reduction

  ★ 21 · Updated 2026-09-20

  Runs LLM-written processing scripts against large API responses in a sandboxed runtime to reduce context size.

  ⚙ Understand existing MCP server⚙ Select sandboxed runtime⚙ Plan implementation steps
• config-audit - Audit Claude Code Configuration Artifacts

  claude-codeconfig-audittoken-optimizationstatic-analysis

  ★ 0 · Updated 2026-09-17

  Audits Claude Code hooks, skills, CLAUDE.md, and agents for over-engineering, redundancy, and token waste using model routing.

  ⚙ Discover configuration artifacts⚙ Fetch official documentation⚙ Analyze artifact configuration patterns
• geminiignore-finops - Configure and optimize .geminiignore files for AI FinOps

  finopscontext-managementtoken-optimizationgeminiignore

  ★ 1 · Updated 2026-09-16

  Constructs and maintains .geminiignore files to optimize AI context window usage and reduce token consumption costs across project repositories.

  ⚙ Analyze workspace tech stack⚙ Create or update .geminiignore⚙ Apply category exclusion rules
• token-efficiency-coach - Diagnose and reduce Claude Code token usage

  token-optimizationclaude-codecontext-managementmcp

  ★ 0 · Updated 2026-09-15

  Diagnoses and reduces Claude Code token usage and context consumption by analyzing system configuration, session state, and workflow habits.

  ⚙ Diagnose fixed configuration costs⚙ Measure session variable costs⚙ Evaluate workflow operational habits
• create-expert-skill - Create production-ready skills from expert knowledge.

  skill-creationdomain-expertiseontologytoken-optimization

  ★ 26 · Updated 2026-09-14

  Extracts domain expertise and system ontologies to create production-ready skills with progressive knowledge loading and script automation.

  ⚙ Assess skill creation suitability⚙ Discover domain expertise and ontologies⚙ Design multi-layer skill architecture
• rtk-optimizer - Wrap verbose shell commands with RTK to reduce tokens

  shelltoken-optimizationrtkcli

  ★ 17 · Updated 2026-09-14

  Detects high-verbosity shell commands and wraps them with RTK to reduce context window token consumption.

  ⚙ Detect high-verbosity shell commands⚙ Suggest RTK command wrappers⚙ Execute shell commands with RTK
• caveman - Ultra-compressed communication mode to reduce token usage

  token-optimizationcommunication-styletext-compressioncaveman

  ★ 1 · Updated 2026-09-13

  Compresses text responses to reduce token usage while preserving technical accuracy across multiple intensity levels.

  ⚙ Compress technical text responses⚙ Switch compression intensity levels⚙ Preserve exact technical terms
• finops - Audit cloud costs, token usage, and pricing models

  finopscloud-costtoken-optimizationpricing-models

  ★ 24 · Updated 2026-09-12

  Audit cloud costs, optimize API token usage, and evaluate pricing models.

  ⚙ Audit cloud costs⚙ Optimize API token usage⚙ Evaluate pricing models
• caveman - Ultra-compressed communication mode for saving tokens

  communicationtoken-optimizationmodecaveman

  ★ 0 · Updated 2026-09-11

  Cuts token usage by removing filler, articles, and pleasantries while keeping technical accuracy.

  ⚙ Compress responses to reduce tokens⚙ Remove filler words and articles⚙ Abbreviate common technical terms
• caveman - Ultra-compressed communication mode for token reduction.

  communicationtoken-optimizationcaveman-modeconcise-responses

  ★ 0 · Updated 2026-09-10

  Reduces token usage by removing filler, articles, and pleasantries while maintaining technical accuracy.

  ⚙ Compress responses to save tokens⚙ Remove filler words and pleasantries⚙ Preserve technical accuracy and code
• caveman - Ultra-compressed mode to cut token usage.

  communicationtoken-optimizationconcise

  ★ 0 · Updated 2026-09-10

  Cuts token usage by removing filler, articles, and pleasantries while keeping full technical accuracy.

  ⚙ Compress technical responses⚙ Drop filler words and pleasantries⚙ Abbreviate common technical terms
• cc-safe-setup - Safety-first configuration for Claude Code

  claude-codesafety-hookssecuritygit-safety

  ★ 6 · Updated 2026-09-10

  Installs pre-built safety hooks into Claude Code to block dangerous file operations, git disasters, and credential leaks.

  ⚙ Install pre-built safety hooks⚙ Block dangerous file deletions⚙ Prevent force pushing to main
• oktk - CLI Output Compressor for LLMs

  clitoken-optimizationllmcompression

  ★ 33 · Updated 2026-09-09

  Compresses CLI command outputs before sending them to LLMs to reduce token consumption.

  ⚙ Intercept command outputs⚙ Detect command types⚙ Apply command-specific filters
• moai-library-toon - TOON YAML Agent/Workflow Format

  TOONYAMLagent-definitionworkflow-definition

  ★ 602 · Updated 2026-06-15

  YAML-based token-efficient agent and workflow definitions with BMAD-style hierarchical structure

  ⚙ create agent definition⚙ create workflow definition⚙ validate workflow
• progressive-loading - Progressive module loading for skills

  progressive-loadingmodularitycontext-awarenesstoken-optimization

  ★ 602 · Updated 2026-05-28

  Implements hub-and-spoke lazy loading to minimize token usage in large skills

  ⚙ detect context⚙ select modules⚙ manage token budget
• tokenranger - Compress LLM Context with TokenRanger

  performancecloud-llmcontext-compressiontoken-optimization

  ★ 816 · Updated 2026-03-20

  Compress session context through local Ollama SLM before sending to cloud LLMs

  ⚙ install plugin⚙ setup sidecar⚙ configure settings
• using-markdown-new - Web Content Fetching via markdown.new Service

  web-fetchingcontent-conversiontoken-optimization

  ★ 0 · Updated 2026-03-09

  Converts web URLs to clean Markdown format for efficient content retrieval

  ⚙ fetch web content⚙ convert URLs to Markdown⚙ optimize token usage
• ccg-latent - CCG Latent Chain Mode - Token-efficient hidden-state reasoning

  code-developmenttoken-optimizationmulti-step-workflowhidden-state-reasoning

  ★ 8 · Updated 2026-03-09

  Execute multi-step development tasks using hidden-state reasoning to reduce token usage

  ⚙ create task context⚙ retrieve current context⚙ update context delta

Scroll to load more