Coding & Dev Tools

materialofair Skill

Generate and maintain BDD scenarios and step definitions using Gherkin plus playwright-bdd with a one-scenario-at-a-time TDD loop.

materialofair Bundle

De-AI Writing Skill

materialofair Skill

Analyze coverage, prioritize untested risk hotspots, generate missing tests, and verify threshold improvements.

materialofair Bundle

Diagnose why a OpenCode skill is under-triggering, over-triggering, undiscoverable, or misconfigured.

materialofair Bundle

Playwright-based E2E driving for Electron applications using launch mode or attach mode with robust window selection and runtime inspection.

storybookjs Skill

Creates a pull request following Storybook conventions. Use when creating PRs, opening pull requests, or submitting changes for review.

storybookjs Skill

Use this skill when Storybook exists but needs an upgrade.

yokingma Bundle

当需要用 lark-cli 操作飞书多维表格（Base）时调用：搜索 Base、建表、字段管理、记录读写、记录分享链接、视图配置、历史查询，以及角色/表单/仪表盘管理/工作流；也适用于把旧的 +table / +field / +record 写法改成当前命令写法。涉及字段设计、公式字段、查找引用、跨表计算、行级派生指标、数据分析需求时也必须使用本 skill。

yokingma Bundle

飞书知识库：管理知识空间、空间成员和文档节点。创建和查询知识空间、查看和管理空间成员、管理节点层级结构、在知识库中组织文档和快捷方式。当用户需要在知识库中查找或创建文档、浏览知识空间结构、查看或管理空间成员、移动或复制节点时使用。

yokingma Bundle

飞书电子表格：创建和操作电子表格。支持创建表格、创建/复制/删除/更新工作表、读写单元格、追加行数据、查找内容、导出文件。当用户需要创建电子表格、管理工作表、批量读写数据、在已知表格中查找内容、导出或下载表格时使用。若用户是想按名称或关键词搜索云空间里的表格文件，请改用 lark-doc 的 docs +search 先定位资源。

yokingma Bundle

Use when creating, editing, auditing, or restructuring a skill or SKILL.md, including scaffolding new skills, cleaning stale files, validating frontmatter, and packaging skill bundles.

mrilikecoding Skill

Voice development and style coaching for creative writing. Analyzes the user's natural writing patterns, builds a voice profile, coaches on register transitions, and flags unintentional voice shifts. The voice is the user's — this skill helps them find and refine it.

mrilikecoding Skill

Draft a point-by-point response to real peer reviewer comments received from a journal. Use when you have received peer review feedback and need to prepare a revision and response letter. Handles disagreement diplomatically.

mrilikecoding Skill

Orchestrates a full simulated peer review of an academic paper using an ensemble of independent reviewer subagents. Use when asked to peer review a paper, get feedback on a manuscript, or prepare a paper for submission. Produces structured reviewer reports, a response document, and guides revision.

mrilikecoding Skill

Creative writing project architecture — concept mapping, thematic structure, outlining, and strand interweaving. Helps the user see the shape of their project. Use when structuring a new project, reorganizing an existing one, or mapping how narrative, art-as-code, and theory interweave.

mrilikecoding Skill

Analyze a paper and recommend target journals for submission. Use when asked where to submit a paper, which journal is best for a manuscript, or to compare journal options. Researches fit, impact, timelines, and audience.

fabioc-aloha Skill

Adversarial code review with three parallel perspectives — Advocate, Skeptic, Architect — that create productive tension. Use for high-stakes PRs, architectural changes, or when single-pass review would miss issues. Surfaces findings through disagreement, not consensus.

fabioc-aloha Skill

Detect, resolve, and manage the Alex_ACT_Memory shared memory bus. Fires on bootstrap, session start (announcements), and feedback writes.

fabioc-aloha Bundle

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Four-phase root-cause-first method (investigate → pattern-analyze → hypothesize → implement) that beats guess-and-check thrashing.

akhileshu Bundle

Implement an existing slice design document safely through reconciliation, tracer code, incremental checkpoints, tests, and local verification. Use when implementing docs/slices/*.md or another bounded feature slice in a Go, full-stack web, or similar codebase.

akhileshu Bundle

Go systems planning guidance for turning milestone rows into implementation-ready slices with clear control flow, interfaces, pseudocode, tests, and repository boundaries. Use when designing Go features, parsers, pipelines, storage code, concurrency, or network-bound systems before implementation.

akhileshu Bundle

Safely evolve architecture between implementation slices using tracer code, stable boundary contracts, invariant-based tests, and incremental refactoring. Use when a later slice changes storage, transport, state, rendering, concurrency, or other internal implementation choices.

