Skill reviews

Deploy, monitor, and debug long GPU jobs on RENTED/remote instances (AutoDL, RunPod, vast.ai, Lambda, Slurm, K8s): teardown/billing safety, spot resilience, resumable checkpointing

• References files that are not bundled: scripts/health_patrol.sh.template
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 15 top-level sections: this looks like several domains in one skill

Operate and evaluate Unified AI System through nine governed MCP tools, including provider-free prompt enhancement, while preserving fake-provider, authorization, and evidence boun

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Fine-tune and post-train LLMs with Unsloth Core on a single consumer GPU: VRAM sizing, LoRA/QLoRA, GRPO/DPO, chat-template correctness, and GGUF export.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• Does not say what the process needs to start

Automate Webflow CMS collections, site publishing, page management, asset uploads, and ecommerce orders via Rube MCP (Composio). Always search tools first for current schemas.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Linear process with no failure handling

Execute comprehensive client-side injection vulnerability assessments on web applications to identify XSS and HTML injection flaws, demonstrate exploitation techniques for session

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Linear process with no failure handling

Master Django 5.x with async views, DRF, Celery, and Django Channels. Build scalable web applications with proper architecture, testing, and deployment.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• Linear process with no failure handling

Algorithmic philosophies are computational aesthetic movements that are then expressed through code. Output .md files (philosophy), .html files (interactive viewer), and .js files

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Says nothing while it works

Produces clean, functional code that matches the architecture and checklists.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Does not say what the process needs to start

Master AngularJS to Angular migration, including hybrid apps, component conversion, dependency injection changes, and routing migration.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 16 top-level sections: this looks like several domains in one skill
• Says nothing while it works

Generate Atlas Cloud images and videos through its asynchronous media API with schema-first model selection and credential-safe polling.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Adversarial code auditor that hunts down bugs, logic errors, and security flaws. Use for deep correctness passes, not style reviews.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• Does not say what the process needs to start

Compile durable, non-obvious findings into an interlinked markdown knowledge store — atomic files, [[wiki-links]], a maintained index — so an agent gets smarter across sessions ins

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

Master modern GraphQL with federation, performance optimization, and enterprise security. Build scalable schemas, implement advanced caching, and design real-time systems.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• Linear process with no failure handling

Integrate the beta markstream-svelte renderer into Svelte 5 or SvelteKit with runes, explicit CSS, smooth streaming, workers, and SSR-safe boundaries.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Does not say what the process needs to start

Generate production-ready mise.toml setups for local development, CI/CD pipelines, and toolchain standardization.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Linear process with no failure handling

Delegate coding tasks to the OpenCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.

• References files that are not bundled: scripts/relay.mjs
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 1 referenced file(s) missing: scripts/relay.mjs

Design and implement multi-tenant SaaS architectures with row-level security, tenant-scoped queries, shared-schema isolation, and safe cross-tenant admin patterns in PostgreSQL and

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• 15 mutating operations with no state check

Set up and verify Talivia revenue analytics through MCP, with explicit confirmation for website changes and payment attribution.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

Add rate limiting to API routes, middleware, and edge functions with @upstash/ratelimit: sliding window, fixed window, and token bucket backed by Upstash Redis.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (8 tags): a typed call is more reliable
• Does not say what the result is

Generate project-specific AGENTS.md and companion rules by analyzing a codebase. Supports full, minimal, update, and dry-run modes with package-manager detection, monorepos, backup

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the process needs to start
• 8 mutating operations with no state check

Master software architect specializing in modern architecture

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill
• Linear process with no failure handling

Automated cleanup of unused AWS resources to reduce costs

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 15 top-level sections: this looks like several domains in one skill
• No condition that starts the skill

Review product risk before coding by checking demand, alternatives, channels, switching costs, and failure signals.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Write copy following Sentry brand guidelines. Use when writing UI text, error messages, empty states, onboarding flows, 404 pages, documentation, marketing copy, or any user-facing

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• No condition that starts the skill