loom-serialization
Data serialization and deserialization patterns across formats. Use when implementing data exchange, API payloads, storage formats, encoding/decoding, or cross-language communication. Keywords: serialize, deserialize, serialization, deserialization, JSON, YAML, TOML, XML, Protocol Buffers, protobuf, MessagePack, CBOR, serde, encoding, decoding, schema, schema evolution, versioning, backward compatibility, forward compatibility, binary format, text format, data interchange, gRPC, API contracts.
loom-security-scan
Quick routine security checks for secrets, dependencies, container images, and common vulnerabilities. Run frequently during development. Triggers: security scan, SAST, DAST, vulnerability scan, dependency scan, container scan, secret scan, credential scan, quick scan, secrets check, vulnerability check, security check, pre-commit security, routine security, Snyk, Trivy, Semgrep, CodeQL, Bandit, safety, npm audit, cargo audit, gitleaks, trufflehog, govulncheck, pip-audit.
loom-security-audit
Performs comprehensive security audits identifying vulnerabilities, misconfigurations, and security best practice violations across applications, APIs, infrastructure, and data pipelines. Covers OWASP Top 10, compliance requirements (SOC2, PCI-DSS, HIPAA, GDPR), penetration testing, vulnerability assessment, risk assessment, security reviews, and hardening. Trigger keywords: security audit, vulnerability assessment, penetration test, pentest, OWASP, CVE, security review, risk assessment, compliance, SOC2, PCI-DSS, HIPAA, GDPR, security checklist, threat modeling, attack surface, security posture, vulnerability scan, security hardening, security baseline, security controls, security gap analysis, infrastructure security, API security, cloud security, container security, Kubernetes security, network security, application security, data security, ML model security.
loom-search
Full-text search and search engine implementation. Use when implementing search functionality, autocomplete, faceted search, relevance tuning, or working with search indexes. Keywords: search, full-text search, Elasticsearch, OpenSearch, Meilisearch, Typesense, fuzzy search, autocomplete, faceted search, facets, inverted index, relevance, ranking, scoring, tokenizer, analyzer, search-as-you-type, aggregations, synonyms, indexing, query, filtering, highlighting, search UI, typeahead, suggestions.
loom-rust
Rust language expertise for writing safe, performant, production-quality Rust code. Primary language for the Loom project. Use for Rust development, ownership patterns, error handling, async/await, cargo management, CLI tools, and serialization. Triggers: rust, cargo, rustc, ownership, borrowing, lifetime, trait, impl, struct, enum, Result, Option, async, await, tokio, serde, clap, thiserror, anyhow, Arc, Mutex, RwLock, RefCell, Box, Rc, Vec, HashMap, HashSet, String, derive, macro.
loom-refactoring
|
loom-react
Modern React development patterns including components, hooks, state management, routing, forms, and UI architecture. Covers React 19+, React Router v7, Jotai atoms, server components, accessibility, performance optimization, and testing. Use for building React applications with client-side routing, global state, component composition, and async data loading. Triggers: react, jsx, tsx, component, hook, useState, useEffect, useContext, useReducer, useMemo, useCallback, useRef, props, state, render, virtual DOM, reconciliation, single page application, spa, react-router, jotai, vite, bun, Next.js, Remix, client-side routing, server components, accessibility, a11y, ARIA, performance, code splitting, lazy loading, Suspense, error boundaries, form validation, UI components, design system, composition patterns.
loom-error-handling
Comprehensive error handling patterns and strategies including Rust Result/Option, API error responses, data pipeline error handling, and security-aware error handling. Use when implementing exception handling, error recovery, retry logic, circuit breakers, fallback mechanisms, graceful degradation, or designing error hierarchies. Triggers: error, exception, try, catch, throw, raise, Result, Option, panic, recover, retry, fallback, graceful degradation, circuit breaker, error boundary, 500, 4xx, 5xx, thiserror, anyhow, RFC 7807, error propagation, error messages, stack trace.
loom-feature-flags
Feature flag patterns for controlled rollouts, A/B testing, kill switches, and runtime configuration. Use when implementing feature toggles, feature flags, gradual rollouts, canary releases, percentage rollouts, dark launches, user targeting, A/B tests, experiments, circuit breakers, emergency kill switches, model switching, or infrastructure flags.
loom-event-driven
Event-driven architecture patterns including message queues, pub/sub, event sourcing, CQRS, and sagas. Use when implementing async messaging, distributed transactions, event stores, command query separation, domain events, integration events, data streaming, choreography, orchestration, or integrating with RabbitMQ, Kafka, Apache Pulsar, AWS SQS, AWS SNS, NATS, event buses, or message brokers.
loom-rate-limiting
API rate limiting and quota management implementation. Use when implementing request throttling, API quotas, backpressure handling, or protection against abuse. Keywords: rate limiting, rate limit, throttle, throttling, token bucket, leaky bucket, sliding window, fixed window, quota, 429, too many requests, DDoS, abuse prevention, API quota, burst, Redis rate limiting, distributed rate limiting, API gateway, per-user limits, per-IP limits, concurrent requests, request limiting.
loom-data-visualization
Creates effective data visualizations, charts, dashboards, and reports across analytics, infrastructure monitoring, and ML domains. Covers library selection, UX design, and accessibility. Trigger keywords: chart, graph, plot, dashboard, report, visualization, matplotlib, plotly, d3, seaborn, grafana, tableau, superset, metabase, KPI, metric, analytics, histogram, heatmap, time-series, scatter, bar-chart.
loom-usage
|
loom-python
Python language expertise for writing idiomatic, production-quality Python code. Covers web frameworks (FastAPI, Django, Flask), data processing (pandas, numpy, dask), ML patterns (sklearn, pytorch), async programming, type hints, testing with pytest, packaging (pip, uv, poetry), linting (ruff, mypy, black), and PEP 8 standards. Use for any Python development including data engineering and machine learning workflows. Triggers: python, py, pip, uv, poetry, virtualenv, pytest, pydantic, fastapi, django, flask, pandas, numpy, dataclass, type hints, asyncio, mypy, ruff, black, sklearn, pytorch, tensorflow, jupyter, pipenv, conda.
loom-prompt-engineering
Designs and optimizes prompts for large language models including system prompts, agent signals, and few-shot examples. Covers instruction design, prompt security, chain-of-thought reasoning, and in-context learning for orchestrated AI agents. Trigger keywords: prompt, LLM, GPT, Claude, AI, system prompt, user prompt, few-shot, chain of thought, CoT, in-context learning, prompt template, prompt injection, jailbreak prevention, agent signal, agent instruction, agent orchestration, reasoning, instruction tuning.
loom-data-validation
Data validation patterns including schema validation, input sanitization, output encoding, and type coercion. Use when implementing validate, validation, schema, form validation, API validation, JSON Schema, Zod, Pydantic, Joi, Yup, sanitize, sanitization, XSS prevention, injection prevention, escape, encode, whitelist, constraint checking, invariant validation, data pipeline validation, ML feature validation, or custom validators.
loom-crossplane
Cloud-native infrastructure management with Crossplane using Kubernetes APIs. Build internal platform APIs for self-service infrastructure provisioning. Use when implementing infrastructure as code, platform engineering, composite resources, XRDs, compositions, claims, provider configuration, or multi-cloud provisioning. Triggers: crossplane, XRD, composition, claim, provider, managed resource, composite resource, infrastructure API, platform engineering, platform API, infrastructure abstraction, self-service infrastructure, kubernetes infrastructure, cloud control plane.
