Framework health check combining isolation and mechanism compliance. Two modes: (1) Isolation — scan for multi-company contamination (scope headers, memory tags, cross-company…
Score 70/100
Validate that all Discovery artefacts (Epics, Stories) are clear, governed, complete, and safe to pass into Delivery.
Score 70/100
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.
Score 70/100
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…
Score 70/100
Validate a single AIWG component (skill, agent, or command) for completeness and correctness
Score 70/100
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…
Score 70/100
Validates hook, skill, and agent counts are consistent across CLAUDE.md, hooks.json, manifests, and source directories.
Score 70/100
Turn YAML runbooks into auditable agent actions with validation, dry-runs, destructive-step approval, and optional MCP exposure.
Score 70/100
Validate a single findings file against grounding, schema, anti-hallucination, forbidden-fields, and contradiction-honesty checks.
Score 70/100
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.
Score 70/100
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…
Score 70/100
Diagnostic skill that scans the workspace for multi-company isolation issues: L2 rules missing scope headers, memory files without company: field, conflicting directives across…
Score 70/100
Run schema checks from the shell or CI so malformed JSON, JSON5, or YAML inputs fail before they reach downstream tooling.
Score 70/100
Periodic smoke test for behavioral mechanism compliance. Scans the workspace for statically-detectable violations of rules in mechanism-registry.md.
Score 70/100
Use when you have multiple open PRs and want to validate them all (CI, reviews, code quality) and plan a safe merge order.
Score 70/100
Validate AIWG extension definitions against the metadata schema and report errors with field names, line numbers, and remediation hints
Score 70/100
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…
Score 70/100
Lista Técnica de Regras de Negócio do labSIS-KIT. Define comportamento esperado para isolamento, permissões e instalação.
Score 70/100
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…
Score 70/100
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…
Score 70/100
Use when verifying all skills in the repository are well-formed before a release or after adding/editing a skill.
Score 70/100
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.
Score 70/100
Validate API responses against schemas to ensure contract compliance and data integrity. Use when ensuring API response correctness.
Score 70/100
Validate application performance against defined budgets to identify regressions early. Use when checking page load times, bundle sizes, or API response times against thresholds.
Score 70/100
Cross-cutting validation methodology for verifying phase outputs and project integrity
Score 70/100
Validation-first development - design state machine specifications from requirements, then execute CREATE -> VERIFY -> IMPLEMENT cycle.
Score 70/100
Use when implementation exists but tests or validation evidence are missing or incomplete
Score 70/100
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。
Score 70/100
Use when writing, auditing, or troubleshooting Salesforce Validation Rules. Triggers: 'validation rule', 'required field formula', 'rule fires unexpectedly', 'integration failing…
Score 70/100
Local Vietnamese text-to-speech via VITS2 (offline, no cloud). Supports 5 built-in speaker voices and zero-shot voice cloning from reference audio.
Score 70/100
Only invoke when explicitly requested via "值不值得看"、"评估打分"、"@value-judge" or "evaluate value". Do NOT auto-trigger.
Score 70/100
Oberholzer-Gee's Value Stick — 4-layer model (Customer Delight, Firm Margin, Employee Satisfaction, Supplier Surplus), 3 diagnostic patterns (stick too short, delight giveaway,…
Score 70/100
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.
Score 70/100
Generates a variable reward system with randomized rewards, daily bonuses, mystery box mechanics, and ethical engagement caps.
Score 70/100
Gestalte eine Variationstheorie-Aufgabe mit Kontrast, Separation und Fusion um kritische Features eines Konzepts zu lehren.
Score 70/100
Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits
Score 70/100
Vast.ai CLI to manage GPU instances, volumes, serverless endpoints, and billing.
Score 70/100
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…
Score 70/100
Execute Vast.ai secondary workflow: multi-instance orchestration, spot recovery, and cost optimization.
Score 70/100
Optimize Vast.ai GPU cloud costs through smart instance selection and lifecycle management. Use when analyzing GPU spending, reducing training costs, or implementing budget…
Score 70/100
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…
Score 70/100
Execute Vast.ai incident response for GPU instance failures and outages. Use when responding to instance failures, investigating training crashes, or handling spot preemption…
Score 70/100
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…
Score 70/100
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…
Score 70/100
Monitor Vast.ai GPU instance health, utilization, and costs. Use when setting up monitoring dashboards, configuring alerts, or tracking GPU utilization and spending.
Score 70/100
Optimize Vast.ai GPU instance selection, startup time, and training throughput. Use when optimizing instance selection, reducing startup latency, or maximizing GPU utilization on…
Score 70/100
Upgrade Vast.ai CLI, migrate API versions, and handle breaking changes. Use when upgrading vastai CLI, detecting deprecations, or migrating between API versions.
Score 70/100
Build event-driven workflows around Vast.ai instance lifecycle events. Use when monitoring instance status changes, implementing auto-recovery, or building event-driven GPU…
Score 70/100
Vault health check. Validates structure, detects stale reasoning artifacts by priority level, processes inbox, and suggests cleanup.
Score 70/100
Audit your Obsidian vault in Claude Code — finds stale drafts, empty folders, duplicate filenames, and incomplete files. Saves a dated report.
Score 70/100
Mevcut bir projeye llm-wiki-mind pattern'ına göre yeni bir Obsidian bilgi arşivi (vault) kur ve projeye bağla.
Score 70/100
Use when user says 'lint the vault', 'health check', 'find stale notes', 'vault audit'. Scans for contradictions, orphan pages, stale claims, missing cross-refs.
Score 70/100
Mirrors session and learning JSONL records into the Meta-Vault as Markdown notes with vault-compatible frontmatter.
Score 70/100
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…
Score 70/100
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…
Score 70/100
Show status of all LLM Wiki vaults — page counts, source counts, last activity, and git status. Use when user wants to see vault status, list vaults, or check wiki health.
Score 70/100
Validates vault frontmatter (Zod schema) and wiki-link integrity. Phase 1: hard gate at session-end. Used by session-end skill to block close on invalid vault state.
Score 70/100
Full PR review pipeline: generate prview-rs artifacts then produce a findings-max audit. Use when the user asks to "review PR", "analyze branch", "run prview", "sprawdź PR", "zrób…
Score 70/100
Full PR review pipeline: generate prview-rs artifacts then produce a findings-max audit. Use when the user asks to "review PR", "analyze branch", "run prview", "sprawdź PR", "zrób…
Score 70/100
Guide to quality filtering raw VCF files before computing summary stats (Ts/Tv ratio, variant counts, AF distributions).
Score 70/100