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
55,286 results · page 829 of 1,843
- View details
change-impact-analysisSkillDev tools
Use this skill when you need to analyze how a code, configuration, or requirement change affects quality scope; triggers include change impact analysis.
Ready to connect★ 221
- View details
chaos-testingSkillDev tools
Use this skill when you need evidence-bounded chaos-testing analysis and validation preparation; triggers include 混沌测试 and chaos-testing.
Ready to connect★ 221
- View details
cherrycss-themeSkillDev tools
Guide to creating CSS themes for Cherry Studio — learn the CSS variable system, frosted glass techniques, gradient backgrounds, and more, ending with CSS code that can be pasted and used directly.
Ready to connect★ 221
- View details
ci-fix-and-verifySkillDev tools
Fixes CI failures on a PR, repeating push → wait → fix until all CI checks pass. Use when requested with "/ci-fix-and-verify [PR number]", "fix the CI", "CI is failing", "fix CI", etc.
Ready to connect★ 221
- View details
ci-test-optimizationSkillDev tools
Use this skill when you need evidence-bounded pipeline stages, feedback latency, resources, flakiness, caching/sharding, and rollback boundaries; triggers include CI 测试流水线 and CI test pipeline.
Ready to connect★ 221
- View details
circuit-breaker-testingSkillDev tools
Use this skill when you need evidence-bounded circuit-breaker-testing analysis and validation preparation; triggers include 熔断器测试 and circuit-breaker-testing.
Ready to connect★ 221
- View details
combinatorial-testingSkillMedia
Use this skill when you need to select high-risk multi-factor combinations after factors, values, and constraints are explicit; triggers include 组合测试 and combinatorial test design.
Ready to connect★ 221
- View details
database-design-quality-reviewSkillDatabases & data
Use this skill when an ERD, DDL, ORM schema, or migration plan needs an evidence-bounded database design review before implementation; triggers include database design review, migration readiness review, and schema quality audit.
Ready to connect★ 221
- View details
decision-table-testingSkillMedia
Use this skill when you need to turn conditions, rules, actions, and outcomes into an auditable set of rule combinations; triggers include 决策表测试设计 and decision table test design.
Ready to connect★ 221
- View details
dependency-failure-testingSkillDev tools
Use this skill when you need evidence-bounded dependency-failure-testing analysis and validation preparation; triggers include 依赖故障测试 and dependency-failure-testing.
Ready to connect★ 221
- View details
distributed-trace-analysisSkillDev tools
Use this skill when you need to analyze distributed traces for call paths, latency, errors, and evidence gaps; triggers include distributed trace analysis.
Ready to connect★ 221
- View details
edge-case-discoverySkillDev tools
Use this skill when you need to discover boundary, rare, limit, ordering, or combination scenarios from product and test evidence; triggers include edge case discovery.
Ready to connect★ 221
- View details
equivalence-partitioningSkillMedia
Use this skill when you need to partition inputs into evidence-backed valid, invalid, and unknown classes based on constraints, rules, and response differences; triggers include 等价类划分 and equivalence partitioning test design.
Ready to connect★ 221
- View details
error-handling-design-reviewSkillMedia
Use this skill when error taxonomy, retries, timeouts, fallback, or recovery design needs an evidence-bounded review before implementation; triggers include error handling design review, failure-path review, and recovery readiness review.
Ready to connect★ 221
- View details
failover-testingSkillDev tools
Use this skill when you need evidence-bounded failover-testing analysis and validation preparation; triggers include 故障切换测试 and failover-testing.
Ready to connect★ 221
- View details
flaky-test-analysisSkillDev tools
Use this skill when you need to investigate intermittent test failures from run history and evidence; triggers include flaky test analysis.
Ready to connect★ 221
- View details
focus-coachSkillDev tools
Chinese strategic focus coach. Used when the user needs to make trade-offs between multiple goals, projects, or learning directions; determine the current main line, biggest constraint, phase goals, whether to continue/pause/pivot, or conduct weekly or phase reviews based on learning progress. In le
Ready to connect★ 221
- View details
full-code-reviewSkillMedia
Performs a full code review from a code owner's perspective before submitting a PR. Proceeds in the order of understanding the WHY → design → AST/core types → implementation (sequential reviews by multiple agents), interacting with the user at each phase to fix issues and repeating until quality pro
Ready to connect★ 221
- View details
functional-testingSkillMedia
Use this skill when you need to design functional test plans or cases for business flows, UI, data, and integrations; triggers include functional testing and functional test cases.
Ready to connect★ 221
- View details
learning-coachSkillProductivity
Advanced personal learning coach in Chinese. Use when the user says “开始学习 X”, “继续/下一课”, “学完了”, “记录进度/打卡”, or “我学到哪了/还要多久”, is learning programming, agents, writing, languages, exams, research, or professional skills through real projects, source code, portfolios, problems, or tasks, or keeps asking
Ready to connect★ 221
- View details
llm-consistency-testingSkillAI & models
Use this skill when you need evidence-bounded repeat inputs, version/model/prompt factors, invariants, variance evidence, and comparison boundaries; triggers include LLM 一致性 and LLM consistency.
Ready to connect★ 221
- View details
llm-evaluation-designSkillDatabases & data
Use this skill when you need to design LLM evaluation datasets, judges, metrics, and human-review boundaries; triggers include llm evaluation design.
Ready to connect★ 221
- View details
llm-hallucination-testingSkillAI & models
Use this skill when you need evidence-bounded claim-to-source relations, unsupported assertions, abstention, uncertainty, and evidence review; triggers include LLM 幻觉 and LLM hallucination.
Ready to connect★ 221
- View details
manual-testingSkillDev tools
Use this skill when you need to plan manual or exploratory testing with charters, heuristics, and session records; triggers include manual testing and exploratory testing.
Ready to connect★ 221
- View details
metamorphic-testingSkillMedia
Use this skill when you need to derive test candidates from input transformations and expected relations when a direct oracle is limited; triggers include 变形测试 and metamorphic test design.
Ready to connect★ 221
- View details
metrics-anomaly-analysisSkillMonitoring & ops
Use this skill when you need to identify, contextualize, and investigate metric anomalies from observability evidence; triggers include metrics anomaly analysis.
Ready to connect★ 221
- View details
mock-quality-reviewSkillDev tools
Use this skill when you need to review mock fidelity, contract alignment, over-mocking, and drift evidence; triggers include Mock 质量评审 and mock quality review.
Ready to connect★ 221
- View details
model-based-testingSkillMedia
Use this skill when you need to derive test-path candidates from sourced behavior, state, or process models; triggers include 基于模型的测试 and model-based test design.
Ready to connect★ 221
- View details
multi-agent-testingSkillAI & models
Use this skill when you need evidence-bounded delegation, coordination, shared state, conflicts, ownership, termination, and traceability; triggers include 多 Agent 协作 and multi-agent coordination.
Ready to connect★ 221
- View details
mutation-testing-analysisSkillDev tools
Use this skill when you need to interpret mutation operators, killed and survived mutants, and evidence limits; triggers include 变异测试分析 and mutation testing analysis.
Ready to connect★ 221
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.
54,855 of the 55,286 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 gateway 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.