Định vị dòng trước khi đọc file hoặc tìm file trong cây thư mục — tránh đọc mù, tiết kiệm token. Dùng khi cần tìm hàm, class, symbol, hoặc bất kỳ pattern nào trong source code trước khi gọi viewrange. Hai công cụ: findtree.py (tìm file nào có chứa pattern) và findtool.py (tìm dòng nào trong một file).
Use when optimizing or diagnosing GPU workload performance with CUDA, CUTLASS, Triton, PyTorch, vLLM or TensorRT-LLM; interpreting NCU, Nsys or PyTorch Profiler evidence; or preparing the workload and correctness checks for such optimization. General coding, skill maintenance and conceptual GPU questions do not…
Audit, score, remediate, and verify repositories across code hygiene, architecture hygiene, and engineering hygiene. Use for an explicit Rigor3 or three-hygiene request, a strict repository-wide quality audit, a cross-dimensional cleanup plan, or before-and-after verification. Do not use for an ordinary focused review…
After resolving any bug, save what broke, the root cause, and the fix as a CogmemAi memory so the same problem never has to be debugged twice. Use immediately after a bug is fixed, after diagnosing a flaky test, after recovering from a production incident, or after the user says "got it working", "that fixed it"…
Query the codebase-intelligence CLI to understand TypeScript architecture, dependencies, blast radius, and risk before reading files. Use for any "how is this structured", "what breaks if I change X", "where is the complexity" question.
Systematic evidence-based debugging using runtime logs. Generates hypotheses, instruments code with NDJSON logs, guides reproduction, analyzes log evidence, and iterates until root cause is proven with cited log lines. Use when the user reports a bug, unexpected behavior, or asks to debug an issue.
Run safelint static analysis on the user's project and present Holzmann Power-of-Ten safety violations grouped by file. Supports any language registered with safelint (Python, JavaScript, TypeScript including TSX / AssemblyScript, Java, Rust, Go, PHP, C, and C++ today; more can be added). Use this for "safelint…
Recursive first-principles static dependency tracing for a single code entry point, producing a real-time stream-of-consciousness trace markdown that embodies the AI's reading process as a call-stack of TODOs. Given one entry script (e.g. train.py, minimalgenerateimagev3.py, main.py), the AI reads the code…
A Unity troubleshooting skill for UI elements that do not respond to clicks. It uses a runtime raycast, a test that shows which object receives a pointer event, to find obstructions or interaction settings.
Diagnose and repair Claude Desktop Mac third-party inference / 3p / DeepSeek-style Claude Code setups for best-effort parity with first-party Claude Code. Use when users mention Claude Code Mac app developer mode, Claude Desktop 3p, third-party API providers, DeepSeek V4 Pro/Flash, bypassPermissions not working…
Drive IDA Pro through the IDA Pro MCP like a senior reverse engineer: don't just narrate decompiler output, transform the database. Use this whenever the user is reverse engineering, analyzing malware, working a crackme or CTF, or doing binary/firmware analysis with IDA Pro over an MCP connection (mrexodia/ida-pro-mcp…
A debugging workflow that reproduces a problem with a failing test, collects evidence, finds the underlying cause, applies a fix, and runs regression checks. Regression checks verify that the fix does not break behavior that already worked.
Rebound recomposition budget monitor skill for Compose performance analysis. Guides budget class interpretation, violation diagnosis, skip rate analysis, stability optimization, CLI usage, and IDE plugin workflow. Use this skill whenever the user mentions recomposition, budget, violation, Rebound, skip rate, jank…
Use this skill when the user wants to investigate a bug, defect, incident, or quality issue and find its root cause — including requests to run a "5 whys" analysis, write a postmortem, do a root-cause analysis (RCA), figure out why a bug reached production or slipped past code review/QA, set up a recurring…
Review deeply. Fix safely. Report briefly. Work anywhere — PRs, git workspaces, non-git folders, and documents. Inspect diffs or files, classify findings, fix safe issues, verify, and loop until ready. Supports /diffwarden and /dw slash commands in Claude Code, Cursor, and Pi Agent; Codex CLI uses $diffwarden or…
Analyze, troubleshoot, and operate A1 Evo AcoustiX workflows and Denon/Marantz LAN control using measured artifacts, conservative audio-engineering reasoning, and explicit confirmation for receiver changes.
Diagnose an AIQSA installation from its read-only health telemetry, then bounded logs and process state. Use for failed or stuck runs, errors users hit, sign-in failures, timeouts, provider/tool errors, background jobs, startup failures, slow answers, users' problem reports, and preparing a sanitized summary. Collect…
ECB playback failure debugger for Unity DOTS/ECS. Load when you see: "EntityCommandBuffer playback failed", "entityExists=False", "Buffer does not exist on entity", "Component does not exist on entity", "AppendDestroyedEntityRecordError", "Invalid deferred entity", "Duplicate AddComponent during playback"…
Skill "docs" from DivyamTalwar/Structorium, covering structorium, 1. your job, 2. the workflow, outer loop — scan and check and inner loop — fix issues.
IDA Pro Python scripting for reverse engineering. Use when writing IDAPython scripts, analyzing binaries, working with IDA's API for disassembly, decompilation (Hex-Rays), type systems, cross-references, functions, segments, or any IDA database manipulation. Covers ida modules (50+), idautils iterators, and common…
★not rated 6 6mo agoA77 tokens
copy · 100%MIT
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: