Back to authors
cosmix

cosmix

122 Skills published on GitHub.

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.

UncategorizedView skill →

loom-prometheus

Prometheus monitoring and alerting for cloud-native observability. Use for writing PromQL queries, configuring scrape targets, creating alerting and recording rules, instrumenting applications, and setting up service discovery. Not for dashboards (use loom-grafana) or log analysis (use loom-logging-observability).

UncategorizedView skill →

loom-prompt-engineering

Designs and optimizes prompts for large language models including system prompts, agent signals, and few-shot examples. Use for instruction design, prompt security, chain-of-thought reasoning, and in-context learning for orchestrated agents.

UncategorizedView skill →

loom-python

Python language expertise for idiomatic, production-quality code. Use for web frameworks (FastAPI, Django, Flask), data processing (pandas, numpy), ML patterns (sklearn, pytorch), async programming, type hints, pytest, packaging with uv/poetry, and linting with ruff/mypy/black.

UncategorizedView skill →

loom-rate-limiting

API rate limiting and quota management. Use when implementing request throttling, API quotas, backpressure handling, or abuse protection. Covers token bucket, leaky bucket, sliding/fixed window algorithms, and distributed rate limiting with Redis.

UncategorizedView skill →

loom-react

Modern React development patterns. Use for building React 19+ applications with components, hooks, Jotai state, React Router v7, server components, accessibility, performance optimization, and testing. Covers client-side routing, composition, and async data loading.

UncategorizedView skill →

loom-refactoring

Restructures existing code to improve readability, maintainability, and performance without changing behavior. Use for extracting methods/classes, removing duplication, applying design patterns, improving organization, and reducing technical debt. Not for bug fixes (use loom-debugging) or new features.

UncategorizedView skill →

loom-rust

Rust language expertise for idiomatic, production-quality code. Use for ownership and lifetimes, error handling with anyhow/thiserror, async/await with tokio, cargo workspace management, CLI tools with clap, and serialization with serde. Primary language of the Loom project.

UncategorizedView skill →

loom-search

Full-text search and search engine implementation. Use when implementing search functionality, autocomplete, faceted search, relevance tuning, or working with search indexes like Elasticsearch, OpenSearch, Meilisearch, or Typesense.

UncategorizedView skill →

loom-security-audit

Comprehensive security audits identifying vulnerabilities, misconfigurations, and best-practice violations across applications, APIs, infrastructure, and data pipelines. Use for OWASP Top 10 reviews, compliance assessments (SOC2, PCI-DSS, HIPAA, GDPR), threat modeling, risk assessment, and hardening.

UncategorizedView skill →

loom-security-scan

Quick routine security checks for secrets, dependencies, container images, and common vulnerabilities. Use for lightweight pre-commit and CI scans with tools like Semgrep, Trivy, gitleaks, cargo audit, npm audit, and pip-audit. Not a substitute for deep audits (use loom-security-audit).

UncategorizedView skill →

loom-serialization

Data serialization and deserialization patterns across formats. Use when implementing data exchange, API payloads, storage formats, encoding/decoding, schema evolution, or cross-language communication with JSON, YAML, TOML, Protocol Buffers, MessagePack, CBOR, Avro, or serde.

UncategorizedView skill →

loom-sql-optimization

Analyzes and optimizes SQL queries for performance. Use for index design, query rewriting, EXPLAIN/EXPLAIN ANALYZE interpretation, PostgreSQL tuning, N+1 prevention, CTE and window function optimization, join strategies, and common SQL anti-patterns.

UncategorizedView skill →

loom-technical-writing

Professional technical documentation writing for software projects. Use for READMEs, user guides, tutorials, migration guides, changelogs, API documentation, error messages, and release notes. Covers style, tone, voice, clarity, and audience-appropriate writing.

UncategorizedView skill →

loom-terraform

Infrastructure as Code with Terraform/OpenTofu. Use for cloud resource provisioning, module development, state and backend management, multi-environment deployments (workspaces, tfvars), provider configuration, and refactoring/import workflows.

UncategorizedView skill →

loom-test-strategy

Test strategy guidance — test pyramid design, coverage goals, test categorization, altitude/cost tradeoffs, flaky-test diagnosis, infrastructure architecture, and risk-based prioritization. Use when planning testing approaches, optimizing test suites, or designing test architecture across APIs, data pipelines, ML models, and infrastructure.

UncategorizedView skill →

loom-testing

Test implementation across unit, integration, e2e, security, infrastructure, data pipeline, and ML domains. Use for writing tests, debugging flaky tests, improving coverage, and following TDD/BDD workflows with pytest, jest, vitest, mocha, junit, or testify.

UncategorizedView skill →

loom-threat-model

Threat modeling methodologies (STRIDE, DREAD, PASTA, attack trees) for secure architecture design. Use when planning new systems, reviewing architecture security, mapping trust boundaries and data flows, identifying threats, or assessing risk.

UncategorizedView skill →

loom-typescript

TypeScript language expertise for type-safe, production-quality code. Use for advanced type system features (generics, discriminated unions, conditional and mapped types), strict mode configuration, type-safe APIs with zod/trpc/prisma, and modern tooling across Node, Deno, and Bun.

UncategorizedView skill →

loom-usage

Meta-orchestration skill for Claude driving loom itself. Use when running plans, interpreting loom status, debugging failed or blocked stages, managing worktrees, recovering from crashes, and coordinating multi-stage execution. Do NOT use for writing plans (use loom-plan-writer) or wiring checks (use loom-wiring-test).

UncategorizedView skill →

loom-webhooks

Webhook implementation and consumption patterns. Use when building webhook endpoints, receivers, or senders — covering HMAC signature verification, retry with exponential backoff, idempotency keys, delivery guarantees, replay protection, dead letter queues, payload design, and monitoring.

UncategorizedView skill →

loom-wiring-test

Generates wiring verification YAML for loom plans. Use when writing acceptance, artifacts, wiring, and wiring_tests fields for plan stages to prove features are actually integrated — commands registered, endpoints mounted, modules exported, components rendered.

UncategorizedView skill →

Page 3 of 3 · 122 results