Responde consultas rápidas de derecho laboral con referencia a artículos del ET y convenio colectivo — from betobetico/claude-para-abogados
AUTO-TRIGGER: Apply this skill when the user is preparing to present findings, recommendations, or results to a consulting client.
Runs structured technical due diligence on a vendor, acquisition target, or strategic partner; produces a risk-ranked report with findings, evidence, and a recommendation
Coordinates multi-channel incident response for a consulting engagement - drafts war-room updates, status-page entries, client comms, and the post-incident review; use when a…
Turns a directory of per-client engagement files into a board-ready portfolio status report; use when preparing a weekly digest, a steering-committee briefing, or any…
分析consumer lending reviewer相关互联网金融合规问题。 覆盖：监管框架、资质要求、合规要点、违规风险。 适用情形：用户提及consumer lending reviewer相关事项。
Contencioso-administrativo — guía a través del recurso contencioso- administrativo contra actos de la Administración. Plazos, legitimación, medidas cautelares, costas.
Guide for using /compact (Claude Code built-in) with the pre-compact save pipeline. Shows what gets saved before compression and what gets reinjected after.
Reduce Claude AI token consumption by 5x-27x using prompt-native workflows and structural code manifests.
Credit Maximizer v8.4.0 — 5D router (model×effort×version×context×dispatch) + auto-dispatch to specialized agents/skills + cross-provider session bridge.
**WORKFLOW SKILL** — Structured context analysis before acting. USE FOR: questioning assumptions, mapping dependencies, identifying blind spots, validating scope of any task or…
Begin a work session on a Contextia task. Loads full context including project identity, relevant specs, norms, and previous session logs.
Alias for /gdd:resume — restore session context from the most recent checkpoint.
Recover actionable context from a prior Codex CLI session's local rollout files and continue interrupted work without running `codex resume`.
Delegate the task to a fresh background agent that continues it NOW — produce a save-point, then launch a detached claude --bg session seeded with the resume prompt.
Retoma um batch SDD em andamento. Use quando houver delta operacional novo, mudanças humanas em sdd ou batches, ou quando for preciso continuar a mesma rodada sem reiniciar a…
Download CI Doctor artifacts from a completed prow job and set up a local workdir for continued analysis
Ragas 기반 품질·안전 평가를 매 배포 직후와 매 1시간 cron으로 실행하여 faithfulness, answer relevance, context precision, toxicity, PII leakage 지표를 측정한다.
Generates a board-grade PPTX deck for the contract approval committee — cover, recommendation, financial summary, deviations table, risk register, decision-ask slide.
Captures the business intent behind a contract before any drafting happens. A short intake interview — who, what, why, when, how much, what's the risk tolerance — and produces a…
Generates a multi-tab interactive HTML dashboard across a portfolio of contracts — severity counts, renewal timeline, deviation heat map, spend exposure, cancel-by calendar,…
Produces a one-page executive summary of a contract or contract review — for a CEO, CFO, GM, or business owner who needs to decide in 90 seconds whether to sign, push back, or…
Drafts a first-pass contract document from a populated Contract Brief — pulls the matching template (MSA, SOW, NDA, order form, amendment), inserts the playbook's standard…
Generates a polished, printable, standalone HTML report from a contract review, redline, or amendment-history output.
Audit commercial and vendor agreements to identify hidden risks, asymmetrical clauses, and compliance issues under Indonesian law, outputting a Contract Risk Score (0-100).
Guía para las primeras contrataciones de una startup: tipos de contrato, convenio colectivo aplicable, coste real, alternativas (autónomos, becarios) y riesgos (falso aut — from…
Contrata (recruta) um novo agente especialista para compor o squad. Agentes de nível 5+ (Especialista) podem sugerir contratações.
Read-only nomination brief for a named GitHub contributor on . Aggregates GitHub activity across all contribution tracks plus maintainer-supplied off-GitHub signal, and…
Read-only readiness tracker that maps a contributor's GitHub activity against the adopter's PMC-declared committer or PMC thresholds and surfaces a traffic-light brief (Not yet /…
控制缺陷评估 — 对发现的内部控制缺陷进行评估，确定缺陷等级（重大/重要/一般）， 分析根本原因，并制定整改计划。 适用情形：控制测试发现偏差、审计检查发现问题或业务流程出现重大事故时执行。 核心：缺陷等级评估 + 财务影响量化 + 整改计划制定。
Audit and improve project conventions files (AGENTS.md, CLAUDE.md, GEMINI.md). Scans for all conventions files, evaluates quality against a scoring rubric, outputs a quality…
Convert markdown paper (with LaTeX math, tables, figures) to publication-quality PDF via Mermaid + MathJax + Puppeteer pipeline.
