Skip to content

Explore skills

Search every indexed skill by name, description, repository or instructions, then narrow the results.

Showing 74011–74040 of 76562 skills

go-spec-reviewerinference-gateway/inference-gatewayReview a Go design spec before implementation begins - dispatch a subagent that checks a design doc for completeness, consistency, and idiomatic Go (simplicity, small consumer-defined interfaces, explicit wrapped errors, context propagation) plus Cobra/Viper conventions where applicable. Use when a user has a Go spec to review, asks "is this spec ready?", or is about to implement from a written design. Distilled from spf13/go-skills and adapted to this repo's conventions.Stars: 213Updated Claude CodeCodexUnverifiedInstall
luamakeactboy168/luamakeLuamake 构建系统指南——用于当前项目的 `luamake` / `make.lua` / Ninja 生成流程。当用户需要编写、修改、排查或理解 `make.lua`、目标定义、`lm:conf`、`deps` / `objdeps`、代码生成、Lua C 模块、Bee 运行时集成,或需要解决当前项目中由 `luamake` 驱动的构建问题时,使用此 skill。即使用户没有明确提到 `luamake`,但上下文明显是在处理本项目的构建脚本、构建目录、目标依赖或 `luamake` 生成的 Ninja 流程,也应使用此 skill。不要把它用于纯通用的 C/C++ 编译知识、与本项目无关的 CMake / xmake / Bazel / Meson 问题,或仅讨论编译器理论而未涉及 `luamake` / `make.lua` 的请求。Stars: 211Updated Claude CodeCodexUnverifiedInstall
cilylo/pagecordRun the local CI sequence for this repo. Use when the user asks to run CI, verify a branch before push, or check code quality with the full local pipeline.Stars: 196Updated Claude CodeCodexUnverifiedInstall
code-reviewlylo/pagecordReview Ruby and Rails code as a principal engineer. Use when the user asks for a code review, PR review, diff review, or wants risks, regressions, security issues, Rails idiom problems, UI state issues, or test gaps identified before merging.Stars: 196Updated Claude CodeCodexUnverifiedInstall
rails-best-practices-corelylo/pagecordApply core Ruby on Rails best practices for architecture, naming, RESTful routing, authorisation, safety, and maintainability. Use by default for Rails coding, refactoring, debugging, feature implementation, migrations, controller/model changes, and code review tasks so baseline standards stay consistent.Stars: 196Updated Claude CodeCodexUnverifiedInstall
ui-reviewlylo/pagecordReview UI changes for state, timing, redirects, async behaviour, and browser-level test gaps. Use when the user asks specifically for a UI review or frontend workflow review.Stars: 196Updated Claude CodeCodexUnverifiedInstall
ab-analyze-backendayoubben18/ab-methodAnalyze and document a project's backend patterns — API design, data access, service structure. Use when the user wants a backend-only architecture analysis.Stars: 193Updated Claude CodeCodexUnverifiedInstall
ab-analyze-frontendayoubben18/ab-methodAnalyze and document a project's frontend patterns — component structure, state management, conventions. Use when the user wants a frontend-only architecture analysis.Stars: 193Updated Claude CodeCodexUnverifiedInstall
ab-analyze-projectayoubben18/ab-methodAnalyze a project's architecture end to end — extract domain language, map the tech stack, document frontend and backend patterns. Use when onboarding a new codebase or refreshing the architecture baseline.Stars: 193Updated Claude CodeCodexUnverifiedInstall
ab-cleanupayoubben18/ab-methodClean up a repo already using AB Method - compact the domain and architecture docs to their budgets, split pattern docs by topic, remove disposable task leftovers, and migrate the structure index to 4.0. Use when docs have grown too large, after upgrading AB Method, or when the user asks to clean up.Stars: 193Updated Claude CodeCodexUnverifiedInstall
ab-create-goalayoubben18/ab-methodProduce a ready-to-run prompt for an autonomous /goal loop. Use when the user wants to hand off one continuous objective with a verifiable stop condition to run autonomously.Stars: 193Updated Claude CodeCodexUnverifiedInstall
ab-create-roadmapayoubben18/ab-methodTurn a larger idea into a dependency-ordered roadmap of tasks — the layer above create-task. Use when the work is several distinct tasks with real ordering between them (schema before API before UI), and you want the whole task graph drawn before implementing. Producer only; ab-start-roadmap executes it.Stars: 193Updated Claude CodeCodexUnverifiedInstall
ab-create-taskayoubben18/ab-methodCreate a holistic task — deepen the code it touches, design new seams, and break it into composed missions. Use when the user wants to start a new feature, fix a bug, or begin implementation work.Stars: 193Updated Claude CodeCodexUnverifiedInstall
ab-create-task-from-handoffayoubben18/ab-methodResume a handoff (a side-topic spun off mid-grill) and turn it into a test-driven task. Use when the user wants to continue grilling on a deferred topic captured under docs/handoffs/.Stars: 193Updated Claude CodeCodexUnverifiedInstall
ab-extend-goalayoubben18/ab-methodExtend an existing goal — broaden or add to its objective, building on top of what the earlier /goal run already implemented. Use when the user wants to expand a goal after a /goal run.Stars: 193Updated Claude CodeCodexUnverifiedInstall
ab-extend-taskayoubben18/ab-methodAppend new missions to an existing task. Use when requirements changed or scope grew on a task already underway.Stars: 193Updated Claude CodeCodexUnverifiedInstall
