Coding & Dev Tools

sahilkhan30 Skill

Use when designing extensible architecture components using Adapter, Strategy, or Factory patterns based on explicit variability and coupling requirements.

sahilkhan30 Skill

Use when designing event producers, event consumers, outbox patterns, and duplicate event deduplication.

spardutti Skill

MUST USE when fixing a bug, diagnosing an error, stack trace, exception, crash, failing or flaky test, or any 'why is X not working / returning the wrong value' investigation in any language. Enforces root-cause-before-patching: reproduce, trace the failure backward to its origin, test one hypothesis, then fix once — instead of guarding the symptom. Also covers the 3-attempts-then-question-the-design rule.

spardutti Bundle

MUST USE when creating or editing any code file in any language — deciding how to split files, functions, classes, and modules, or whether to extract a shared helper, base class, or utility from duplicated code. Enforces the Single Responsibility Principle (one reason to change, file/function size limits, separation of concerns) and Avoid-Hasty-Abstractions (AHA / Rule of Three — prefer duplication over the wrong abstraction).

spardutti Bundle

TanStack Query — Cache, Queries, Mutations

spardutti Skill

TanStack Router Best Practices

spardutti Skill

MUST USE when a git merge, rebase, cherry-pick, stash pop, or revert stops with conflicts — 'CONFLICT (content)', 'Automatic merge failed', 'could not apply', unmerged paths, or leftover <<<<<<< markers in a file. Enforces resolve-by-intent: read both sides against the merge base, keep both behaviours where they are compatible, and never pick a side wholesale. Also covers the inverted meaning of ours/theirs during a rebase, conflicts git does not mark (semantic and tree), lockfiles and migrations that are regenerated rather than merged, and finishing the merge.

spardutti Bundle

MUST USE when writing, reviewing, or modifying tests. Enforces Arrange-Act-Assert, assertions that fail when the code breaks (exact values, list ties, side effects, limits), factory-based test data, test isolation, mocking boundaries, and pyramid-balanced coverage; bundle covers mutation testing (Stryker, mutmut) for proving the tests would catch a break.

spardutti Skill

MUST USE when writing or editing TypeScript types, interfaces, generics, type guards, error handling patterns, or tsconfig configuration. Enforces TypeScript 7.x strict-mode best practices and type safety patterns.

caomeiyouren Skill

只读问答场景使用。适用于从代码、配置、技能和文档中查证事实、解释实现、定位逻辑和总结约束，但不直接修改文件。用户提到“这个项目里哪里实现了 X”“目前规范怎么写”“帮我从代码里找答案”时都应触发。

caomeiyouren Skill

任何可见 UI 改动、交互变更、样式修复、响应式适配、暗色模式适配和浏览器侧回归验证都应使用。它负责在真实页面中验证实际渲染效果，而不是只看代码。用户提到 UI validate、screenshot、browser check、responsive、dark mode、视觉回归时都应触发。

caomeiyouren Bundle

审查当前 git 变更、PR、提交范围、技能定义文件、架构调整或安全敏感代码时使用。输出结构化 Review Gate 结论（Pass/Reject）、问题分级（blocker/warning/suggest）、最低验证矩阵、证据链与复查基线。覆盖正确性、安全、架构、SOLID、可删除代码、性能、异常处理与测试风险；默认只输出 review，不直接修改代码。用户提到 review、code review、PR 审查、deep review、review gate、merge ready、blocker、evidence、pass、reject、SOLID、架构审查时都应触发。

caomeiyouren Skill

在动手规划、修改、调试或回答复杂项目问题前使用。用于快速扫描项目结构、依赖、约束文档、关键文件和调用链，输出任务相关上下文，而不是直接改代码。用户提到 analyze context、scan repo、understand project、定位实现、找规范、排查调用链时都应触发。

caomeiyouren Skill

运行并解读 lint、类型检查、测试等质量门时使用。它不只是执行命令，还要根据变更范围选择最小充分检查、分析失败原因，并给出是否允许继续提交或发布的判断。用户提到 lint、typecheck、tests、quality gate、验证改动时都应触发。

caomeiyouren Skill

在用户需求模糊、目标不清、验收标准缺失、范围过大或需要抽离真实意图时使用。它负责把“想做什么”转成可执行的目标、约束、验收标准和优先级。用户提到需求分析、澄清、规划、scope、acceptance criteria、产品目标时都应触发。

caomeiyouren Skill

在进入实现前做技术方案、文件映射、模块边界设计、接口契约和变更影响分析时使用。用户提到 architecture、design plan、file mapping、implementation plan、技术方案、模块拆分、接口设计时都应触发。

caomeiyouren Skill

需要生成 Conventional Commit 提交消息并执行单次提交时使用。适用于 feat、fix、docs、refactor、test、build、ci、chore 等常规提交场景。先检查质量门，再分析 diff，再生成符合 commitlint 预期的消息。

dezvin Bundle

Conduct a deliberate one-question-at-a-time stress test of a plan, idea, or decision until no material user-owned decision remains unresolved. Use only when the user explicitly invokes $grill-me or directly asks to be grilled, interviewed, challenged, or questioned before proceeding. Do not use for ordinary feedback, fact gathering, exhaustive questionnaires, implementation, or decisions that can be handled through inspection, a reversible default, or a practical test.

