prose-polish
Refactor verbose or unnatural natural-language prose — code comments, test descriptions, docstrings, user-facing text — into concise, native-sounding prose in a configured target language, using a sonnet subagent by default. Two modes: file mode rewrites a file's target-language prose in place; text mode returns the refactored text. Preserves code, identifiers, and proper-noun terms while translating ordinary technical vocabulary into the target language. Non-interactive — no user prompts. Use after generating prose with a model prone to verbosity, or to polish text before presenting it.
publicity-review
Review uncommitted diff for content unsuitable for publication to a public repository — secrets/credentials, user-specific absolute paths, internal-only URLs/hostnames, and personal identifiers. Each iteration dispatches a fresh subagent that returns findings and the main thread applies the subagent's mechanical fixes — a single pass by default, or re-dispatching up to `Max iterations` when the caller raises it. Non-interactive — no user prompts. Use as a final gate before publishing changes; designed to be called from non-interactive routines such as dev-workflow's hooks.on_complete or dev-workflow-triage's per-Finding sub-flow.
review-with-untracked
Temporarily visualize untracked new files into the git diff so a chain of diff-deriving review callees can see them, then restore the files to untracked. Runs `git add -N` on untracked new files (intent-to-add), dispatches the requested review callees (rules-review / skill-review / publicity-review / verify-diff / tidy) in order, then `git reset -- <paths>` to restore the untracked state. Holds a closed list of each callee's visualization and restore-safety assumptions. Non-interactive — no user prompts. Project-local routine — not for marketplace distribution.
rules-review
Check code changes for .claude/rules/ compliance. Use this skill when you need to verify that code changes follow project coding rules, whether as part of dev-workflow or standalone. Triggers on: rule compliance check, rules review, verify conventions, check coding standards. Best suited for hard rules (naming, imports, placement, explicit prohibitions); intent-style rules are checked on a best-effort basis.
run-node-tests
Run the repository's Node test suite under tests/ via `node --test` and report a structured verdict. Project-local routine — not for marketplace distribution.
run-tests
Verify plugins marketplace structure, version consistency, and JSON/frontmatter validity via subagent
security-scanner
Scan installed plugins and skills for security risks including malicious code AND malicious natural language instructions. Use /security-scanner to audit before installation.
skill-review
Review uncommitted skill changes against an internal checklist of skill-creator best practices and apply improvements. Use this whenever the user asks to "review skills", "check best practices", "improve SKILL.md", or wants a quality check on skill files before committing. Use this when there are uncommitted diffs in SKILL.md, README.md, or references/ files under skills/ or .claude/skills/. This is for reviewing existing skill changes, not creating new skills from scratch. Runs standalone — no external skill dependencies.
tidy
Review changed code for reuse, quality, and efficiency, then apply cleanup edits. Dispatches a fresh host-provided reviewer per iteration when available; the main thread applies mechanical edits and re-dispatches until no further edits remain. Non-interactive — no user prompts. Use after implementation as a code-cleanup pass complementary to correctness review.
tr
Translate text between Japanese and English. Auto-detects source language. Use --hq for high-quality (sonnet), --fast for standard (haiku).
triage-review
Daily review of the latest origin triage-* branch. Operator-prepared invariant — the operator fetches origin and switches the local repository to the triage branch before invocation. The skill verifies that the current branch matches `triage-*`, then dispatches `Skill(prompt-tuning)` per prompt-eligible changed file, `Skill(skill-review)` with `Base ref: main`, `Skill(publicity-review)` with `Base ref: main`, and `Skill(rules-review)` with `--base-commit main` (rules-compliance detection layer) in sequence, finally emits a summary. Project-local routine — not for marketplace distribution.
verify-bundle-sync
Verify the dev-workflow-bundle canonical and bundle copy directories are in sync. Workaround for upstream symlink bug; delete this skill and its callers when symlinks are restored.
verify-diff
Empirically verify that a code diff achieves its stated objective by dispatching a bias-free executor that actually runs auto-derived evaluation scenarios against the post-diff file. The executor returns a JSON verdict with `suggested_edits`, and this skill applies them — a single pass by default, or iteratively up to `Max iterations` when the caller raises it. Non-interactive — no user prompts. Use after applying an Edit when you need a dynamic cross-check that complements static reviewers like skill-review.