ab-mastermindayoubben18/ab-methodThe intelligent entry point to the AB Method. Use when the user isn't sure which workflow they need, asks whether to create a goal or a task, or wants to understand how the AB Method works end to end. Routes intent to the right workflow instead of reimplementing it.Stars: 193Updated Claude CodeCodexUnverifiedInstall
ab-resume-taskayoubben18/ab-methodContinue an existing task from its progress tracker. Use when the user wants to resume, continue, or pick up earlier task work.Stars: 193Updated Claude CodeCodexUnverifiedInstall
ab-start-roadmapayoubben18/ab-methodExecute a roadmap autonomously to completion — the layer above start-task. Use when a roadmap's tasks are planned and you want them run in dependency order, with independent tasks optionally in parallel (or `inline`, without mission subagents), ending in one reviewed pull request. Verifies the dependency tree is planned before running; stops if a needed task has no plan. Executor only.Stars: 193Updated Claude CodeCodexUnverifiedInstall
ab-start-taskayoubben18/ab-methodRun an existing task autonomously to a reviewed pull request — each remaining mission in a subagent (or in the conversation with the `inline` argument), a commit after every green mission, then the protect step, reviews, a draft PR and a final review against the seams and coding rules. Use when the user wants to hand off a well-defined task and review a PR instead of missions. Pass `inline` to run the missions without subagents.Stars: 193Updated Claude CodeCodexUnverifiedInstall
ab-update-architectureayoubben18/ab-methodRefresh architecture and domain documentation after impactful changes. Use when code has drifted from the documented architecture.Stars: 193Updated Claude CodeCodexUnverifiedInstall
adopt-or-buildayoubben18/ab-methodBefore building a feature or fix, search for open-source libraries that already solve it and decide per piece whether to adopt one or build it. A library is adopted only when it is actively maintained, not outdated, and compatible with the project's exact stack (versions, runtime, module format, types). Use when scoping a large or already-solved capability, or when the user asks "is there a library for this", "should we build this ourselves", or wants to avoid reinventing something.Stars: 193Updated Claude CodeCodexUnverifiedInstall
change-mapayoubben18/ab-methodDraw a task's blast radius twice. BEFORE implementing, a PLANNED map of the modules the missions expect to add, change or touch; AFTER the reviewers pass, an ACTUAL map derived from the real diff, plus the DRIFT between them. Writes docs/tasks/<task>/change-map.md. Use from create-task / extend-task (planned pass), and after review-implementation + sync-architecture in create-task / resume-task / start-task / start-roadmap (actual pass), or standalone on a task.Stars: 193Updated Claude CodeCodexUnverifiedInstall
codebase-designayoubben18/ab-methodShared vocabulary and principles for designing deep modules — small interfaces, clean seams, testable through the interface — grounded in Ousterhout's A Philosophy of Software Design. Holds the seam doc format, the default seam catalog and the book's red flags. Use when designing or improving a module's interface, deciding where a seam goes, writing a seam doc, hunting deepening opportunities, or when another skill needs the deep-module vocabulary.Stars: 193Updated Claude CodeCodexUnverifiedInstall
critique-planayoubben18/ab-methodPre-implementation critic. Spins up a read-only domain critic that challenges a drafted plan — a task's missions or a roadmap's task graph — against the ubiquitous language, CONTEXT.md, ADRs and the documented seams, flags plans that bend a feature around a design it should reshape, and pushes back ONLY on genuine conflicts. Silent when the plan is sound. Use before implementing (from create-task / create-roadmap) or standalone to stress-test a plan against the project's domain model.Stars: 193Updated Claude CodeCodexUnverifiedInstall
domain-modelayoubben18/ab-methodGrilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.Stars: 193Updated Claude CodeCodexUnverifiedInstall
grill-meayoubben18/ab-methodInterview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".Stars: 193Updated Claude CodeCodexUnverifiedInstall
grill-with-docsayoubben18/ab-methodGrilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Parks the rare question you genuinely can't answer yet as an unresolved question with a placeholder, so the build proceeds instead of stalling. Use when user wants to stress-test a plan against their project's language and documented decisions.Stars: 193Updated Claude CodeCodexUnverifiedInstall
handoffayoubben18/ab-methodCompact the current conversation (or a side-topic that surfaced mid-grill) into a handoff document another agent can pick up. Use when a tangent deserves its own task, or to summarize a session for a fresh agent.Stars: 193Updated Claude CodeCodexUnverifiedInstall
improve-codebase-architectureayoubben18/ab-methodOptional repo-wide review. Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick and hand it to /create-task. Informed by the domain language in CONTEXT.md, the decisions in docs/adr/ and the seams in docs/seams/. Task-time deepening happens in create-task's planning scan instead; use this when the user wants a deliberate repo-wide review, wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.Stars: 193Updated Claude CodeCodexUnverifiedInstall