akhileshu Bundle

Full-stack planning guidance for turning milestone rows into implementation-ready vertical slices from database to UI, with concrete TypeScript contracts, state flows, tests, and repository boundaries. Use when designing a web feature blueprint, studying a product row, or mapping client and server responsibilities before implementation.

akhileshu Bundle

Design-first engineering guidance for safe data-flow transformations, explicit invariants, and clean domain boundaries. Use when mapping inputs to outputs, structuring domain logic, or simplifying boundary-heavy code before implementation.

airborne12 Bundle

监听分配给自己的 Jira（内部 Jira Server）并对新事件做单轮自动处置：校验 aibot 等 AI 值班机器人的分析、追出修复 PR 在 apache/doris 与 internal-core 各分支的落地/pick 情况、判断当前 issue 版本对应的基线分支与是否需要 pick，受控回写评论与状态并推送飞书简报。当用户要求盯 Jira、监听 Jira、值班处理新分配的 Jira、校验 AI 分析结论、查某个修复在哪些分支/要不要 pick、或按事件驱动跟进 CIR/DORIS/CORE issue 时使用。

airborne12 Skill

为 Apache Doris 创建 pull request，遵循仓库当前的 PR 模板与标题规范。当用户说"提PR""提交PR""创建PR""create PR""push and create PR"，或想把分支推上去开 PR 时使用。所有仓库标识、远端名、默认分支、模板内容都从当前仓库现场解析，不写死。

airborne12 Bundle

Interpret Apache Doris query runtime profiles, especially profile bottleneck triage, misleading wait counters, per-operator metric priority, scan, join-order/runtime-filter analysis, and evidence-bounded performance explanations. Use when given a Doris profile, query id, profile URL/text, or a request to explain Doris query performance.

amaledtuning Bundle

Opt-in router for design quality passes across UI, websites, presentations, PDFs, documents, images, posters, banners, infographics, decks, ads, and product materials. Use when the user explicitly invokes `$design-pass`, asks for a design pass, or wants a visual/UX/readability/attention/trust/decision-quality review without needing to remember the individual design skill names.

amaledtuning Bundle

Reduce cognitive load across interfaces, presentations, PDFs, documents, diagrams, workflows, forms, dashboards, onboarding materials, and visual explanations. Use when Codex needs to simplify complexity, chunk information, reduce memory burden, replace recall with recognition, clarify steps, manage progressive disclosure, or make a process easier to understand and complete.

amaledtuning Bundle

Build ethical motivation, trust, credibility, emotional resonance, progress cues, social proof, and engagement across websites, apps, forms, presentations, pitch decks, PDFs, posters, ads, profile pages, checkout flows, and product visuals. Use when Codex needs to make an experience feel credible, human, motivating, reassuring, memorable, or worth continuing without using dark patterns.

amaledtuning Bundle

Shape visual attention across websites, apps, presentations, PDFs, documents, posters, banners, images, and infographics. Use when Codex needs to make the most important element noticed first, strengthen visual hierarchy, salience, grouping, contrast, affordance, scan path, or ensure color is not the only carrier of meaning in a visual or interface.

amaledtuning Bundle

Simplify decisions, comparisons, pricing, recommendation flows, defaults, framing, choice architecture, error prevention, validation, undo, confirmation, and recovery across interfaces, presentations, PDFs, documents, tables, dashboards, forms, and decision-support visuals. Use when Codex needs to reduce choice overload, make tradeoffs clearer, prevent predictable mistakes, or help users recover safely.

amaledtuning Skill

Practical lane-execution playbook for Codex workers running independent implementation/validation tracks with strict non-overlapping ownership.

amaledtuning Skill

Use when orchestrating delegated work in an active chat to ensure rule updates apply from the next orchestration step, delegated writes are integrated and verified in the same thread, and user-facing continuity updates remain explicit after each worker result.

fal3 Bundle

Plan, implement, debug, and verify migrations from callback-, delegate-, Dispatch-, or permissive-concurrency Swift code to Swift 6 strict concurrency, including target-specific build settings, approachable concurrency, default actor isolation, @concurrent work, actors, Sendable boundaries, cancellation, and structured tasks. Use for Swift 6 compiler diagnostics, concurrency adoption plans, legacy async bridges, or migration-focused tests in Apple-platform apps and Swift packages. Do not use for general Swift syntax, performance work without a concurrency finding, framework-specific threading rules without a Swift migration, or requests that merely contain an already-correct async function.

fal3 Bundle

Use when designing new or intentionally modernized SwiftUI app architecture targeting Swift 6 with strict concurrency and iOS/iPadOS 18 or macOS 15, especially Observation ownership, dependency boundaries, SwiftData, structured concurrency, navigation state, and test seams. Do not use for arbitrary Swift questions, older deployment targets, UIKit-only work, or migrations where the existing Core Data, Combine, Dispatch, or XCTest design is not being reconsidered.