loom-concurrency
Comprehensive concurrency and parallelism patterns for multi-threaded and async programming. Use when implementing async/await, parallel processing, thread safety, worker pools, or debugging race conditions and deadlocks. Triggers: async, await, thread, mutex, lock, semaphore, channel, actor, parallel, concurrent, race condition, deadlock, livelock, atomic, futures, promises, tokio, asyncio, goroutine, spawn, Arc, Mutex, RwLock, mpsc, select, join, worker pool, queue, synchronization, critical section, context switch.
loom-prometheus
|
loom-code-review
Performs comprehensive code reviews focusing on correctness, maintainability, performance, security, and best practices. Trigger keywords: review, code review, PR review, pull request, check code, audit code, feedback, approve, request changes, comment, suggestion, LGTM, nit, blocker, code quality, best practice, architecture review, design review, security review, infra review.
loom-plan-writer
REQUIRED skill for creating Loom execution plans. Designs DAG-based plans with mandatory knowledge-bootstrap and integration-verify bookends, parallel subagent execution within stages, and concurrent worktree stages for maximum throughput. Trigger keywords: loom, plan, stage, worktree, orchestration, parallel execution, parallel stages, concurrent execution, knowledge-bootstrap, integration-verify, acceptance criteria, signal, handoff, execution graph, dag, dependencies, loom plan, create plan, write plan, execution plan, orchestration plan, stage dependencies, parallel subagents, functional verification, wiring verification, smoke test.
drupal-security
Drupal security expertise. Auto-activates when writing forms, controllers, queries, or handling user input. Prevents XSS, SQL injection, and access bypass vulnerabilities.
ddev-expert
DDEV local development expertise. Use when working with DDEV projects, containers, configuration, or troubleshooting DDEV environments.
docker-local
Custom Docker Compose local development patterns. Use when working with Docker-based local environments, container configuration, or troubleshooting Docker setups.
drupal-expert
Drupal 10/11 development expertise. Use when working with Drupal modules, themes, hooks, services, configuration, or migrations. Triggers on mentions of Drupal, Drush, Twig, modules, themes, or Drupal API.
drupal-migration
Drupal migration expertise. Use when working with D7-to-D10 migrations, CSV imports, JSON API imports, or custom migration plugins.
crucible-planner
Interactive planning system for epic fantasy novels using the Crucible Structure—a 36-beat narrative framework with three interwoven story strands (Quest, Fire, Constellation), five Forge Points, and a Mercy Engine. Use when user wants to plan a fantasy novel, provides a story premise/synopsis, asks to "plan my fantasy book," wants to create planning documents for an epic fantasy, or mentions the Crucible Structure. Guides users through multi-choice questions to generate 7 planning document categories (14 files total) from a simple premise.
crucible-writer
First-draft writing assistant for Crucible-planned novels. Use when author has completed planning (crucible-planner) and outlining (crucible-outliner) and wants to write the actual prose. Handles scene-by-scene drafting, style matching, continuity tracking, and hallucination prevention. Triggers on "write my novel," "draft chapter X," "start writing from my outline," "help me write my book," or when user has Crucible outline and wants prose output. Works with any Crucible-planned story.
crucible-editor
Revision and editing assistant for Crucible-drafted novels. Use when author has completed a first draft and wants to revise, edit, or polish their manuscript. Handles developmental editing, line editing, copy editing, and final polish. Triggers on "edit my novel," "revise chapter X," "polish my manuscript," "help me edit," or when user has completed draft chapters and wants to improve them.
crucible-outliner
Chapter-by-chapter outline generator for stories planned with the Crucible Structure. Use when a user has completed Crucible planning documents (thesis, strand maps, forge points, etc.) and wants to create detailed chapter outlines. Triggers on requests like "outline my book," "create chapter outline," "outline Book 1," "turn my Crucible plan into chapters," or when user has Crucible planning docs and wants to start writing. Works for single books or multi-book series.
