Yuansheng-Org
Yuansheng-Org/yuansheng-kit
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Yuansheng-Org/yuansheng-kit --skill capability-skill命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Diagnose RISC-V performance root causes and give evidence-based guidance without editing code, generating patches, or choosing implementations. Use for a named function or hot region with perf annotate or perf report, objdump or llvm-objdump disassembly, and optional perf stat, readelf -A, or hwprobe; or for RISC-V/RVV performance questions about unvectorized loops, vsetvl, LMUL/register groups, fixed-width VLEN/LMUL, packed low-bit decoding, hand-written assembly, matrix-engine or packed-SIMD offload, control flow or layout, register pressure, FP, traps, JIT codegen, timers, interrupts, privileged CSRs, glibc, Go, or crypto. Supports profile-backed diagnosis, labeled static-only analysis, and comparison of a few functions measured with the same event, input, and window. Do not use for non-RISC-V targets, isolated instruction/CSR/extension semantics, code-change or patch requests, or implementation selection. With no profile or disassembly, return a constrained hypothesis-only blueprint without asking.
Python coding standards, idioms, and review guidance for writing, reviewing, refactoring, and organizing Python code. Use when working on Python modules, functions, tests, package layout, type hints, error handling, context managers, generators, dataclasses, decorators, concurrency patterns, performance improvements, or Python anti-pattern cleanup.
Require an explicit official or user-provided verification source for the active Yuansheng Craft patch plan before creating and authorizing a candidate-specific verification manifest.
基于 SOC 职业分类
正在显示 SKILL.md
| name | capability-skill |
| description | Load a deterministic capability-probe sentinel. |
CAPABILITY_SKILL_BODY_SENTINEL
This skill exists only to verify isolated OpenCode Skill discovery and loading.