This skill should be used when the user asks to "convert this video", "change format to mp4", "trim from X to Y", "cut the first X seconds", "speed up this video", "slow motion",…
Check for a published coordinator update and advise a preserve-by-default migration path — never a blind overwrite.
COPD management - lung function monitoring (FEV1), symptom assessment (CAT, mMRC), exacerbation tracking, and vaccination records
Review Copilot comments on a GitHub PR, validate each suggestion, apply valid fixes, commit, reply with commit links, and resolve threads.
Complete guide for migrating from Apache Cordova to Capacitor. Use this skill when users need to modernize a Cordova/PhoneGap app to Capacitor, migrate plugins, or understand…
Collaborative brainstorming mode for thinking through problems, ideas, and features before planning. Use when the user wants to discuss, explore ideas, or think through a problem…
Audit Core Web Vitals (LCP, INP, CLS) for a URL list or sitemap via PageSpeed Insights and CrUX — producing a per-URL scorecard, worst-offender summary, and root-cause remediation…
CoreAI:Zeus orienta setup e contexto, organiza decisões e encaminha trabalho para skills instaladas com cliente ContextOS validado.
Deep Corefall BP-LEVEL closure review (BP0..BP12) with T-CAPTURE evidence, grading.json LLM-graded verdicts, Self-Play Validation Matrix, AI-Agent Self-Test Report, Universal…
extract/提取/promote/整理/归档/digest L4-inbox 收件箱, 按三轴 (抗遗忘度/强度/复用面) 路由到 L1-long/L2-mid/L3-short/项目/领域, 默认 --apply 落盘 + 增量游标 (--dry-run opt-in 仅出 JSON plan 预览).
lint / 校验 / 体检 / audit / 死链 / 孤儿 / 规范化 / frontmatter — cortex 知识库与记忆树的合规检查与可逆 autofix。覆盖 wikilink 死链、frontmatter 缺字段、命名违规、目录同构、孤儿页、等级语义反写、脚本目录用途混淆等 7 类规则。默认 --fix 落盘修复；--check…
Compute cost of goods sold, absorption vs variable costing, and simple product costing for Indonesian SME operations.
MAD-based outlier detection on session spend. Robust to the very outliers it hunts (unlike mean+sigma).
Run the corpus benchmark — booster locally, optional Gemini/Sonnet/Opus baselines — and persist a verifiable measured-vs-claimed table
Compare 2-5 investment or decision options using NPV, IRR, payback, profitability index, and qualitative strategic weighting — with sensitivity analysis, risk adjustment, and a…
Apply a simple code transform via agent-booster's WASM engine — sub-millisecond, deterministic, $0 (no LLM call). Companion to cost-booster-route.
Route tasks through hooks_route, partition by Agent Booster availability, and report Tier 1 bypass utilization with $0 cost
Read accumulated cost-tracking spend + budget config, compute utilization, emit 50/75/90/100% alert ladder
Burn-rate trend over time with optional drift-alert exit code. Bins session spend into buckets, surfaces window-over-window delta, and can exit 1 when latest bucket exceeds prior…
成本中心绩效分析 — 分析各成本中心成本绩效，评估产出效率和成本控制水平。 适用情形：月度/季度成本中心绩效评估时执行，从 [ERP]/[COST]/[MES] 获取数据， 计算各成本中心单位成本/成本效率，评估绩效等级，归因差异来源。 核心：单位成本 + 成本效率 + 产能利用率 + 责任归属。
Wrap getTokenOptimizer().getCompactContext() to retrieve compacted ReasoningBank context for cost-analysis queries; report bridge-reported tokensSaved
成本控制主流程 — 整合标准成本差异 + 费用率分析 + 成本中心绩效的综合成本管理。 适用情形：月度成本分析时执行，整合 standard-cost-variance、 expense-ratio-analysis 和 cost-center-performance，输出完整的成本控制报告。 核心：成本监控 → 差异诊断 → 责任落实 → 改善跟踪。
Multi-baseline counterfactual cost analysis. Compares actual session spend to hypothetical always-haiku / always-sonnet / always-opus routing baselines.
Snapshot delta between two cost-summary JSON outputs. PR-level cost regression detection — answers "what changed between these two specific snapshots?".
Estimate the cost of a task before starting it. Analyzes task complexity, predicts token usage, and compares cost across all Claude models.
Export cost-tracking telemetry in Prometheus textfile or webhook JSON formats — for external observability (Grafana, Datadog, custom dashboards)
AWS Pricing과 Cost Explorer를 MCP로 조회하여 agent별 비용 귀속을 집계하고 예산 alert을 발행하며, 사용 패턴이 정당하면 Opus → Sonnet → Haiku 모델 다운그레이드를 권고한다.
Per-session cost and token budget tracking for AI coding agents. Monitors cumulative spend, warns at thresholds, and enforces limits with three modes: reject (stop work), alert…