REQUIRED before opening any pull request. Always invoke when about to open a PR, create a merge request, push for review, or run pre-PR checks.
Validate code quality: auto-fix formatting/lint, verify types, run tests. Use when user asks to \"validate code\", \"/validate-code\", \"check code\", or wants to validate before…
Validate a single AIWG component (skill, agent, or command) for completeness and correctness
Audit an existing Sim knowledge base connector against the service API docs and repository conventions, then report and fix issues in auth, config fields, pagination, document…
Validates hook, skill, and agent counts are consistent across CLAUDE.md, hooks.json, manifests, and source directories.
Use when user asks to \"validate delivery\", \"check readiness\", or \"verify completion\". Runs tests, build, and requirement checks with pass/fail instructions.
Turn YAML runbooks into auditable agent actions with validation, dry-runs, destructive-step approval, and optional MCP exposure.
Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify…
Validate a single findings file against grounding, schema, anti-hallucination, forbidden-fields, and contradiction-honesty checks.
Validates a business idea using the minimalist entrepreneur framework. Use when someone has a business idea and wants to test if it's worth pursuing before building anything.
Audit an existing Sim integration against the service API docs and repository conventions, then report and fix issues across tools, blocks, outputs, OAuth scopes, triggers, and…
Diagnostic skill that scans the workspace for multi-company isolation issues: L2 rules missing scope headers, memory files without company: field, conflicting directives across…
Run schema checks from the shell or CI so malformed JSON, JSON5, or YAML inputs fail before they reach downstream tooling.
Periodic smoke test for behavioral mechanism compliance. Scans the workspace for statically-detectable violations of rules in mechanism-registry.md.
Use when you have multiple open PRs and want to validate them all (CI, reviews, code quality) and plan a safe merge order.
Validate AIWG extension definitions against the metadata schema and report errors with field names, line numbers, and remediation hints
Use when the user wants to validate content structure and format — check if content matches expected schema, required sections, word count, formatting rules, and placeholder…
Lista Técnica de Regras de Negócio do labSIS-KIT. Define comportamento esperado para isolamento, permissões e instalação.
Validate all README files in the repository for required sections and installation code blocks. Checks section presence using config from .readme-validator.yaml or sensible…
Validate that input meets prerequisites based on the user's saved standards for the project type. Use at the start of any quality pipeline to ensure the user has provided…
Use when verifying all skills in the repository are well-formed before a release or after adding/editing a skill.
Validate AI/ML models and datasets for bias, fairness, and ethical concerns. Use when auditing AI systems for ethical compliance, fairness assessment, or bias detection.
Validate API responses against schemas to ensure contract compliance and data integrity. Use when ensuring API response correctness.
Validate application performance against defined budgets to identify regressions early. Use when checking page load times, bundle sizes, or API response times against thresholds.
Cross-cutting validation methodology for verifying phase outputs and project integrity
Validation-first development - design state machine specifications from requirements, then execute CREATE -> VERIFY -> IMPLEMENT cycle.
Use when implementation exists but tests or validation evidence are missing or incomplete
每写一个文件立即跑 build/lint/type-check/test，失败立即停下让用户决策。auto-loaded by build-api / build-web / fix 等 IMPLEMENT phase。DDT 每文件验证 + 失败立即停的 validation loop。
Use when writing, auditing, or troubleshooting Salesforce Validation Rules. Triggers: 'validation rule', 'required field formula', 'rule fires unexpectedly', 'integration failing…
Validis integration. Manage data, records, and automate workflows. Use when the user wants to interact with Validis data.
Help entry point — answers questions and routes to the right command
Local Vietnamese text-to-speech via VITS2 (offline, no cloud). Supports 5 built-in speaker voices and zero-shot voice cloning from reference audio.
Анализ первичных и поддерживающих видов деятельности — затраты, добавленная стоимость, конкурентные преимущества
Only invoke when explicitly requested via "值不值得看"、"评估打分"、"@value-judge" or "evaluate value". Do NOT auto-trigger.
Oberholzer-Gee's Value Stick — 4-layer model (Customer Delight, Firm Margin, Employee Satisfaction, Supplier Surplus), 3 diagnostic patterns (stick too short, delight giveaway,…
Vanta integration. Manage data, records, and automate workflows. Use when the user wants to interact with Vanta data.
Vapi integration. Manage data, records, and automate workflows. Use when the user wants to interact with Vapi data.
Use when the user asks to personalize the GitHub Copilot CLI assistant, adapt Copilot to their style, use vardoger, or analyze their Copilot CLI conversation history.
Generates a variable reward system with randomized rewards, daily bonuses, mystery box mechanics, and ethical engagement caps.
Gestalte eine Variationstheorie-Aufgabe mit Kontrast, Separation und Fusion um kritische Features eines Konzepts zu lehren.
Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits
Vast.ai CLI to manage GPU instances, volumes, serverless endpoints, and billing.
Execute Vast.ai primary workflow: GPU instance provisioning and job execution. Use when renting GPUs for training, searching offers by price and specs, or managing the full…
Execute Vast.ai secondary workflow: multi-instance orchestration, spot recovery, and cost optimization.
Optimize Vast.ai GPU cloud costs through smart instance selection and lifecycle management. Use when analyzing GPU spending, reducing training costs, or implementing budget…
Implement team access control and spending governance for Vast.ai GPU cloud. Use when managing multi-team GPU access, implementing spending controls, or setting up API key…
Execute Vast.ai incident response for GPU instance failures and outages. Use when responding to instance failures, investigating training crashes, or handling spot preemption…
Install and configure Vast.ai CLI and REST API authentication. Use when setting up a new Vast.ai integration, configuring API keys, or initializing Vast.ai GPU cloud access in…
Migrate GPU workloads to or from Vast.ai, or between GPU providers. Use when switching from AWS/GCP/Azure GPU instances to Vast.ai, migrating between GPU types, or re-platforming…
Monitor Vast.ai GPU instance health, utilization, and costs. Use when setting up monitoring dashboards, configuring alerts, or tracking GPU utilization and spending.
Optimize Vast.ai GPU instance selection, startup time, and training throughput. Use when optimizing instance selection, reducing startup latency, or maximizing GPU utilization on…
Upgrade Vast.ai CLI, migrate API versions, and handle breaking changes. Use when upgrading vastai CLI, detecting deprecations, or migrating between API versions.
Build event-driven workflows around Vast.ai instance lifecycle events. Use when monitoring instance status changes, implementing auto-recovery, or building event-driven GPU…
Vault health check. Validates structure, detects stale reasoning artifacts by priority level, processes inbox, and suggests cleanup.
Audit your Obsidian vault in Claude Code — finds stale drafts, empty folders, duplicate filenames, and incomplete files. Saves a dated report.
Mevcut bir projeye llm-wiki-mind pattern'ına göre yeni bir Obsidian bilgi arşivi (vault) kur ve projeye bağla.
Use when user says 'lint the vault', 'health check', 'find stale notes', 'vault audit'. Scans for contradictions, orphan pages, stale claims, missing cross-refs.
Mirrors session and learning JSONL records into the Meta-Vault as Markdown notes with vault-compatible frontmatter.
Use when user asks 'what do we know about X?', 'have we solved this before?', 'find notes on Y'. Reads vault index → drills into relevant pages → synthesizes answer with…
Automates HashiCorp Vault secret rotation using the Vault HTTP API and dynamic secrets engines. Manages database credential leases, PKI certificate renewal, and AWS STS token…