work-complete
Work completion handler. Archives the plan file. Example: /work-complete
rust-actor
Actor model expert covering message passing, state isolation, supervision trees, deadlock prevention, fault tolerance, Actix framework, and Erlang-style concurrency patterns.
rust-anti-pattern
Rust anti-patterns and common mistakes expert. Handles code review issues with clone abuse, unwrap in production, String misuse, index loops, and refactoring guidance.
rust-async
Advanced async patterns expert. Handles Stream processing, backpressure control, select/join operations, cancellation, Future trait implementation, and async runtime optimization.
rust-async-pattern
Advanced async patterns expert covering Stream implementation, zero-copy buffers, tokio::spawn lifetimes, plugin system scheduling, tonic streaming, and async lifetime management.
rust-auth
Authentication and authorization expert covering JWT, API keys, OAuth, RBAC, password hashing, distributed token storage, and session management patterns.
rust-cache
Caching and distributed storage expert covering Redis, connection pools, TTL strategies, cache patterns (Cache-Aside, Write-Through), invalidation, and performance optimization.
rust-coding
Rust coding conventions expert covering naming, formatting, comments, clippy, rustfmt, lints, code style, best practices, and idiomatic patterns.
rust-concurrency
Concurrency and async programming expert. Handles Send, Sync, threads, async/await, tokio, channels, Mutex, RwLock, deadlock prevention, and race condition debugging.
rust-const
Const generics and compile-time computation expert covering const fn, type-level computation, const evaluation, MaybeUninit arrays, and compile-time validation.
rust-coroutine
协程与绿色线程专家。处理 generator, suspend/resume, stackful coroutine, stackless coroutine, context switch, 协程, 绿色线程, 上下文切换, 生成器--- # 协程与绿色线程 ## 核心问题 **如何实现高效的轻量级并发？** 协程提供用户态的上下文切换，避免内核线程的开销。
rust-database
"Rust database skill for SQLx/Diesel/SeaORM design, transaction boundaries, migration safety, query performance, and operational reliability."---
rust-distributed
分布式系统专家。处理 Raft, 2PC, 共识算法, 分布式事务, 分布式一致性, 分布式协调--- # 分布式系统 ## 核心问题 **如何在分布式环境中实现数据一致性和高可用？** 分布式系统需要在CAP理论中做出权衡。
rust-dpdk
用户态网络专家。处理 DPDK, 用户态驱动, 高性能网络, packet processing, 零拷贝, RSS 负载均衡--- # 用户态网络 (DPDK) ## 核心问题 **如何实现百万级 PPS 的高性能网络数据包处理？** 传统内核网络栈有太多上下文切换和内存拷贝开销。
rust-ebpf
eBPF 与内核模块专家。处理 eBPF program, kernel module, map, tail call, perf event, 跟踪, 内核探针, 性能分析--- # eBPF 与内核编程 ## 核心问题 **如何在不修改内核的情况下安全地扩展内核功能？** eBPF 提供在内核中安全执行用户态代码的能力。
rust-ecosystem
Rust ecosystem expert covering crate selection, library recommendations, framework comparisons, async runtime choices (tokio, async-std), and common tools.
rust-embedded
嵌入式与 no_std 专家。处理 no_std, embedded-hal, 裸机开发, 中断, DMA, 资源受限环境等问题。触发词：no_std, embedded, embedded-hal, microcontroller, firmware, ISR, DMA, 嵌入式, 裸机--- # 嵌入式与 no_std 开发 ## 核心问题 **如何在资源受限环境或没有标准库的情况下编程？** no_std 不是 Rust 的子集，而是一种不同的编程模式。
rust-error
Error handling expert covering Result, Option, panic strategies, custom error types with thiserror/anyhow, error propagation patterns, and context-rich error chains.
rust-error-advanced
深入错误处理专家。处理 Result vs Option, thiserror, anyhow, error context, library vs application errors, 错误处理, Result 用法, 什么时候用 panic--- # 深入错误处理 ## 核心问题 **这个失败是预期的还是 bug？** 错误处理策略决定代码的健壮性。
rust-ffi
FFI cross-language interop expert covering C/C++ bindings, bindgen, cbindgen, PyO3, JNI, memory layout, data conversion, and safe FFI patterns.
rust-gpu
GPU 内存与计算专家。处理 CUDA, OpenCL, GPU memory, compute shader, memory coalescing, zero-copy, 显存管理, 异构计算--- # GPU 内存与计算 ## 核心问题 **如何在 Rust 中高效管理 GPU 内存和异构计算？** GPU 计算需要特殊的内存管理策略和同步机制。
rust-learner
Rust learning and ecosystem tracking expert covering version updates, new features, RFC tracking, crate updates, best practice evolution, and learning resources.
rust-lifetime-complex
Advanced lifetime expert covering HRTB, GAT, 'static bounds, trait object constraints, type system conflicts, and lifetime elision edge cases.triggers: - lifetime - HRTB - GAT - higher-ranked - 'static - trait object - one type is more general - lifetime conflict--- # Advanced Lifetime and Type System Expert ## Core Question **Why won't this type conversion compile?** The type system's boundaries are often surprising.
rust-linear-type
线性类型与资源管理专家。处理 Destructible, 资源清理, RAII, unique object, linear semantics, 线性语义, 资源所有权, 独占语义--- # 线性类型 ## 核心问题 **如何保证资源不被泄漏或被重复释放？** 线性类型语义保证每个资源被精确使用一次。
rust-macro
Macro and procedural metaprogramming expert covering macro_rules!, derive macros, proc-macros, compile-time computation, and code generation patterns.
rust-middleware
Web middleware expert covering request tracking, CORS configuration, rate limiting, authentication guards, compression, and middleware composition patterns.
rust-mutability
Interior mutability expert covering Cell, RefCell, Mutex, RwLock patterns, borrow conflicts (E0596, E0499, E0502), and thread-safe mutation strategies.
rust-observability
"Rust observability skill for tracing, metrics, structured logging, OpenTelemetry pipelines, and production incident diagnostics."---
rust-ownership
Ownership, borrowing, and lifetime expert. Handles compiler errors E0382, E0597, E0506, E0507, E0515, E0716, E0106 and provides systematic solutions for memory safety patterns.
rust-performance
Performance optimization expert covering profiling, benchmarking, memory allocation, SIMD, cache optimization, false sharing, lock contention, and NUMA-aware programming.
rust-pin
Pin and self-referential types expert covering Pin, Unpin, Future, async state machines, pinning projection, and memory stability guarantees.
rust-resource
智能指针与资源管理专家。处理 Box, Rc, Arc, Weak, RefCell, Cell, interior mutability, RAII, Drop, 堆分配, 引用计数, 智能指针--- # 智能指针与资源管理 ## 核心问题 **这个资源应该用什么方式管理？** 选择正确的智能指针是 Rust 编程的核心决策之一。
rust-skill
Rust 编程专家技能。处理所有 Rust 相关问题：编译错误、所有权、生命周期、并发、async/await、性能优化等。触发词：Rust, cargo, 编译错误, ownership, borrow, lifetime, async, tokio, Send, Sync, Result, Error--- # Rust Expert Skill 我会像经验丰富的 Rust 开发者一样思考和解决问题。 ## 我的思维方式 ### 1. 安全第一 Rust 的类型系统是我的安全网。每一个 `&` 和 `mut` 都有其意义。 ### 2. 零成本抽象 高级代码不应该有运行时开销。如果有疑问，性能测试会说话。 ### 3. 所有权驱动设计 谁拥有这个数据？" 是我最先问的问题。 ### 4. 编译时检查优于运行时检查 尽可能在编译期发现问题，而不是依赖运行时检查。
rust-skill-index
Rust 技能索引。提供所有技能的快速导航和查询入口。触发词：skill, index, 技能, 索引, 目录--- # Rust 技能索引 > **当前共 38 个技能**，完整内容请参见根目录 `SKILL.md`
rust-testing
"Rust testing expert for unit, integration, async, property-based, concurrency, and benchmark testing workflows."---
rust-type-driven
Type-driven design expert covering newtype pattern, type state, PhantomData, marker traits, builder pattern, compile-time validation, sealed traits, and zero-sized types (ZST).
rust-unsafe
Unsafe code and FFI expert covering raw pointers (*mut, *const), FFI patterns, transmute, union, #[repr(C)], SAFETY comments, soundness rules, and undefined behavior prevention.
Page 746 of 1681 · 84020 results
