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.
Category: AI & models
8,992 results · page 205 of 300
- View details
debugging-methodologySkillAI & models
Systematic root cause analysis for production and development bugs. Hypothesis-driven debugging — never guess-and-check.
Ready to connect★ 67
- View details
define-strategySkillAI & models
Product strategy workflow — chain positioning, business model, OKRs, and roadmap Use when: Defining product strategy, setting OKRs, planning roadmap, or making strategic decisions
Ready to connect★ 67
- View details
goal-driven-executionSkillAI & models
Transforms imperative instructions into declarative goals with verifiable success criteria. Enables autonomous looping until verified completion.
Ready to connect★ 67
- View details
hallucination-preventionSkillAI & models
Detects and mitigates LLM hallucinations in production pipelines. Validates AI-generated facts, code, and decisions before they reach end users or downstream systems.
Ready to connect★ 67
- View details
idea-to-specSkillAI & models
Converts vague ideas into concrete, testable specifications with acceptance criteria. No implementation begins without a spec.
Ready to connect★ 67
- View details
incremental-codingSkillAI & models
Build in verifiable increments. Never implement more than can be tested right now. Ship partial working systems over complete broken ones.
Ready to connect★ 67
- View details
integration-testingSkillAI & models
Test real system boundaries, not mocks of mocks. Integration tests verify that components work together, not that they work in isolation.
Ready to connect★ 67
- View details
lov-better-statuslineSkillAI & models
Configure and back up the agent status bar, with support for listing historical versions and restoring. Supports explicit input and result read-back. Use to update an agent status
Ready to connect★ 67
- View details
lov-cc-mvSkillAI & models
Move a project folder AND migrate all its Claude Code state in one shot — session store, prompt-up-arrow history, running-session records. Supports both directory-level moves AND session-level cherry-picking (by id, regex on first user prompt, or interactive picker). Use whenever the user wants to r
Ready to connect★ 67
- View details
lov-check-balanceSkillAI & models
Check remaining quota and reset times for agent accounts like Claude, Codex, and DeepSeek in one command, merging official subscription windows, API balances, local gateway usage, and consumption rates. Use when the user says "查我的额度", "还有多少用量", "什么时候重置", or asks how much quota is left.
Ready to connect★ 67
- View details
lov-distill-to-systemSkillAI & models
Write evidence-backed reusable experience into the most appropriate project or shared Agent specification. Supports explicit input and result read-back. Use to persist a reusable
Ready to connect★ 67
- View details
lov-do-they-love-meSkillAI & models
Turns a two-person WeChat private chat into an evidence-based love index analysis: quantifies interaction rhythm, uses a local model to distinguish work/emotional/life content, and produces a phone-portrait infographic. Use when the user says “分析我们的聊天记录”“他／她爱不爱我”, or asks for a chat relationship ana
Ready to connect★ 67
- View details
lov-fix-codex-sessionSkillAI & models
Diagnose and repair unrecoverable Codex sessions: locate dangling tool call/output entries, and after switching model providers, fix provider bindings causing Model provider not found, restoring deliverables and a path to continue.
Ready to connect★ 67
- View details
lov-skill-add-caseSkillAI & models
将已验收结果整理成官网案例，普通用户登录即可手动导入或由 Agent 投稿，无需 GitHub 权限。Use when the user asks to add or publish an accepted Skill case.
Ready to connect★ 67
- View details
lov-skill-optimizerSkillAI & models
Audit and optimize one or more existing Agent Skills from a canonical source path, then bump semver, update README/SKILL.md/skill.yaml/CHANGELOG.md, and verify installed copies and catalog synchronization. Checks frontmatter, trigger quality, CLI hygiene, naming, portability, version drift, dirty wo
Ready to connect★ 67
- View details
lov-skill-pricingSkillAI & models
Generates an explainable Skill Pricing Card for one or more Agent Skills: combining creator time and maintenance costs, user value, scarcity, purchase confidence, and ecosystem potential to output a suggested price, price range, channel strategy, and evidence gaps; trigger phrases include "给这个 Skill
Ready to connect★ 67
- View details
plan-featureSkillAI & models
Create complete development plan with parallel exploration
Ready to connect★ 67
- View details
prompt-injection-defenseSkillAI & models
Guards AI agents and LLM-powered applications against prompt injection attacks — both direct and indirect. Validates AI inputs and outputs at every trust boundary.
Ready to connect★ 67
- View details
refactoringSkillAI & models
Safe, behavior-preserving code transformation backed by tests. Refactor with evidence, not instinct.
Ready to connect★ 67
- View details
research-and-summarizeSkillAI & models
Distill complex topics into layered, actionable summaries. Start with the key insight, layer in detail, end with recommended next action.
Ready to connect★ 67
- View details
sgc-install-aiSkillAI & models
Quickly initialize production-ready AI features for an existing or new App, with options for a local Agent Client, MaaS relay channel, model preference, and matching UI. Use when the user says integrate AI, add chat/generation capabilities to an App, Agent Client, MaaS, or model selection.
Ready to connect★ 67
- View details
simplicity-firstSkillAI & models
Prevents overengineering by enforcing minimum viable code. No speculative features, no premature abstractions, no unnecessary complexity.
Ready to connect★ 67
- View details
think-before-codingSkillAI & models
Forces explicit reasoning before writing any code. Surfaces assumptions, manages confusion, and prevents hallucination by demanding clarity upfront.
Ready to connect★ 67
- View details
1c-bsl-validateSkillAI & models
Validates common module calls in BSL against a configuration export - whether the module exists and its method is exported. Works without the platform, using the index from 1c-config-index.
Ready to connect★ 66
- View details
1c-bsp-apiSkillAI & models
Reference for the API of the 1C Standard Subsystems Library (БСП/BSP) — which common modules exist, their export methods, signatures, parameter types, execution contexts, and overridable handlers. Use it when writing code in a configuration with BSP and you need to find a module name or
Ready to connect★ 66
- View details
1c-bsp-commandSkillAI & models
Add a command to a standard subsystem (BSP) add-in
Ready to connect★ 66
- View details
1c-bsp-registrationSkillAI & models
Add the BSP registration function (СведенияОВнешнейОбработке) to the object module of the external data processor
Ready to connect★ 66
- View details
1c-cf-add-objectSkillAI & models
Add a metadata object to a 1C configuration with a form, subsystem, and validation. Workflow: meta-compile → cf-edit → subsystem-edit → form-add → form-compile → validate.
Ready to connect★ 66
- View details
1c-cf-editSkillAI & models
Targeted editing of a 1C configuration. Use when you need to change configuration properties, add or remove an object from the composition, or configure default roles
Ready to connect★ 66
- View details
1c-cf-infoSkillAI & models
Analysis of 1C configuration structure - properties, composition, object counters. Use for a configuration overview - what objects exist, how many there are, and what settings they have
Ready to connect★ 66
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.
54,624 of the 55,055 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.