context-optimization
Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.
glean-mcp
Your work knowledge agent. Use Glean chat to answer any question about the user's company, accounts, colleagues, meetings, documents, or work history. Glean synthesizes across 100+ enterprise apps and always cites sources.
tool-design
Design tools that agents can use effectively, including when to reduce tool complexity. Use when creating, optimizing, or reducing agent tool sets.
context-fundamentals
Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.
project-development
Design and build LLM-powered projects from ideation through deployment. Use when starting new agent projects, choosing between LLM and traditional approaches, or structuring batch processing pipelines.
memory-systems
Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency, or reason over structured knowledge.
context-compression
Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.
agent-spec-generator
Design and generate Glean Agent specifications. Use when creating new agents, speccing out agent requirements, or generating JSON for Agent Builder import. Triggers on: 'create an agent', 'design an agent', 'agent spec', 'build an agent for [use case]'.
browser-automation
Guidance for effective browser automation with dev-browser plugin. Use for testing local development, verifying UI changes, debugging visual issues, and automating browser tasks.
advanced-evaluation
Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when building evaluation systems, comparing model outputs, or establishing quality standards for AI-generated content.
context-engineering-collection
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.
brief
Get a pre-meeting briefing for any account. Usage: /brief {account name}. Returns checklist progress, hours remaining, last interaction, missed comms, and open to-dos.
novel-creator
|
reviewing-code
>-
git-worktrees
>-
finishing-work
>-
systematic-debugging
>-
security-review
>-
receiving-code-review
>-
brainstorming
>-
parallel-agents
>-
researching-codebase
>-
markdown-validation
>-
implementing-plans
>-
documenting-decisions
>-
writing-plans
>-
test-driven-development
>-
verification-before-completion
>-
clawdhub
Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI.
doppler
Fetch secrets from Doppler for API keys and credentials.
linear
Query and manage Linear issues, projects, and team workflows.
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
frontend-design
Expert frontend design guidelines for creating beautiful, modern UIs. Use when building landing pages, dashboards, or any user interface.
sacred-blessing
Creates personalized sacred blessings for tasks, transitions, or life moments using inclusive feminine spiritual language. Draws from Hebrew Priestess traditions with a modern, witchy sensibility.
incantation
Generates a single-sentence power phrase for a specific moment or intention. Not affirmation (passive) but incantation (active)—words meant to be spoken aloud, carried into action, or encoded into work.
micro-ritual
Designs simple, embodied rituals for life moments using ordinary objects at hand. Grounded witchcraft for the modern practitioner—no special equipment, no performance, just presence.
tarot
Perform a single-card tarot reading with random Major Arcana selection. Use when seeking perspective on decisions, feeling stuck, exploring options, or when the user asks for a tarot reading or card draw.
romantical
Transforms your daily agenda into a narrative of intention and meaning. Finds the sacred in the mundane, the ritual in the routine.
correspondence
Finds the symbolic vocabulary for any intention—herbs, colors, stones, times, directions, and elements that align with what you're working toward. Practical magic for altars, outfit choices, or encoding meaning into action.
generate-image
Generate images using Replicate's Nano Banana Pro model with Esoterica's eco-futurist aesthetic. Use when creating hero images, social assets, or exploring visual variations.
zotero-mcp
Interface with Zotero's MCP server to search and retrieve bibliographic data using advanced semantic search and multi-strategy approaches. Designed for output as a plain markdown formatted outline, suitable for pasting into Logseq. Also offers side-by-side translation of Chinese titles and abstracts for improved English language search within Logseq. Context-aware - uses agents in Claude Code, batched searches in Claude Desktop.
Ruby Object Design Expert
Automatically invoked when making decisions about Ruby code structure and organization. Triggers on mentions of "class or module", "should this be a class", "struct vs class", "PORO", "data object", "design pattern", "class vs module", "when to use class", "module vs class", "stateless class", "value object", "data container", "object factory", "extend self", "singleton class". Provides guidance on choosing the right Ruby construct (class, module, Struct, Data, Hash) based on the principle that Ruby is object-oriented, not class-oriented.
rails-model-patterns
ActiveRecord model patterns and conventions for Rails. Automatically invoked when working with models, associations, validations, scopes, callbacks, or database schema design. Triggers on "model", "ActiveRecord", "association", "has_many", "belongs_to", "validation", "validates", "scope", "callback", "migration", "schema", "index", "foreign key".
Ruby Refactoring Expert
Automatically invoked when analyzing code quality, refactoring, or maintainability. Triggers on mentions of "code smell", "refactor", "code quality", "technical debt", "complexity", "maintainability", "clean code", "SOLID", "DRY", "improve code", "simplify", "extract method", "extract class", "long method", "large class", "duplication". Provides Ruby refactoring patterns and code smell identification based on Ruby Science methodology for recently written Ruby/Rails code.
rails-jobs-patterns
ActiveJob and background processing patterns for Rails. Automatically invoked when working with background jobs, Sidekiq, async processing, job queues, scheduling, or the app/jobs directory. Triggers on "job", "background job", "ActiveJob", "Sidekiq", "async", "queue", "perform_later", "worker", "scheduled job", "cron", "retry", "idempotent".
rails-service-patterns
Rails service object patterns and business logic organization. Automatically invoked when working with service objects, extracting business logic, implementing command/query patterns, or organizing app/services. Triggers on "service object", "service", "business logic", "workflow", "orchestration", "command pattern", "query object", "form object", "interactor", "result object".
rails-graphql-patterns
GraphQL patterns for Rails applications using graphql-ruby gem. Automatically invoked when working with GraphQL schemas, types, resolvers, mutations, subscriptions, or the app/graphql directory. Triggers on "GraphQL", "schema", "resolver", "mutation", "query type", "subscription", "graphql-ruby", "field", "argument", "N+1 graphql", "dataloader".
rails-controller-patterns
Rails controller patterns and conventions. Automatically invoked when working with controllers, routes, strong parameters, before_actions, or request handling. Triggers on "controller", "action", "routes", "routing", "strong params", "params.expect", "before_action", "respond_to", "RESTful", "CRUD", "redirect", "render".
hotwire-patterns
Stimulus and Turbo patterns for Rails frontend development. Automatically invoked when working with Hotwire, Stimulus controllers, Turbo frames/streams, progressive enhancement, or modern Rails JavaScript. Triggers on "Stimulus", "Turbo", "Hotwire", "turbo_frame", "turbo_stream", "Stimulus controller", "data-controller", "data-action", "progressive enhancement", "SPA-like".
coderabbit-fix-flow
This skill should be used when CodeRabbit code review feedback needs to be processed and fixed systematically. Use after running `coderabbit --plain` to automatically save feedback, analyze issues using MCP tools, and implement minimal code fixes with proper planning.
Page 1070 of 1309 · 65416 results
