15,663 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Active triager — normalizes a raw bug issue into a fix-ready L1 problem or rejects it. First pass on every bug-labeled issue; re-entered on harness kick-back with the failed attempt as evidence. Never fixes, never localizes on first pass.
Top-down, whole-system audit of a codebase's DEEP LOGIC - the bugs that live in the SEAMS between modules, not inside any one file. Finds contracts that drift across module boundaries, invariants enforced on one path but broken on a sibling path, cross-cutting responsibilities (deletion cascade, tenant-scope…
Refatoração sistemática de código baseada na metodologia de Martin Fowler. Use quando usuários pedem para refatorar código, melhorar estrutura de código, reduzir dívida técnica, limpar código legado, eliminar code smells ou melhorar a manutenibilidade do código. Esta skill guia através de uma abordagem em fases com…
Fast project health check. Structure completeness, namespace purity, file staleness, hook functionality, decisions format, memory adoption, dream history, setup quality — all from local files. Works with or without git. No agents, no external fetches, 15-30 seconds. For deep analysis with feature adoption and session…
Structured debugging assistant. Use /debug to get a guided diagnosis of any bug — Claude will ask the right questions and then pinpoint the root cause.
Static call-path engine. Answers "what calls what?" from structure, not execution. Use before reading source files — it is faster and token-cheaper than grep-and-read.
A connectivity-checking workflow for Kuaishou internal services, including single sign-on, configuration services, caches, and bastion hosts. A bastion host is a controlled server used to reach protected systems.
Use when a shell command unexpectedly changed or deleted files, when you need to find which command touched a file, or to roll files back to before some command — bashback snapshots every command's file side effects and can undo them.
Refactor, review, and harden code without changing intended behavior. Use for cleanup, code review remediation, extracting responsibilities, simplifying modules, improving tests, lint remediation, duplicate detection, and preventing static-analysis-grade security, reliability, and maintainability issues across major…
Lets the agent inspect and automate a live Chrome instance through the DevTools protocol: performance traces, network, console. Runs locally from the chrome-devtools-mcp npm package.
A backend API investigation skill that maps interfaces, traces individual request paths, and diagnoses server errors. It applies to common frameworks such as Spring, Express, FastAPI, and Gin.
Expose running process manipulation tools (memory read/write, pattern scans, hooks, detours, Lua scripts) inside a 64-bit target process like Star Citizen.
Explore and understand code structure efficiently using semantic navigation. Use when exploring unfamiliar code, understanding architecture, finding symbol relationships, or investigating how something works.
Structured human-in-the-loop debugging mode for when static code reading isn't enough. Use this skill whenever you're stuck debugging an issue where you can't tell what's actually happening at runtime — async timing, complex control flow, multiple call paths, conditional branches, or bugs that only reproduce when the…
Read-only root-cause diagnosis for bugs, failures, flaky behavior, and performance regressions. Use when the user asks to diagnose, investigate, debug, explain, or find the cause of broken, throwing, failing, incorrect, intermittent, or slow behavior. Gather evidence and report the likely root cause without modifying…
Use this skill when the user asks for a review, audit, evaluation or analysis of a codebase, to identify bugs, security vulnerabilities, outdated dependencies or runtimes, performance bottlenecks, or code quality concerns.
Performs a focused audit of a declared system intent to restore confidence by examining relevant states, signals, and evidence, without modifying intent definitions or health automatically.
★not rated 2 5mo agoA38 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: