Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Filter by category
63,368 results · page 1467 of 2,113
- View details
external-pr-reviewSkillProductivity
Lets your agent review external contributor pull requests and save the review as markdown files.
Ready to connect★ 82
- View details
feedback-rejection-flowSkillDev tools
Lets your agent route rejected work back for fixes, record each review round, and restart the approval process.
Ready to connect★ 82
- View details
first-officerSkillDev tools
Lets your agent run and resume Spacedork workflows, dispatching workers and managing approval steps.
Ready to connect★ 82
- View details
fo-dispatch-recoverySkillAI & models
Gives your agent ready-made fallback steps for restarting tasks after a delegated job fails to launch.
Ready to connect★ 82
- View details
fo-gate-lifecycleSkillDev tools
Walks your agent through preparing, presenting, and closing review-and-approval checkpoints in a Spacedock workflow.
Ready to connect★ 82
- View details
fo-status-viewerSkillMedia
Lets your agent check and update Spacedock workflow task statuses using structured queries.
Ready to connect★ 82
- View details
gedcom-creatorSkillFiles & storage
Lets your agent create GEDCOM family tree files from research notes, JSON, or tables.
Ready to connect★ 80
- View details
github-release-guideSkillDev tools
Lets your agent check a GitHub repo is safe to release, a github claude skill for going public or shipping new versions.
Ready to connect★ 81
- View details
graSkillDocs & knowledge
Lets your agent research family history, analyze records, resolve conflicts, and write cited genealogy proof summaries.
Ready to connect★ 80
- View details
guardrails-reviewerSkillAI & models
Lets your agent review project guardrails to check engineering standards like trigger criteria and rule enforceability.
Ready to connect★ 82
- View details
guardrails-writerSkillMonitoring & ops
Lets your agent write project guardrails that define shared constraints and update rules across teams.
Ready to connect★ 82
- View details
guideSkillMedia
Helps your agent decide which skill to use next by matching the current task to the right workflow.
Ready to connect★ 82
- View details
hld-reviewerSkillSecurity
Lets your agent review a High-Level Design document for responsibilities, trust, dependencies, and failure boundaries.
Ready to connect★ 82
- View details
hld-writerSkillDocs & knowledge
Lets your agent write high-level design documents from a finished PRD and API contract.
Ready to connect★ 82
- View details
hyper-waterfallSkillProductivity
Lets your agent start and manage issue-based Hyper-Waterfall tasks and find the related manuals and skills.
Ready to connect★ 82
- View details
interview-scheduleSkillCommunication
Lets your agent schedule candidate interviews in Feishu, invite interviewers, and draft candidate invitations.
Ready to connect★ 80
- View details
lld-reviewerSkillCloud & infra
Lets your agent review low-level design documents (LLD review) and approved fix plans for completeness.
Ready to connect★ 82
- View details
lld-writerSkillDocs & knowledge
Lets your agent write low-level design documents from a completed PRD, HLD, or API contract.
Ready to connect★ 82
- View details
m01-ownershipSkillDev tools
CRITICAL: Use for ownership/borrow/lifetime issues. Triggers: E0382, E0597, E0506, E0507, E0515, E0716, E0106, value moved, borrowed value does not live long enough, cannot move out of, use of moved value, ownership, borrow, lifetime, 'a, 'static, move, clone, Copy, 所有权, 借用, 生命周期
Ready to connect★ 53
- View details
m02-resourceSkillDev tools
CRITICAL: Use for smart pointers and resource management. Triggers: Box, Rc, Arc, Weak, RefCell, Cell, smart pointer, heap allocation, reference counting, RAII, Drop, should I use Box or Rc, when to use Arc vs Rc, 智能指针, 引用计数, 堆分配
Ready to connect★ 53
- View details
m03-mutabilitySkillDev tools
CRITICAL: Use for mutability issues. Triggers: E0596, E0499, E0502, cannot borrow as mutable, already borrowed as immutable, mut, &mut, interior mutability, Cell, RefCell, Mutex, RwLock, 可变性, 内部可变性, 借用冲突
Ready to connect★ 53
- View details
m04-zero-costSkillDev tools
CRITICAL: Use for generics, traits, zero-cost abstraction. Triggers: E0277, E0308, E0599, generic, trait, impl, dyn, where, monomorphization, static dispatch, dynamic dispatch, impl Trait, trait bound not satisfied, 泛型, 特征, 零成本抽象, 单态化
Ready to connect★ 53
- View details
m05-type-drivenSkillMedia
CRITICAL: Use for type-driven design. Triggers: type state, PhantomData, newtype, marker trait, builder pattern, make invalid states unrepresentable, compile-time validation, sealed trait, ZST, 类型状态, 新类型模式, 类型驱动设计
Ready to connect★ 53
- View details
m06-error-handlingSkillDev tools
CRITICAL: Use for error handling. Triggers: Result, Option, Error, ?, unwrap, expect, panic, anyhow, thiserror, when to panic vs return Result, custom error, error propagation, 错误处理, Result 用法, 什么时候用 panic
Ready to connect★ 53
- View details
m07-concurrencySkillDev tools
CRITICAL: Use for concurrency/async. Triggers: E0277 Send Sync, cannot be sent between threads, thread, spawn, channel, mpsc, Mutex, RwLock, Atomic, async, await, Future, tokio, deadlock, race condition, 并发, 线程, 异步, 死锁
Ready to connect★ 53
- View details
m09-domainSkillMedia
CRITICAL: Use for domain modeling. Triggers: domain model, DDD, domain-driven design, entity, value object, aggregate, repository pattern, business rules, validation, invariant, 领域模型, 领域驱动设计, 业务规则
Ready to connect★ 53
- View details
m10-performanceSkillDev tools
CRITICAL: Use for performance optimization. Triggers: performance, optimization, benchmark, profiling, flamegraph, criterion, slow, fast, allocation, cache, SIMD, make it faster, 性能优化, 基准测试
Ready to connect★ 53
- View details
m11-ecosystemSkillDev tools
Use when integrating crates or ecosystem questions. Keywords: E0425, E0433, E0603, crate, cargo, dependency, feature flag, workspace, which crate to use, using external C libraries, creating Python extensions, PyO3, wasm, WebAssembly, bindgen, cbindgen, napi-rs, cannot find, private, crate recommend
Ready to connect★ 53
- View details
m12-lifecycleSkillMedia
Use when designing resource lifecycles. Keywords: RAII, Drop, resource lifecycle, connection pool, lazy initialization, connection pool design, resource cleanup patterns, cleanup, scope, OnceCell, Lazy, once_cell, OnceLock, transaction, session management, when is Drop called, cleanup on error, guar
Ready to connect★ 53
- View details
m13-domain-errorSkillMedia
Use when designing domain error handling. Keywords: domain error, error categorization, recovery strategy, retry, fallback, domain error hierarchy, user-facing vs internal errors, error code design, circuit breaker, graceful degradation, resilience, error context, backoff, retry with backoff, error
Ready to connect★ 53
Popular skills lists
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
- Best Claude skills for superpowers
- Best Claude skills for obsidian
- Best Claude skills for frontend design
- All best lists
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
61,234 of the 63,368 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your workspace and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.