Python Rope Refactor
Rope-first workflow for ANY mechanical Python rename/move (functions/methods/classes/variables/modules/packages), updating imports/references via scripts/rope_refactor.py; use even for small renames; only fallback if rope fails/dynamic imports.
worktree-task
使用 git worktree + 背景代理会话管理大型任务（默认启动 Claude Code；可用 --codex 快速切到 Codex CLI，或通过 --agent-cmd 指定任意命令）。适合用户希望在不阻塞当前会话的情况下执行大型或多步骤任务。
castella-mcp
Enable AI agents to introspect and control Castella UIs via MCP. Create MCP servers, expose UI resources, handle MCP tools, and use semantic IDs.
castella-core
Build desktop, web, or terminal UIs with Castella. Create widgets, components, layouts, manage reactive state, handle events, and use the theme system.
castella-agent-ui
Build chat interfaces and agent management UIs with Castella. Create chat components, display tool calls, manage multiple agents, and build agent hubs.
castella-a2a
Connect to A2A protocol agents from Castella. Communicate with agents, display agent cards, send messages, handle responses, and stream results.
castella-a2ui
Render A2UI JSON as native Castella widgets. Parse A2UI messages, handle actions, progressive rendering, data binding, and connect to A2UI-enabled agents.
castella-packaging
Package Castella applications for distribution using ux, PyInstaller, or Nuitka. Create executables, macOS app bundles, and cross-compile for other platforms.
specswarm-ship
Systematic quality validation, test verification, and safe merging workflow for deployment/release operations. ALWAYS asks for confirmation when user wants to ship, deploy, merge, release, or complete features to production, merge to main branch, or finalize features. This is a DESTRUCTIVE operation (merges and deletes branches).
specswarm-upgrade
Systematic compatibility analysis, migration guidance, and breaking change detection for dependency/framework upgrades. Auto-executes when user clearly wants to upgrade, update, migrate, or modernize software dependencies, frameworks, packages, or technology stacks.
specswarm-modify
Impact-analysis-first modification workflow with backward compatibility assessment and breaking change detection. Auto-executes when user clearly wants to modify, change, update, adjust, enhance, extend, or alter existing feature behavior (not fixing bugs, not refactoring quality). For features that work but need to work differently.
specswarm-build
Systematic spec-driven workflow (specification→clarification→planning→tasks→implementation→validation) for feature development. Auto-executes when user clearly wants to build, create, add, implement, develop, make, construct, or set up software features, components, or functionality.
specswarm-fix
Systematic bugfix workflow with regression testing, auto-retry logic, and comprehensive validation. Auto-executes when user clearly wants to fix, debug, repair, resolve, broken, not working, doesn't work, not showing up, not appearing, not displaying, not rendering, doesn't show, won't show, isn't showing, doesn't appear, doesn't display, failing, errors, bugs, issues, not loading, doesn't load, crashed, crashes, problem with, trouble with.
codex
Execute Codex CLI for code analysis, refactoring, and automated code changes. Use when you need to delegate complex code tasks to Codex AI with file references (@syntax) and structured output.
refactoring
**MANDATORY**: Apply when refactoring or when asked to improve maintainability. Enforces staged, low-risk refactors and clean commit boundaries.
standup
Generate a daily standup update in Markdown using git, GitHub (gh), and Jira (best-effort).
git
**MANDATORY**: Load when creating commits or PRs. Covers conventional commits, branching, and PR conventions
git-workflow
**MANDATORY**: Enforce branch/worktree workflow. Use when starting work, picking up work, creating branches, using git worktrees, or when asked to implement anything non-trivial. Ensures all work happens on correctly named branches, preferably in dedicated worktrees.
communication
Writing and collaboration standards for PR reviews, PR descriptions, and ticket updates. Use when writing messages that other humans will read (PR review comments, PR bodies, JIRA ticket bodies/comments).
code-review
**MANDATORY**: Apply when reviewing code changes, PR diffs, or code-review requests. Enforces quality standards, warning seriousness, and meaningful comments.
Page 668 of 1486 · 74266 results
