14 个（2389-research 的仓库） · 按人气排序
Use when adding a plugin to the marketplace, or when authoring, editing, or re-rendering a scene under scripts/animations/scenes/ — including when a scene fails the render contract, the contrast gate, or the grid baseline.
中文简介正在准备中。当前显示原文说明。
Create high-converting, visually distinctive landing pages. Use when building marketing pages, product launches, SaaS homepages, or any single-page conversion-focused website. Guides section-by-section composition with anti-AI-slop principles.
中文简介正在准备中。当前显示原文说明。
Performs static analysis of binary code using radare2 and Ghidra — function enumeration, cross-reference tracing, decompilation, and control flow graphs without executing the binary. Use when disassembling or decompiling code, mapping functions, tracing data flow, or building hypotheses before dynamic verification.
中文简介正在准备中。当前显示原文说明。
Analyzes ELF binaries, executables, and firmware images to understand behavior without source code; coordinates sub-skills binary-re:triage, binary-re:static-analysis, binary-re:dynamic-analysis, binary-re:synthesis, and binary-re:tool-setup. Use when working with a binary, executable, or ELF file; asked to reverse engineer, disassemble, decompile, or figure out what something does; targeting ARM64, ARMv7, x86_64, or MIPS; or analyzing Python bytecode (.pyc, marshal). For Python bytecode analysis, see docs/python-bytecode-re.md.
中文简介正在准备中。当前显示原文说明。
Observes runtime behavior of binaries via QEMU emulation, GDB debugging, and Frida hooking — syscall tracing, breakpoints, memory inspection, and function interception. Use when running, tracing, or debugging a binary, verifying hypotheses from static analysis, or watching actual syscalls, network calls, or file access; requires human approval before any execution.
中文简介正在准备中。当前显示原文说明。
Compiles binary analysis findings into structured reports — correlates facts from triage, static, and dynamic phases, validates hypotheses against evidence, and produces traceable documentation. Use when ready to summarize findings, generate a report, document what a binary does, or prepare results for handoff or archival.
中文简介正在准备中。当前显示原文说明。
Installs and configures reverse engineering tools including radare2, Ghidra, GDB, QEMU, Frida, and cross-compilation toolchains for ARM64, ARMv7, x86_64, and MIPS. Use when a tool command fails, a required tool is missing, or you need to set up a fresh analysis environment.
中文简介正在准备中。当前显示原文说明。
Fingerprints unknown binaries using rabin2 — detects architecture (ARM, x86, MIPS), ABI, libc, dependencies, and strings of interest. Use when first encountering an unknown binary, ELF file, or firmware blob, or when you need architecture or ABI information before committing to deeper analysis.
中文简介正在准备中。当前显示原文说明。
Judge board subskill for simmer. Dispatches a panel of judges with different lenses, runs one deliberation round where they challenge each other's scores, then synthesizes consensus scores + single ASI. Drop-in replacement for simmer-judge that produces identical output format. Do not invoke directly — dispatched by the simmer orchestrator when JUDGE_MODE is board.
中文简介正在准备中。当前显示原文说明。
Setup subskill for simmer. Inspects the artifact or workspace, infers evaluation contracts and search space, proposes a complete assessment to the user, and produces a setup brief after confirmation. Conversational, not form-based — the agent does the work of understanding the problem, then presents what it found. Do not invoke directly — called by simmer orchestrator.
中文简介正在准备中。当前显示原文说明。
Use when user says "simmer this", "refine this", "hone this", "iterate on this", or asks to improve a specific artifact over multiple rounds. Runs an iterative refinement loop with investigation-first judges that read the code, understand the problem, and propose evidence-based improvements. Auto-selects single judge or multi-judge board based on complexity. Works on any artifact type: documents, prompts, specs, emails, creative writing, API designs, pipelines, codebases. Supports multi-file workspace targets, runnable evaluators, and open-ended optimization (model selection, pipeline topology, prompt tuning).
中文简介正在准备中。当前显示原文说明。
Generator subskill for simmer. Produces an improved version of the artifact based on the judge's ASI feedback. Handles both single-file and workspace targets. Do not invoke directly — dispatched as a subagent by the simmer orchestrator.
中文简介正在准备中。当前显示原文说明。
Judge subskill for simmer. Scores a candidate artifact against user-defined criteria on a 1-10 scale and produces ASI (highest-leverage direction) for the next generator round. Supports judge-only, runnable evaluator, and hybrid evaluation modes. Do not invoke directly — dispatched as a subagent by the simmer orchestrator.
中文简介正在准备中。当前显示原文说明。
Reflect subskill for simmer. Records iteration results in trajectory table, tracks best candidate, handles regression rollback, and passes ASI forward to the next round. Supports both single-file and workspace modes. Do not invoke directly — called by simmer orchestrator after each judge round.
中文简介正在准备中。当前显示原文说明。