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
8,867 results · page 202 of 296
- View details
ecosystem-researchSkillAI & models
Research community usage patterns, real-world gotchas, and client compatibility for a specific known library, tool, or protocol feature. Use when a technical-researcher orchestrator needs community-sourced evidence about a named library or feature — bug reports, workarounds, compatibility gaps, and
Ready to connect★ 66
- View details
elementsSkillAI & models
Element type development across the schema, adapter, and flow packages — config fields, output sensors, model element construction, and the registries every element type must be added to. Element types are battery, battery_section, connection, grid, inverter, load, node, policy, and solar. Use when
Ready to connect★ 66
- View details
evaluate-sdlc-layersSkillAI & models
Validate and iterate on the SDLC Layer Separation Architecture implementation across the check categories defined in its Evaluation Checklist — cross-references, doc completeness, knowledge-explorer layer filters, research entry metadata, integration points, and plan consistency. Produces a structur
Ready to connect★ 66
- View details
fastmcp-client-cliSkillAI & models
Query and invoke tools on MCP servers using fastmcp list and fastmcp call. Use when you need to discover what tools a server offers, call tools, or integrate MCP servers into workflows.
Ready to connect★ 66
- View details
find-causeSkillAI & models
Wraps investigation requests with evidence-chain discipline. Use when asked to find out why something happens, research a root cause, debug an issue, or investigate unexpected behavior. Transforms vague investigation requests into reproducible-proof investigations with a 5-step protocol — disambigua
Ready to connect★ 66
- View details
gate-pushSkillAI & models
Single-verb branch-to-PR quality gate pipeline. Use when the user wants to gate, push, and open a PR for a branch in one command.
Ready to connect★ 66
- View details
gather-contextSkillAI & models
Research codebase — surface patterns, find prior art, prepare for brainstorm. Spawns subagents if available.
Ready to connect★ 66
- View details
ghSkillAI & models
Install and configure the GitHub CLI (gh) for AI agent environments where gh may not be pre-installed and git remotes use local proxies instead of github.com. Use when gh command not found, shutil.which returns None, need GitHub API access for issues or PRs or releases or workflow runs, or repositor
Ready to connect★ 66
- 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★ 66
- View details
groom-backlog-itemSkillAI & models
Grooms a backlog item by running RT-ICA assessment, enriching acceptance criteria, and preparing it for implementation. Use when the user asks to groom, refine, prioritize, or prepare a backlog item — activate with a backlog item number (#N) or title.
Ready to connect★ 66
- View details
groom-milestoneSkillAI & models
Grooms a GitHub milestone for parallel execution — batch-grooms ungroomed items, assesses scope gaps, analyzes cross-item dependencies via Impact Radius overlap, builds conflict groups, assigns items to execution waves, and persists the dispatch plan via dispatch_create_plan MCP tool. Calls dispatch
Ready to connect★ 66
- 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★ 66
- View details
holistic-lintingSkillAI & models
Comprehensive linting and formatting verification workflows. Provides automatic format-lint-resolve pipelines for orchestrators and sub-agents. Use when running linters, fixing ruff/mypy/bandit errors, ensuring code quality before completion, or resolving linting issues systematically.
Ready to connect★ 66
- View details
holistic-linting-resolverSkillAI & models
Linter-specific resolution workflows for ruff, mypy, pyright, and basedpyright. Provides systematic root-cause analysis procedures, suppression gates, and verification steps. Use when resolving linting errors as a sub-agent, implementing fixes systematically, or conducting type flow analysis.
Ready to connect★ 66
- 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★ 66
- 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★ 66
- 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★ 66
- View details
kage-bunshinSkillAI & models
Spawn and manage persistent interactive Claude Code CLI sessions with bidirectional communication via tmux. Provides spawn, send, read, status, list, and kill subcommands for orchestrating parallel peer sessions. Uses built-in --worktree and --tmux flags. Sessions stay alive for multi-turn steering.
Ready to connect★ 66
- View details
kaizen-improvementSkillAI & models
Transform transcript analysis findings into actionable improvements. Triggers on "generate hooks from findings", "improve agent", "fix anti-pattern", "kaizen improvement", "generate hook proposals", or "create improvement plan". Provides templates for hook generation, agent prompt refinement, skill
Ready to connect★ 66
- View details
llamafileSkillAI & models
When setting up local LLM inference without cloud APIs. When running GGUF models locally. When needing OpenAI-compatible API from a local model. When building offline/air-gapped AI tools. When troubleshooting local LLM server connections.
Ready to connect★ 66
- View details
lov-agent-instructionsSkillAI & models
诊断或完善项目 Agent 指令文件，适配不同宿主并保留真实工程约定。支持明确输入与结果回读。Use to review or improve
Ready to connect★ 66
- View details
lov-better-statuslineSkillAI & models
配置并备份 Agent 状态栏，支持列出历史版本和恢复。支持明确输入与结果回读。Use to update an agent status
Ready to connect★ 66
- 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★ 66
- View details
lov-check-balanceSkillAI & models
一条命令查清 Claude、Codex、DeepSeek 等 agent 账号的剩余额度与重置时间，合并官方订阅窗口、API 余额、本地网关消费与消耗速率；用户说“查我的额度”“还有多少用量”“什么时候重置”，或问 how much quota is left 时使用。
Ready to connect★ 66
- View details
lov-distill-to-systemSkillAI & models
把有证据的可复用经验写入最合适的项目或共享 Agent 规范。支持明确输入与结果回读。Use to persist a reusable
Ready to connect★ 66
- View details
lov-feedback-loopSkillAI & models
把用户对 Agent 的被动情绪与主动点赞、点踩、评分变成可统计的反馈事件， 按任务、技能、规则、全局 Prompt 的最小作用域迭代，并生成满意度复盘报告。 Use when the user rates a run, asks for satisfaction stats, or installs the feedback loop into another agent.
Ready to connect★ 66
- View details
lov-fix-codex-sessionSkillAI & models
诊断并修复无法恢复的 Codex 会话：定位悬挂 tool call/output，并在切换模型 提供商后处理 Model provider not found 的 provider 绑定，恢复交付物与可继续路径。
Ready to connect★ 66
- 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★ 66
- 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★ 66
- 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★ 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.
53,462 of the 53,895 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.