dezvin Bundle

Use this skill when the user wants to analyze decisions from a discussion, transcript, current Codex context, export, or existing preflight and either stop at a decision review or turn resolved decisions into a handoff-ready design before implementation. Trigger for questions about what was decided, rejected, superseded, conflicting, or still open, and for implementation-ready design or architecture handoffs. Do not use for ordinary summaries, direct implementation or file editing, deployment or CI checks, or deciding unresolved choices for the user.

dezvin Bundle

Use when continued work must advance through bounded iterations because decision-relevant information will emerge only during execution and the full route cannot yet be planned honestly. Trigger when several viable directions remain, the next segment depends on findings from current work, important constraints or inputs will appear during execution, or new evidence may invalidate the current basis. Keep a stable target contour, mark later stages as provisional, choose the nearest segment whose purpose and completion result can be defined now, and update only the affected layer after new evidence. Do not use merely because work is complex, strategic, risky, long-running, or multi-step; for ordinary prioritization with clear criteria; for a one-pass recommendation or reframing; or when the route and done condition are already clear.

dezvin Bundle

Use this skill only when the user explicitly invokes $export-current-thread or directly asks to export or save the current Codex thread, conversation, chat, or session as a local txt file. Create a readable recovery transcript by default and offer a separate full command-and-result export only after the transcript is ready. Do not invoke implicitly for ordinary logging, summaries, handoffs, or unrelated file exports.

epistemedeus Bundle

Inspect Morpho on Base with deterministic, read-only evidence. Use for borrower position and stress analysis, unsigned protection planning, market underwriting, or historical PreLiquidation replay. Never treat the output as transaction authorization, a forward profit forecast, or a substitute for fresh direct-chain verification before financial action.

epistemedeus Skill

Profile a Base or EVM wallet or contract address with deterministic public-chain evidence. Use to distinguish EOA from contract, inspect native and curated token holdings, decode token or NFT metadata, detect EIP-1967 proxies, check activity, resolve a forward-confirmed Basename, or size up an address before another transaction. The output is evidence, not a safety guarantee.

epistemedeus Skill

Generate a paste-ready Schema.org JSON-LD bundle and structured-data gap analysis for a public business website. Use for LocalBusiness or MedicalBusiness identity, services, offer catalogs, FAQ, reviews, geo, hours, missing-schema analysis, or a ranked implementation list for AI-search and rich-result eligibility. Never fabricate ratings, reviews, hours, addresses, or other business facts.

epistemedeus Bundle

Verify or reconcile a claimed canonical Base USDC payment against its successful public transaction receipt. Use for post-settlement x402 or MPP audits, marketplace earnings or spend claims, payment-receipt reconciliation, exact payer-recipient-amount checks, and diagnosing a platform counter that may not match on-chain settlement.

epistemedeus Skill

Inspect a mined Base or Ethereum transaction through a normalized public receipt. Use for success or revert status, block identity and time, gas use, effective gas price, total transaction fee, decoded ERC-20 Transfer events, canonical USDC transfer evidence, or distinguishing a missing receipt from an unavailable RPC. This is read-only chain evidence, not settlement-claim verification or transaction execution.

epistemedeus Bundle

Compare x402 and MPP payment challenges for one exact public HTTPS GET URL before buyer authorization. Use to normalize live payment terms, verify URL and realm binding, detect expiry or cross-protocol economic drift, and decide whether an offer is parseable or needs review. The target inspection uses no credential, signs nothing, sends no payment, follows no redirects, and reads no response body.

fiveonecode Bundle

Build and run iOS/macOS apps using xcodebuild and xcrun simctl directly. Use when building Xcode projects, running iOS simulators, managing devices, compiling Swift code, running UI tests, or automating iOS app interactions with a native Xcode/macOS CLI baseline.

fiveonecode Bundle

Use for repositories that already use or explicitly evaluate XcodeGen: maintain project.yml/project.yaml as source of truth, diagnose generated projects, configure resources and test hosts, manage SwiftPM state, and verify binary packaging without replacing general Xcode build guidance.

fiveonecode Bundle

Writes, reviews, and improves Swift Testing code using modern APIs and best practices. Use when reading, writing, or reviewing projects that use Swift Testing, including @Test, #expect, #require, async tests, XCTest migration, traits, confirmations, exit tests, and Swift 6.2+ testing features.

fiveonecode Bundle

Create, update, review, and improve technical specification documents so they are complete, testable, and implementation-ready. Use when defining new features/systems/APIs, updating existing specs, restructuring documents, auditing missing requirements, or converting vague plans into concrete, verifiable requirements and acceptance criteria.

fulcradynamics Skill

Load the user's cross-platform preferences at session start and capture new ones the moment they're expressed. Trigger when the user says 'remember that I…', 'from now on…', 'I always/never want…', corrects a preference you applied, or confirms a pattern you noticed — and at the start of any session where user preferences would change your behavior.

fulcradynamics Bundle

Autonomously orchestrate the ingestion of 3rd-party data exports (e.g., Spotify, Netflix) from the Fulcra File Store into properly mapped Fulcra Annotations.

fulcradynamics Skill

Deprecated — renamed to fulcra-get-started. Use the fulcra-get-started skill instead.

fulcradynamics Skill

A plain, no-nonsense introduction to the Fulcra CLI, covering core primitives (data types and versioned file uploads).

fulcradynamics Bundle

Enable agents to collaborate using shared memory, workspace inboxes, and user artifacts via Fulcra's versioned file storage.