'Structured escalation with evidence. Surfaces blocking issues for human decision, referencing the Manifest hierarchy.'

Use to govern executive involvement, cross-functional response, and risk

Create or update escalation rules for a decision area

ethicist-analyst

Evaluation framework patterns for RAG and LLMs, including faithfulness metrics, synthetic dataset generation, and LLM-as-a-judge patterns. Triggers: ragas, deepeval, llm-eval, faithfulness, hallucination-check, synthetic-data.

This skill should be used when evaluating the logical flow, structure, readability, and overall quality of research paper text. Use for assessing academic writing targeting top-tier computer science conferences.

Make an evidence-based hiring decision and produce a Candidate Evaluation Decision Pack (criteria + scorecard, signal log, work sample/trial plan + rubric, reference check script + summary, decision memo). Use for candidate evaluation, hiring decisions, reference checks, work samples/take-homes, and hiring bar calibration. Category: Hiring & Teams.

Help the user make clearer decisions between competing options using frameworks and mental models from 40 product leaders.

Design event-driven architectures using Kafka, RabbitMQ, event sourcing, CQRS, and saga patterns. Activates when users need help with event-driven design, message queues, event sourcing, or asynchronous communication patterns.

Implements Clix event tracking (Clix.trackEvent) with consistent naming, safe

Atomic insights that remain true and useful over time.

Use para implementar registro de evidências, eventos de domínio e listeners no Laravel.

EdgeVLA - Open-source edge vision-language-action model for robotics. Standardizes Open-X Embodiment datasets for consistent VLA training and deployment.

Run python examples in auto mode with logging, rerun helpers, and background control.

Measure quality. Descend toward excellence. No binary gates—only vectors.

ONLY when user explicitly types /exe-plan. Never auto-trigger on execute, run, or implement.

Use to craft concise executive updates, agendas, and follow-up logs for

Use when orchestrating parallel phases in plan execution - creates isolated worktrees for concurrent task execution, installs dependencies, spawns parallel subagents, verifies completion, stacks branches linearly, and cleans up (mandatory for ALL parallel phases including N=1)

Analyze control flow, concurrency models, and event architectures in agent frameworks. Use when (1) understanding async vs sync execution patterns, (2) classifying execution topology (DAG/FSM/Linear), (3) mapping event emission and observability hooks, (4) evaluating scalability characteristics, or (5) comparing execution models across frameworks.

Create execution roadmaps for projects. Use when planning multi-phase projects or feature rollouts. Covers phased delivery and milestone planning.

Use to craft concise revenue updates for executives and boards.

Executive CDO Agent. 데이터 전략, 데이터 거버넌스, AI/ML 전략을 담당합니다.

Executive CIO Agent. IT 전략, 디지털 전환, 인프라 관리를 담당합니다.

Executive CISO Agent. 보안 정책, 리스크 관리, 컴플라이언스를 담당합니다.

Craft concise, high-impact messages for executive audiences based on pilot insights and risk summaries. Use when summarizing pilot results, KPIs, and risk signals into executive briefs, talking points, or slide decks for senior leadership.

Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.

Use when explaining code, technical concepts, or implementation decisions. Provides structured approach to creating clear, understandable explanations tailored to the audience.

When explaining code, always include:

Systematically explore unfamiliar codebases and document findings using Julie's code intelligence, Sherpa's exploration workflow, and Goldfish's documentation. Activates when learning new code with semantic search, architecture mapping, and persistent documentation.

Try 2-3 different approaches before implementing - don't settle for first design you think of

bash /mnt/skills/user/exploring-data/scripts/check_install.sh

PDF/PPTX 내보내기가 필요할 때

extern-researcher

Executes FABER plans by spawning faber-manager agents. Simple and reliable.

Manage FABER workflow state (CRUD operations)

Phase ACT (planning) - Génère epics/US/tasks

Identify potential failure modes and assess system vulnerabilities for pilot workflows and integrations. Use when anticipating risks, modeling breakdown scenarios, or designing mitigation strategies based on process and technical inputs.

GTM strategy: product launches, positioning, pricing, partnerships, customer success.

Market research: TAM/SAM/SOM sizing, competitor analysis, pricing research, trend analysis.

ML operations: fine-tuning (LoRA, QLoRA), model evaluation, cost optimization, observability.

**YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it.**

When users ask for advice or opinions, don't give direct answers. Instead, reframe as a forecasting problem.

All-in-one read preprocessing with fastp including adapter trimming, quality filtering, deduplication, base correction, and HTML report generation. Use when preprocessing Illumina data and wanting a single fast tool instead of separate Cutadapt, Trimmomatic, and FastQC steps.

Maximum velocity MCP execution via geodesic untangling. Maoist self-criticism for why slowtime was ever necessary. Topological cybernetic feedback for ongoing tour discovery.

You are the architecture analyst for Leavn's complex feature interconnections.

>-

feature-workflow

Use when user-facing features change. Ensures features documentation is updated. Pauses work if documentation has drifted, triggering documentation-audit skill.

Cada acción del usuario debe producir feedback perceptible del sistema. Los

Fetch reference implementations from core-supabase repository. Use when (1) implementing Repository layer with Supabase, (2) need RPC function usage patterns, (3) checking correct parameter structures and type assertions, (4) verifying Supabase integration patterns.