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: Dev tools
16,833 results · page 206 of 562
- View details
routine-abstraction-improverSkillDev tools
Autonomous maintenance routine that flattens over-engineered
Ready to connect★ 267
- View details
routine-abstraction-policeSkillDev tools
Autonomous maintenance routine that finds imports crossing a stated
Ready to connect★ 267
- View details
routine-dead-code-removalSkillDev tools
Autonomous maintenance routine that deletes provably unreachable code
Ready to connect★ 267
- View details
routine-dup-unifierSkillDev tools
Autonomous maintenance routine that finds duplicated implementations
Ready to connect★ 267
- View details
routine-flaky-test-fixerSkillDev tools
Autonomous maintenance routine that root-causes intermittently
Ready to connect★ 267
- View details
routine-logic-bugfixerSkillDev tools
Autonomous maintenance routine that picks one tricky logic unit in a
Ready to connect★ 267
- View details
routine-logic-simplifierSkillDev tools
Autonomous maintenance routine that finds one convoluted unit of
Ready to connect★ 267
- View details
routine-shipped-feature-inlinerSkillDev tools
Autonomous maintenance routine that finds gates for fully shipped
Ready to connect★ 267
- View details
routine-useless-test-prunerSkillDev tools
Autonomous maintenance routine that finds tests that cannot fail —
Ready to connect★ 267
- View details
- View details
spike-consumer-adversarialSkillDev tools
OI-3 spike harness — heavy consumer, ADVERSARIAL arm. Worst-case early-exit test: the mid-workflow Skill call has no continuation guardrail and the guidance skill ends with a final-sounding anchor. Use only when explicitly invoked by the spike harness with a TRIAL_ID and data path.
Ready to connect★ 263
- View details
spike-guidance-adversarialSkillDev tools
OI-3 spike harness — ADVERSARIAL inline guidance variant. Worst-case anchor: ends with a final-sounding completion statement and gives NO instruction to return to the caller. Use only when a spike consumer skill invokes it.
Ready to connect★ 263
- View details
spike-guidance-forkedSkillDev tools
OI-3 spike harness — the FORKED (context fork) readability-guidance variant. Same payload as the inline variant but declared to run in a forked context. Use only when a spike consumer skill invokes it.
Ready to connect★ 263
- View details
spike-guidance-inlineSkillDev tools
OI-3 spike harness — the INLINE (non-forked) readability-guidance variant. Surfaces the shared readability standard into the calling skill's own context. Use only when a spike consumer skill invokes it.
Ready to connect★ 263
- View details
stakeholder-summarySkillDev tools
Produces a plain-language stakeholder summary from an existing feature specification, for sharing with non-technical stakeholders before implementation kicks off. Use when the user wants to draft a stakeholder summary, executive summary, or business summary of a feature spec or PRD. Does not write t
Ready to connect★ 263
- View details
update-pr-descriptionSkillDev tools
Generate a PR description from the current branch's changes against a GitHub PR, using the gh CLI. Use when writing, drafting, or updating pull request descriptions, PR summaries, or PR bodies. Does not review code or post review comments — use code-review for local review or post-code-review-to-pr
Ready to connect★ 263
- View details
wi-writerSkillDev tools
Write durable work items with scoped descriptions, testable categorized acceptance criteria, governing references, and risk-matched guards
Ready to connect★ 267
- View details
api-versioningSkillDev tools
Use when versioning Spring MVC or WebFlux APIs in Spring Boot 3 / Spring Framework 6. Covers explicit URL, header, and media-type strategies, compatibility rules, and deprecation handling.
Ready to connect★ 263
- View details
configuration-propertiesSkillDev tools
Use when introducing or correcting grouped Spring Boot configuration, typed property binding, validation, profiles or secret injection. Do not rewrite unrelated single-value configuration.
Ready to connect★ 263
- View details
hexagonal-architectureSkillDev tools
Use when the project follows hexagonal (ports & adapters) architecture. Prevents domain code from depending on Spring or JPA. Use when you see packages like domain/, application/, infrastructure/, or adapters/ in the project structure.
Ready to connect★ 263
- View details
http-interface-clientsSkillDev tools
Use when calling external HTTP APIs from Spring Boot 3 / Spring Framework 6 with declarative HttpExchange interfaces. Covers manual proxy registration, RestClient versus WebClient, and timeout and error handling conventions.
Ready to connect★ 263
- View details
layered-architectureSkillDev tools
Use when generating or modifying any Spring Boot class — controllers, services, repositories, DTOs, mappers, or configuration. Enforces strict layer separation and prevents business logic from leaking across boundaries.
Ready to connect★ 263
- View details
multi-module-mavenSkillDev tools
Use when working in a multi-module Maven project. Covers parent POM conventions, shared dependency management, inter-module rules, and build ordering.
Ready to connect★ 263
- View details
null-safetySkillDev tools
Use when annotating nullability in Spring Boot 3 / Spring Framework 6 code, integrating Kotlin, or adding static nullability checks without assuming Spring Framework 7 JSpecify defaults.
Ready to connect★ 263
- View details
oauth2-resource-serverSkillDev tools
Use when configuring Spring Boot as an OAuth2 resource server, validating JWTs from an external auth provider (Keycloak, Auth0, Okta, Cognito), extracting claims, or implementing scope-based authorization.
Ready to connect★ 263
- View details
openapi-firstSkillDev tools
Use when the project follows API-first / OpenAPI-first approach: generating controller interfaces, DTOs, and clients from an OpenAPI spec. Use when you see openapi.yaml, openapi-generator-maven-plugin, or ApiDelegate pattern in the project.
Ready to connect★ 263
- View details
problem-details-rfc9457SkillDev tools
Use when implementing error handling, exception mappers, or error response formatting. Enforces RFC 9457 (Problem Details for HTTP APIs) using Spring's built-in ProblemDetail.
Ready to connect★ 263
- View details
resilience-retrySkillDev tools
Use when adding retries, backoff, or concurrency protection to Spring Boot 3 / Spring Framework 6 services. Covers Spring Retry or Resilience4j selection, proxy behavior, and transaction limits.
Ready to connect★ 263
- View details
rest-api-conventionsSkillDev tools
Use when generating REST controllers, DTOs, success response contracts, pagination, HTTP status mapping, or API versioning. For RFC 9457 exception and error response formatting, use problem-details-rfc9457 unless the project explicitly requires a legacy error envelope.
Ready to connect★ 263
- View details
spring-boot-migrationSkillDev tools
Use when preparing a Spring Boot 3 application for Boot 4, upgrading to Boot 3.5 first, removing deprecated APIs, auditing dependencies, or planning a staged Framework 7 migration.
Ready to connect★ 263
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.
53,585 of the 54,017 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.