crouton-labs/crouton-kit
37 skills · 1 total installs
$npx skills add crouton-labs/crouton-kitSkillInstalls
context-managementToken budgeting, placement effects, RAG patterns, prompt caching, compression, and multi-turn context strategies for LLM applications.captureBrowser automation and UI validation via the capture CLI. Interact with pages using accessibility-driven click, type, screenshot, a11y tree, JS exec, and HAR…claude-mdBest practices for writing effective CLAUDE.md files. Use when creating, updating, or auditing CLAUDE.md files for projects or directories.cli-designDesign CLIs for humans and LLM agents — subcommand shape, output streams, exit codes, JSON modes, TTY-aware color, structured errors, mutation safety.commandsGuide to writing slash commands for Claude Code. Use when creating commands that set mode, constraints, or workflows invoked via /command-name.contextGrove instance awareness — shows which parallel instance you're in, sibling instances, port mappings, and how to avoid cross-instance collisions.debuggingSystematic debugging methodologies for hard bugs. Covers rubber ducking, code tracing, hypothesis testing, logging strategies.eval-and-quality-gatesEvaluation strategies and quality gates for LLM systems. LLM-as-judge implementation, prompt regression testing, structural and semantic validation pipelines,…examplefrontend-designCreate distinctive, production-grade frontend interfaces with high design quality.frontend-mockupBuild interactive HTML mockups that match the project's actual theme for UX exploration and design review.hooksGuide to Claude Code hooks — lifecycle events, handler types, decision control, and common patterns.humanloopPause agent execution to have the human validate decisions, choose between options, answer freetext, or comment on a document — via the `hl` CLI.interface-designThis skill is for interface design — dashboards, admin panels, apps, tools, and interactive products.linear-cliThis skill should be used when the user asks to "create a Linear issue", "list Linear tickets", "start working on a ticket", "update Linear issue", "link PR to…llm-posting-guideWrite social media posts for X (Twitter) and LinkedIn that avoid AI tells, pass platform algorithms, and drive engagement.modes-authoringGuide to writing ai-cli mode files. Use when creating modes for non-interactive Claude Code sessions — preconfigured agent runs with locked-in system prompts,…multi-agent-orchestrationDesign and implement multi-agent LLM systems. Covers orchestrator patterns, parallel agent coordination, pipeline architecture, hierarchical delegation, agent…output-varietyTechniques for getting varied, non-repetitive outputs from repeated LLM calls.prompting-effectivelyStructure Claude prompts for clarity and better results using roles, explicit instructions, context, positive framing, and strategic organization.review-designValidate technical designs against requirements for coverage, feasibility, and architectural soundness. Use after creating a design.review-planValidate implementation plans against requirements and design. Use after creating a plan to ensure full coverage and no ambiguities.review-requirementsValidate requirements documents for EARS compliance, completeness, and consistency. Use after creating requirements.rulesGuide to writing .claude/rules/*.md files — auto-applied constraints scoped by file patterns.scripts-and-toolingGuide to creating CLI tools and scripts that augment Claude Code.silas-posting-guideWrite X (Twitter) posts in Silas's voice—direct, dense, practitioner-first style with thinking-out-loud cadence.skillsGuide to writing SKILL.md files for Claude Code. Use when creating skills that provide on-demand reference, methodology, or workflow guidance.sounding-humanRemove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written.structured-outputGet reliable typed JSON from LLMs using constrained decoding, JSON Schema, Zod, Pydantic, and Instructor.system-vs-user-promptWhat belongs in system prompt vs user prompt and why. Placement decisions for API calls, system messages, and prompt architecture — system as…termrenderRich terminal rendering of directive-flavored markdown. Panels, trees, columns, callouts, mermaid diagrams, syntax-highlighted code, diffs, charts, KPI tiles,…testingTest writing and fixing methodology. Covers TDD, investigating failures, and delegating fixes to agents. Use when writing tests or diagnosing test failures.tool-designDesign tool interfaces for LLM agents — descriptions, parameter schemas, error messages, granularity, and composition.ux-designUX design principles, heuristics, and evaluation frameworks. Use when reviewing interface usability, planning user flows, evaluating designs against…verify-runtimeVerify that a code change actually does what it's supposed to by running the app and observing behavior.writing-rulesThis skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on…x-growthX (Twitter) growth strategy — engagement tactics, posting frequency, community building, and audience growth.