Enforce script-only text encoding fixes in any repository. Use when files contain mojibake, broken Cyrillic/UTF-8 text, or UTF-8 BOM issues, and require Codex to run the bundled scripts/fixmojibake.py instead of manual or ad-hoc encoding edits.
Reviews code diffs after implementation, auto-fixes safe issues, and runs specialist security and architecture reviewers on large diffs. Also triages issues and PRs when the user mentions them. Not for exploring ideas or debugging.
Detect, triage, and fix performance problems across Windows native C/C++ (clang-cl/MSVC; VTune, AMD uProf, ETW/WPA), WSL Linux, native Linux (perf/flamegraphs/GCC/Clang), and CUDA/NVIDIA environments (nvidia-smi, nvcc, Nsight Systems, Nsight Compute). Invoke when the user asks to optimize or debug performance, review…
Product readiness auditor that crawls any codebase, maps what exists, identifies gaps, incomplete code, vulnerabilities, and dead ends, then produces a prioritized remediation plan. Trigger this skill when the user says 'inspect this project', 'audit my code', 'what's broken', 'product readiness check', 'MVP audit'…
Use when debugging, tracing, or mutating state in a running or testable Java application — inject code at method entry/exit, read/write fields, trace calls, throw exceptions, or verify behavior without recompiling.
Android Memory Leak Analyser & Solver — ingests LeakCanary traces from issue-tracker tickets, fetches tickets tagged as memory leaks from the configured issue-tracker board, or accepts raw traces pasted in chat. Identifies the reference chain, user journey, root cause, and reproduction steps. Generates a concise…
Diagnose why the current Claude Code session went wrong (or generally review how it went) using the Three Gaps framework (Understanding / Specification / Execution: Context / Tooling / Reasoning). MAIN spawns a fork to diagnose, presents findings, and applies any file fix only after explicit user approval — the fork…
Use when asked to execute a QA guide, QA plan, PR QA checklist, UX test plan, end-to-end verification guide, browser-based product test plan, or output from the qa-ux-plan skill and then record, fix, and re-verify discovered issues. Applies to workflows that should iterate through evaluator-generator negotiation…
This skill should be used when the user asks to "autofix pr", "fix pr locally", "fix ci failures", "fix review comments", "iterate on pr", "fix failing checks", "fix pr comments", "make ci green", "fix the build", "address reviewer feedback", or wants to iteratively fix CI failures and review comments on a GitHub PR…
Use when you want to find and remove dead/legacy code, unused endpoints, orphaned data-streams, stale config, or unbuilt proposed-nodes that bloat a repo — a static debloat/cleanup pass over an existing architecture-map. Findings arrive as plain-language cards a non-developer can decide on, and approved findings…
Debug a failed dynobox run from its terminal output. Use this skill when the user pastes or references output from npx dynobox run (especially --debug output with failed assertions), asks why a dyno run, scenario, or assertion failed, or wants a failing dyno fixed. Produces a root-cause diagnosis and proposed fixes…
Use when working in a project that is onboarded to ig (infragraphify) and you need to answer how repos/services connect, where the code for a concept or endpoint lives, how a frontend call reaches its backend handler, what infrastructure backs a service, or the blast radius of a change — instead of grepping a…
Use when configuring Claude Code statusLine on Windows with PowerShell, especially when statusLine shows blank/empty or causes terminal layout corruption on exit.
Send elisp to the running Emacs at runtime — evaluate snippets, dump live buffer state, capture Messages output, or run a measured snippet inside a profiling session — and receive the result back as a follow-up message. The skill scopes every dispatch to the current workspace so operations like "create a buffer" or…
Use FIRST for any question about THIS codebase's structure, symbols, or relationships — where a function/class/file is defined, what calls or imports it, what breaks if you change it, how two parts connect, or to load focused source context before editing or reviewing. Routes to the cgraph MCP tools (graphquery /…
Perform a deterministic, graph-driven Change Impact Analysis for a repository. Given a set of changed files, builds a dependency graph, finds directly and transitively affected modules, validates API contracts for breaking changes, parses CODEOWNERS, and computes a 0-100 deployment risk score. Trigger on: change…
Use this skill to investigate EC2 CPU exhaustion and performance degradation. Activate when: CPU utilization is high or at 100%, instance is slow or unresponsive, CloudWatch CPU alarm has triggered, T-series CPU credits are depleted, or the user reports performance issues on an EC2 instance. This skill provides…
Use when Codex Desktop on Windows cannot enable Computer Use, Any App works but Chrome is disconnected, or plugin caches/configuration for browser, chrome, and computer-use are missing or corrupted.
Deploy a VAST DataEngine pipeline, check its status, view logs, traces, and metrics. Use when deploying a pipeline to Kubernetes, monitoring execution, or debugging function failures.
Plan, research, implement, debug, and verify software changes deliberately. Use for product or coding work that needs current technical choices, explicit tradeoffs, minimal-scope edits, and delivery-grade validation.
★not rated 2 14d agoA45 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: