Show cost trends across multiple workflow sessions, surfacing expensive operations, spending patterns, and outliers
Use when a change may increase infrastructure or runtime cost (compute, storage, network egress, third-party API calls, observability volume) and the team needs a focused…
Claude API cost awareness — token estimation, cost drivers, and efficiency strategies for Claude Code sessions
Standardized cost-estimation framework for great_cto plans. Forces explicit LLM cost, infra cost, human-supervision time, and the (defensible) human-equivalent comparison.
See the main Cloud Cost Models skill for comprehensive coverage of cost modeling and pricing strategies.
Techniques for gaining visibility into cloud spending, attributing costs to business units, and detecting financial anomalies. — from general/hello-world-templates
Techniques for gaining visibility into cloud spending, attributing costs to business units, and detecting financial anomalies. — from majiayu000/claude-skill-registry
Optimize cloud costs through resource rightsizing, tagging strategies, reserved instances, and spending analysis.
Optimize cloud costs through resource rightsizing, tagging strategies, reserved instances, and spending analysis.
Cost Optimization Analyzer - Auto-activating skill for AWS Skills. Triggers on: cost optimization analyzer, cost optimization analyzer Part of the AWS Skills skill category.
Cloud cost optimization, token/API cost tracking, build time optimization, and FinOps patterns
Comprehensive procedures for analyzing, optimizing, and monitoring LLM costs and performance in Myco's agent harness system.
Review system costs and propose reductions. Use when a senior developer needs cost-saving recommendations.
Analyze token usage patterns and recommend cost optimizations with estimated savings
Implement cost-optimized LLM routing with NO OpenAI. Use tiered model selection (DeepSeek, Haiku, Sonnet) to achieve 70-90% cost savings.
Audit construction project management software for budget tracking accuracy, earned value management (EVM) formula correctness, risk factor modeling, schedule-cost integration,…
Estimate and control costs for Solana apps: RPC, indexing, storage, bots, and on-chain fees. Use for budgeting and scaling.
Predict construction project costs using Machine Learning. Use Linear Regression, K-Nearest Neighbors, and Random Forest models on historical project data.
Adds cost (input + output tokens × model price) and latency (p50, p95) to eval results, plots model options on a Pareto frontier, and produces a quality-per-dollar composite score…
Macht Untersuchungskosten und Schäden gegen verantwortliche Mitarbeiter und Organmitglieder geltend – § 93 AktG, § 249 BGB, Verjährung im Internal Investigations Praxis.
Generate a cost report showing token usage and USD costs by agent and model
Analyze and optimize cost structures for profitability. TRIGGERS - Use when user needs help with cost-structure related tasks.
Understand which costs are fixed, variable, and step, so you know how profit responds to volume and where cuts actually help.
Auto-capture per-session token usage from the Claude Code session jsonl and persist to the cost-tracking namespace
Record or summarise LLM / service spend in the JSONL ledger. Auto-invoke when the user asks about "cost", "spend", "budget", "how much did X cost".
Track API token costs for specific operations in Claude Code. Use when the user invokes /cost-tracking to start measuring costs, or says "stop tracking", "stop cost tracking", or…
Read every docs/benchmarks/runs/*.json and surface drift in win rate, latency, escalation rate, and LLM-baseline cost over time
Audit LLM token cost estimates against actual API usage. Activate on 'cost verification', 'token estimate accuracy', 'API cost audit', 'estimation variance'.
Look up Costa Rican companies and taxpayers for free by cedula juridica via the Ministerio de Hacienda public JSON endpoint (api.hacienda.go.cr) - the same keyless API that Costa…
Pull a CoStar comp set (sale or lease) for a Lee Raleigh broker, applying behavioral rules from the SOP. Drives CoStar via the Claude in Chrome extension.
Build transparent, stage-based legal cost estimates and budgets with staffing, rates, hours, assumptions, exclusions, disbursements, taxes, scenarios, contingencies, and change…
Use when a task needs the judgment of a costume attendant/dresser — planning or timing a quick change, building a costume plot or track sheet, deciding a laundry/repair rotation,…
Use when a task needs the judgment of a Costume Designer — deciding build vs. rent vs. buy for a specific garment, budgeting a production's costume-shop spend across principals…
Local text-to-speech using Alibaba's CosyVoice3 on macOS Apple Silicon. Supports Chinese, English, Japanese, Korean, and 18+ Chinese dialects.
알고리즘 문제를 분석하여 고등학교 수학 해설집 스타일의 구조화된 해설을 작성하고, [카테고리]/[문제이름]/README.md 에 저장합니다. "문제 분석", "문제 풀이 분석", "cote analysis" 등의 요청에 트리거됩니다.
LeetCode 문제 풀이 템플릿을 자동 생성합니다. "leetcode", "릿코드", "LeetCode 문제", "leetcode 템플릿" 등의 요청에 트리거됩니다.
Coterie Insurance integration. Manage data, records, and automate workflows. Use when the user wants to interact with Coterie Insurance data.
Cotif: Schriftsatz-, Brief- und Memo-Bausteine: Cotif: Schriftsatz-, Brief- und Memo-Bausteine.
Consulta cotizaciones Pix en ComparaPix para comparar apps por simbolo y precio. Usar cuando el usuario pida cotizacion pix, mejor app para pagar con pix, BRLARS/BRLUSD/BRLUSDT,…
Build a beginner running plan from wherever you are to a real goal — first nonstop mile, 5K, or 10K — that builds up slowly enough to avoid injury.
Couchbase integration. Manage data, records, and automate workflows. Use when the user wants to interact with Couchbase data.
Obsidian LiveSync の CouchDbClient の構造と使用方法を説明します。CouchDbRepository トレイトの実装方法、HTTP プロキシパターン（forward_request）、longpoll リクエストの処理、メトリクス収集、ヘルスチェックの実装を理解・拡張する際に使用します。CouchDB…
Council Chamber orchestration with Memory Bridge. Single session, multiple personas, structured deliberation.
Multi-model AI council for actionable project advice. Leverages Gemini 3 Flash and GPT-5.2 skills in parallel, then synthesizes through an Opus Judge for stage-appropriate,…
Build a personalized team of AI agent personas for OpenClaw. Interviews the user, analyzes their workflow, then creates specialized agents with distinct personalities,…
Use when user wants to ask the AI council a question, get multiple AI perspectives, or consult with both Codex and Gemini.
Use for code review and quality feedback from both Codex and Gemini. Triggers on "council review code", "council code review", "have council review this", "get council feedback on…
Use for multi-perspective analysis with both Codex and Gemini exploring different viewpoints. Triggers on "council perspectives", "pros and cons from council", "council evaluate…
Multi-perspective analysis methodology for complex decisions. Dynamically generates relevant expert viewpoints, consults each perspective systematically, and synthesizes insights…
Overview of 7 core perspectives with variable naming system. Use when need to understand the full council structure, adapt perspective names to domains, or see the complete…
Multi-agent debate system. USE WHEN council, debate, perspectives, agents discuss. SkillSearch('council') for docs.
Get multi-model AI consensus on complex questions using Claude, Codex, and Gemini
Quality gate using LLM Council multi-model consensus for CI/CD pipelines. Use for automated approval workflows and pipeline quality checks.
Adversarial parallel comparison — runs the SAME task across multiple model tiers and/or providers in parallel, then surfaces where each model disagrees, fails, or hallucinates.
Add one optional external Codex critique after the existing council has produced a decision draft. Use when an ambiguous, high-consequence decision would benefit from a separate…
Convene 6 intellectual personas across multiple LLM providers for hard decisions. Each persona runs on a different provider for genuinely different reasoning — not costume changes…
Send an idea to the Council of the Wise for multi-perspective feedback. Spawns sub-agents to analyze from multiple expert perspectives.
Orchestrates multi-model LLM consensus through a three-phase deliberation protocol. Use when you need collaborative AI review, multi-model problem-solving, code review from…
Invoke before a high-cost-to-reverse decision, together with the Council posture that will wear it — queries episodic memory (~/.claude/epistemic/) and lists up to 3 past cases…
Run a multi-persona LLM-council review of an idea using Claude Code subagents — six personas (Operator, Financier, Skeptic, Visionary, Customer Advocate, Strategist) each review…