Skill reviews

Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.

• 10 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

Author and review high-quality agent skills with triggers, progressive disclosure, and safety notes.

• References files that are not bundled: references/foo.md, scripts/validate.py
• 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

AWS Cloud Development Kit (CDK) expert for building cloud infrastructure with TypeScript/Python.

• References files that are not bundled: references/cdk-patterns.md, scripts/validate-stack.sh
• 10 top-level sections: this looks like several domains in one skill
• 2 referenced file(s) missing: references/cdk-patterns.md, scripts/validate-stack.sh

AWS cost optimization, monitoring, and operational excellence expert. Use when analyzing AWS bills, estimating costs, setting up CloudWatch alarms, querying logs, auditing CloudTra

• References files that are not bundled: references/operations-patterns.md, references/cloudwatch-alarms.md
• 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

SST v4 (Ion) expert for managing AWS resources as code with the Pulumi-backed framework.

• References files that are not bundled: references/authoring.md, references/testing.md, references/deploy-and-troubleshoot.md
• 3 referenced file(s) missing: references/authoring.md, references/testing.md, references/deploy-and-troubleshoot.md
• Does not say what the result is

Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and cont

• 11 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

Generate and edit images/video with Google's Gemini media models (Nano Banana 2/Pro, Gemini Omni Flash), with cost-approval gates, reference-image support, and a prompt/output log

• References files that are not bundled: references/<model>.md
• 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 (6 tags): a typed call is more reliable

Find exploitable vulnerabilities in GitHub Actions workflows. Every finding MUST include a concrete exploitation scenario — if you can't build the attack, don't report it.

• References files that are not bundled: references/pwn-request.md, references/comment-triggered-commands.md, references/expression-injection.md
• 10 top-level sections: this looks like several domains in one skill
• 9 referenced file(s) missing: references/pwn-request.md, references/comment-triggered-commands.md, references/expression-injection.md

Automate LinkedIn tasks via Rube MCP (Composio): create posts, manage profile, company info, comments, and image uploads. 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
• 13 mutating operations with no state check

Handle n8n files and binary data across uploads, downloads, transforms, multimodal inputs, agent tools, and chat surfaces.

• 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
• The response is described with custom markup (6 tags): a typed call is more reliable

CRITICAL: Use for Robius event and action patterns. Triggers on: custom action, MatchEvent, post_action, cx.widget_action, handle_actions, DefaultNone, widget action, event handlin

• References files that are not bundled: references/action-patterns.md, references/event-handling.md, references/moly-action-patterns.md
• 3 referenced file(s) missing: references/action-patterns.md, references/event-handling.md, references/moly-action-patterns.md
• Says nothing while it works

Prepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or w

• References files that are not bundled: references/definition-of-done.md, references/security-checklist.md, references/performance-checklist.md
• 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

Analyze Rails apps and provide upgrade assessments

• 14 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
• No condition that starts the skill

Apply proven SwiftUI UI patterns for navigation, sheets, async state, and reusable screens.

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

CRITICAL: Use for Makepad packaging and deployment. Triggers on: deploy, package, APK, IPA, 打包, 部署, cargo-packager, cargo-makepad, WASM, Android, iOS, distribution, installer, .deb

• References files that are not bundled: references/makepad-packaging-action.md, references/platform-troubleshooting.md
• 12 top-level sections: this looks like several domains in one skill
• 2 referenced file(s) missing: references/makepad-packaging-action.md, references/platform-troubleshooting.md

AWS serverless and event-driven architecture expert based on Well-Architected Framework. Use when building serverless APIs, Lambda functions, REST APIs, microservices, or async wor

• References files that are not bundled: references/eda-patterns.md, references/serverless-patterns.md, references/security-best-practices.md
• 6 referenced file(s) missing: references/eda-patterns.md, references/serverless-patterns.md, references/security-best-practices.md
• Does not say what the result is

Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes. Use when adding devcontainer support to a project, setting up isola

• References files that are not bundled: references/dockerfile-best-practices.md, references/features-vs-dockerfile.md
• 13 top-level sections: this looks like several domains in one skill
• 2 referenced file(s) missing: references/dockerfile-best-practices.md, references/features-vs-dockerfile.md

Comprehensive GitLab CI/CD pipeline patterns for automated testing, building, and deployment.

• References files that are not bundled: assets/gitlab-ci.yml.template, references/pipeline-stages.md
• 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

Operates HyperExecute end-to-end for TestMu AI/LambdaTest cloud test execution: analyze projects, create YAML, validate locally, run CLI jobs, debug failures, and wire CI.

• References files that are not bundled: scripts/doctor.js, scripts/validate-config.js, scripts/build-command.js
• 4 referenced file(s) missing: scripts/doctor.js, scripts/validate-config.js, scripts/build-command.js
• Does not say what the result is

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

Strategies and patterns for optimizing cloud costs across AWS, Azure, and GCP.

• References files that are not bundled: references/tagging-standards.md, assets/cost-analysis-template.xlsx
• 16 top-level sections: this looks like several domains in one skill
• 2 referenced file(s) missing: references/tagging-standards.md, assets/cost-analysis-template.xlsx

Generate, refine, validate, and render diagrams from natural language, notes, code, schemas, or existing diagram sources: flowcharts, swimlanes, attack-path graphs, data-flow diagr

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

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

Use when reviewing animation and motion code against a strict craft, performance, accessibility, and interaction-quality bar.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the process needs to start
• Linear process with no failure handling