Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mickeyyaya/refactoring-skills --skill skill-cataloggit clone --depth 1 https://github.com/mickeyyaya/refactoring-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mickeyyaya/refactoring-skills/skill-catalog)<a href="https://agentmods.dev/skills/mickeyyaya/refactoring-skills/skill-catalog"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/skill-catalog/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mickeyyaya/refactoring-skills/skill-catalog"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/skill-catalog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.04741 |
| Opus 5 | $0.00026 | $0.02371 |
| Sonnet 5 | $0.00011 | $0.00948 |
| Haiku 4.5 | $0.00005 | $0.00474 |
Grade A, and why
skill-catalog scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Catalog — Navigation & Dispatch Index
Overview
This catalog is the entry point for the entire skill library. When you are unsure which skill to use, start here. The catalog maps common tasks and scenarios to the right skill so you spend less time searching and more time doing.
When to use: Any time you are unsure which skill applies to your current task, are looking for a skill by domain or keyword, want to see what coverage the library provides, or need to cross-reference related skills for a complex task.
This is a pure navigation document — it does not teach patterns itself. Each listed skill contains the full detail, examples, red flags, and language-specific code.
Quick Dispatch Table
Use this table for fast lookup. Find the scenario closest to your current task, then open the mapped skill.
| Scenario / Task | Skill to Use |
|---|---|
| Unsure which skill applies | You are here — read the category index below |
| Code smells, unclear ownership, long methods | detect-code-smells |
| Move, extract, inline, or rename code safely | refactor |
| Break large methods into smaller steps | refactor-composing-methods |
| Replace conditionals, loops, or callbacks with FP | refactor-functional-patterns |
Simplify long if/else chains or switch blocks |
refactor-simplifying-conditionals |
| Simplify method signatures or argument lists | refactor-simplifying-method-calls |
| Move fields, methods between classes | refactor-moving-features |
| Replace primitives with classes, enums, objects | refactor-organizing-data |
| Abstract or generalize duplicated logic | refactor-generalization |
| Decide whether and how to refactor | refactoring-decision-matrix |
| Choose creational or structural design patterns | design-patterns-creational-structural |
| Choose behavioral design patterns | design-patterns-behavioral |
| Detect which patterns exist in code | pattern-detection-walkthroughs |
| Full PR review workflow | review-code-quality-process |
| SOLID principles and clean code review | review-solid-clean-code |
| API contract and REST interface review | review-api-contract |
| Quick review checklist reference | review-cheat-sheet |
| Detect anti-patterns and performance issues | anti-patterns-catalog |
| CPU/memory/database performance anti-patterns | performance-anti-patterns |
| Error handling, retry, circuit breaker | error-handling-patterns |
| Async, concurrency, race conditions, locking | concurrency-patterns |
| Type safety, generics, branded types | type-system-patterns |
| Dependency injection, inversion of control | dependency-injection-module-patterns |
| Language-specific idioms (Go, Rust, Python, TS, Java) | language-specific-idioms |
| Security review, injection, secrets, OWASP | security-patterns-code-review |
| Authentication and authorization patterns | auth-authz-patterns |
| Multi-tenant data isolation, scoping | multi-tenancy-patterns |
| REST API design, versioning, pagination | review-api-contract |
| GraphQL schema design, gRPC service definitions | graphql-grpc-api-patterns |
| Rate limiting, throttling, quota management | api-rate-limiting-throttling |
| WebSockets, SSE, real-time push | real-time-communication-patterns |
| Message queues, pub/sub, broker patterns | message-queue-patterns |
| Database queries, indexes, transactions | database-review-patterns |
| Caching strategy, eviction, cache invalidation | caching-strategies |
| Search indexes, Elasticsearch, query optimization | search-indexing-patterns |
| ETL, data pipelines, streaming | data-pipeline-patterns |
| Input validation, schema validation, parsing | data-validation-schema-patterns |
| Architectural decisions, layering, hexagonal | architectural-patterns |
| Domain-driven design, bounded contexts | domain-driven-design-patterns |
| Event sourcing, CQRS, projections | event-sourcing-cqrs-patterns |
| Microservices, resilience, service mesh | microservices-resilience-patterns |
| Database migrations, schema evolution | migration-patterns |
| CI/CD pipelines, automated delivery | cicd-pipeline-patterns |
| Container orchestration, Kubernetes patterns | container-kubernetes-patterns |
| Feature flags, progressive delivery, canary | feature-flags-progressive-delivery |
| Observability, metrics, alerting | observability-patterns |
| Distributed tracing, span propagation | distributed-tracing-patterns |
| Frontend state management, Flux, Redux | state-management-patterns |
| Internationalization, localization, locale | i18n-l10n-patterns |
| Code documentation, docstrings, ADRs | code-documentation-patterns |
| Testing strategy, unit/integration/E2E | testing-patterns |
| Building an AI feature, RAG pipeline, prompt engineering | ai-ml-integration-patterns |
| LLM tool use, function calling, structured output, hallucination mitigation | ai-ml-integration-patterns |
| Monorepo tooling, dev containers, platform engineering, DX-first API design | developer-experience-patterns |
| Developer onboarding, local-prod parity, fast feedback loops | developer-experience-patterns |
| File upload, presigned URLs, resumable uploads, upload security | file-upload-media-patterns |
| Image optimization, async media processing, CDN transforms, content-addressable storage | file-upload-media-patterns |
| Calibrate review confidence, reduce false positives, tune severity | review-accuracy-calibration |
| Review LLM-generated or AI-assisted code | ai-generated-code-review |
| Write actionable, clear review feedback comments | review-feedback-quality |
| Risk-based review ordering, time-boxing, when to stop reviewing | review-efficiency-patterns |
| Select static analysis tools, configure CI quality gates | review-automation-patterns |
| Apply universal review signals across any language | cross-language-review-heuristics |
| Review Go code: goroutine leaks, context propagation, error handling | go-review-patterns |
| Review Python code: mutable defaults, type hints, GIL, idioms | python-review-patterns |
| Review TypeScript code: type escape hatches, async pitfalls, React hooks | typescript-review-patterns |
| Review Rust code: ownership, borrowing, unsafe blocks, lifetimes | rust-review-patterns |
| Review Java code: null safety, Stream API, concurrency, generics | java-review-patterns |
| Review C++ code: RAII, undefined behavior, templates, move semantics | cpp-review-patterns |
| End-to-end PR review orchestration, full workflow from load to verdict | pr-review-workflow |
| Measure review effectiveness: defect escape rate, cycle time, comment resolution | review-metrics |
| End-to-end review diagnostic walkthroughs across security, performance, concurrency | review-walkthroughs |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 412 lines · 53 tokens per session scan A 5e9b727106e6
skill-catalog is a skill published in the GitHub repository mickeyyaya/refactoring-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 4,741 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…