Preflight a Keycloak export, import or migration on a Skycloak-managed cluster against the known blockers, and diagnose a job that already failed by reading the failure reason the API records but the dashboard notice does not show. Use when an export or import fails, a migration stalls, or before moving realm data in…
Retrieve a distilled timeline of the current troubleshooting incident and generate a runbook skeleton. Returns a concise summary by default, or the full untruncated timeline on request.
Repair code with before-and-after execution evidence instead of unverified suggestions. Use when a user pastes a code snippet, error message, assignment function, Python file, notebook, or public GitHub repository and wants it explained, debugged, minimally fixed, run, tested, or reproduced. Route small snippets to…
Use when the user asks "what changed", "what breaks if I touch X", "what is the blast radius / change impact", "what should I re-verify before claiming done", "show the timeline / churn for this entity", or when working in a project that uses warpline for temporal change-impact tracking. warpline is the Weft…
Use this skill whenever the user wants to call, test, inspect, or debug an HTTP API through the Request API Tool MCP server, especially for endpoint checks, login flows, bearer-token reuse, cookies, headers, base URL setup, or repeated API requests. This skill teaches the correct use of newrequestsession…
Investigate why OpenL Tablets produced an unexpected result — wrong value, null, rejected claim, or incorrect decision. Trigger when the user asks why OpenL returned X, pastes a JSON payload for explanation, references a rule execution issue, or asks to fix a dispatch table or rule row.
Read and analyse a Salesforce Apex debug log — exceptions/FATALERROR, governor-limit consumption (SOQL/DML/CPU/heap), the execution call tree, and slow or repeated code units — then ground every finding in the org graph (map the log's code units/methods to qnames and explain WHY with trace/governor/analyzefield). Use…
Debug native C/C++/Rust or other compiled programs with GDB through MCP or shell. Use when localizing crashes, wrong results, hangs, memory corruption, recursion/control-flow bugs, or when an LLM should minimize debugger round trips with breakpoint commands, watchpoints, conditional breakpoints, and GDB Python.
An MCP server that helps a coding agent explore a codebase by analysing its structure, function relationships, and dependencies. It supports Python, TypeScript/JavaScript, Go, and Rust.
Debug applications through VS Code using DebugPilot MCP tools. Connects to VS Code's debugger to inspect state, set breakpoints, step through code, and analyze bugs — all without leaving Claude Code. Use when: (1) VS Code debugger is running and you need to inspect state, (2) investigating a bug with breakpoints, (3)…
A codebase analysis skill for examining architecture, dependencies, and possible problems. A codebase is the complete set of source files and related project code.
A diagnostic workflow for Minecraft Fabric and Forge modpacks, which are collections of Minecraft modifications. It checks Java versions, conflicting or missing mods, outdated files, launch settings, and crash logs.
Diagnose Windows slowness, crashes, storage, startup, driver, service, network, and peripheral problems using SystemLens read-only evidence. Use when a paired PC can supply relevant telemetry; do not use for changing the PC or for unrelated general Windows advice.
Diagnose Huginn app state using the state bridge MCP tools. Use when debugging UI issues, investigating unexpected behavior, checking app state, or when you need to understand what the Huginn app is currently doing.
Search and navigate a codebase through the local code-index CLI (FTS5 text + tree-sitter symbols + semantic vectors). Use for "where is symbol X defined", "where does this string/identifier/error appear", "where do we do X", a file outline, or reading a span by path:line — instead of the built-in grep when the repo is…
Investigate a Splunk production issue. Loads events, runs deterministic detectors, then drives an iterative investigation loop via MCP tools — Claude is the reasoning engine. No Ollama, no API key, no server process. Watch live progress via the TUI (uv run python -m splunk.tui).
A workflow for analysing bug data stored in a table. It helps find the right document, read its records, match differently named columns, and summarise the results.
Use when Codex must directly operate or troubleshoot the installed grok-plugin-codex MCP capability surface, including CLI/model checks, literal prompt runs or continuations, session inspection or export, and known background-job control. Do not use for bounded repository delegation, implementation, review…
★not rated 0
changed 4d agoA79 tokens
originalMIT
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: