Skill reviews

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

Protocolo de Inteligência Pré-Tarefa — ativa TODOS os agentes relevantes do ecossistema ANTES de executar qualquer tarefa solicitada pelo usuário.

• References files that are not bundled: scripts/pre_task_check.py
• 18 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: scripts/pre_task_check.py

Automate TikTok tasks via Rube MCP (Composio): upload/publish videos, post photos, manage content, and view user profiles/stats. Always search tools first for current schemas.

• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill
• 25 mutating operations with no state check

Safe production cleanup and hardening for vibe-coded fullstack apps (Next.js, React, Node.js, etc.). Removes dead imports, unused files, and broken references without breaking rout

• 12 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Triage Monte Carlo alerts interactively or build an automated workflow. Fetch, score, and troubleshoot alerts using MCP tools now, or design a reusable workflow that runs on a sche

• References files that are not bundled: references/triage-stages.md, references/triage-example.md
• 2 referenced file(s) missing: references/triage-stages.md, references/triage-example.md
• Does not say what the result is

Review generated or changed production code with Clean Code, SOLID, DRY, KISS, YAGNI, and LLM-specific failure-mode checks.

• 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
• The skill tells the model to perform an irreversible action with no human approval

Git-aware undo by logical work unit (track, phase, or task)

• 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
• The skill tells the model to perform an irreversible action with no human approval

Delegate coding tasks to the GitHub Copilot CLI (`copilot`) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.

• References files that are not bundled: scripts/relay.mjs
• 10 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: scripts/relay.mjs

Use when explicit CrossFrame work needs a Chinese critical insight essay, commentary, concept essay, public piece, or structure-to-article draft after diagnosis.

• References files that are not bundled: references/writing-techniques/*.md
• 1 referenced file(s) missing: references/writing-techniques/*.md
• Does not say what the result is

Lightweight Gmail integration with standalone OAuth authentication. No MCP server required.

• References files that are not bundled: scripts/gmail.py
• 1 referenced file(s) missing: scripts/gmail.py
• No condition that starts the skill

Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified inter

• References files that are not bundled: scripts/uniprot_client.py
• 1 referenced file(s) missing: scripts/uniprot_client.py
• No condition that starts the skill

Geracao de imagens humanizadas via Google AI Studio (Gemini). Fotos realistas estilo influencer ou educacional com iluminacao natural e imperfeicoes sutis.

• References files that are not bundled: references/api-reference.md
• 28 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: references/api-reference.md

A hard-edged writing style contract for timeless, forceful English prose without modern AI tics. Use when users ask for prose or rewrites that must be clean, exact, concrete, and f

• References files that are not bundled: references/test-cases.md
• 12 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: references/test-cases.md

Delegate coding tasks to a separate Claude Code CLI process or Claude session only when the user explicitly requests it, while the orchestrator retains review and landing responsib

• References files that are not bundled: scripts/relay.mjs
• 1 referenced file(s) missing: scripts/relay.mjs
• 13 mutating operations with no state check

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files.

• References files that are not bundled: viewport-base.css
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 12 top-level sections: this looks like several domains in one skill

Audits and strips Lovable scaffolding from Vite + React projects — removes lovable-tagger, swaps placeholder assets, prunes unused Radix deps, cleans generated docs, and neutralize

• 13 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (7 tags): a typed call is more reliable

One API and one credential for frontier and open-source LLMs, built into your Neon branch and powered by Databricks.

• References files that are not bundled: references/ai-sdk.md
• 13 top-level sections: this looks like several domains in one skill
• The response is described with custom markup (4 tags): a typed call is more reliable

Scaffold, write, debug, and enhance enterprise-grade Playwright E2E tests in Java using Page Object Model, JUnit 5, Allure reporting, and parallel execution.

• References files that are not bundled: references/config.md, references/page-objects.md, references/assertions.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 6 referenced file(s) missing: references/config.md, references/page-objects.md, references/assertions.md

Direct REST API access to PubMed. Advanced Boolean/MeSH queries, E-utilities API, batch processing, citation management. For Python workflows, prefer biopython (Bio.Entrez). Use th

• Does not say what the result is
• No condition that starts the skill

Audit deployed Vercel apps for cost and performance issues using metrics, project config, code scans, and version-aware recommendations.

• References files that are not bundled: references/doctrine.md, references/voice.md, references/observability-plus.md
• 10 top-level sections: this looks like several domains in one skill
• The response is described with custom markup (3 tags): a typed call is more reliable

Delegate coding tasks to Aider (`aider`) 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
• 12 top-level sections: this looks like several domains in one skill

AWS Bedrock AgentCore comprehensive expert for deploying and managing AI agents at scale. Use when working with any AgentCore service including Gateway, Runtime, Memory, Identity,

• References files that are not bundled: references/agentcore-oauth-integration.md, references/agentcore-runtime-core.md, references/agentcore-runtime-deploy.md
• 4 referenced file(s) missing: references/agentcore-oauth-integration.md, references/agentcore-runtime-core.md, references/agentcore-runtime-deploy.md
• Does not say what the result is

Delegate coding tasks to the Cline CLI (`cline`) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.

• References files that are not bundled: scripts/relay.mjs
• 1 referenced file(s) missing: scripts/relay.mjs
• Does not say what the result is

Delegate coding tasks to the OpenAI Codex 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
• 1 referenced file(s) missing: scripts/relay.mjs
• Linear process with no failure handling

GraphQL queries, mutations, and code generation patterns. Use when creating GraphQL operations, working with Apollo Client, or generating types.

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