Productivity

lennney Skill

测试覆盖 / Test coverage. Adds tests for core functionality. Use when the user wants to add test coverage to their project.

luc4n3x Skill

Safe Git and GitHub delivery workflow for any repository. Use when the user asks to branch, commit, push, prepare/open a pull request, update an existing PR, or otherwise publish code changes. Preserves unrelated work, verifies the exact diff, keeps commits intentional, and never merges/releases/force-pushes unless explicitly authorized.

luc4n3x Skill

Routes and governs image-centric work across generation, editing, inspection, comparison, annotation, screenshots, branding, raster assets, vector assets, diagrams, infographics, mockups, and export validation. Use whenever an image is an input, output, reference, acceptance artifact, or major source of truth. Chooses the correct host-supported visual workflow before generation or editing begins.

luc4n3x Skill

Specialist reliability workflow for AndroidX Media3 playback, MediaSession/MediaLibrarySession, MediaLibraryService, Android Auto browsing, queue/timeline identity, caching, preload/recovery, audio/video track selection, and audio-processing pipelines. Use when Media3 behavior, APIs, deprecations, playback lifecycle, controller contracts, or automotive media browsing are material.

luc4n3x Bundle

Retrieves, classifies, validates, and optionally persists compact durable knowledge so future tasks can reuse verified experience without treating memory as current truth. Use when prior project decisions, recurring failures, user-authorized workflow preferences, or general engineering lessons could materially improve a task. Separates IGNORE/SESSION/PROJECT/GENERAL memory, revalidates load-bearing memories against current evidence, prevents sensitive-data and chain-of-thought persistence, and prefers small retrieval capsules over context dumps.

luc4n3x Skill

Adaptive deliberation layer for difficult engineering and design work. Use when a task is ambiguous, high-risk, multi-step, architecture-heavy, debugging-heavy, version-sensitive, cross-module, or otherwise likely to reward slower reasoning. Forces explicit problem framing, competing hypotheses/approaches, disconfirmation, independent challenge, evidence-based adjudication, uncertainty tracking, and a final falsifiable proof without exposing private chain-of-thought or adding ceremony to trivial work.

luc4n3x Skill

Safe dependency and toolchain upgrade workflow. Use when adding, replacing, or upgrading libraries, language runtimes, plugins, build tools, frameworks, lockfiles, or transitive dependency constraints. Minimizes unrelated churn and verifies version-specific APIs.

luc4n3x Skill

Converts verified task outcomes into compact reusable experience cards. Use after meaningful bug fixes, failed hypotheses, performance investigations, migrations, design corrections, or repeated workflows when the result contains a lesson worth reusing. Captures trigger, discriminator, intervention, failed alternatives, evidence, transfer conditions, and counterexamples; separates project lessons from general engineering knowledge; and prevents one successful anecdote from becoming an overbroad rule.

luc4n3x Skill

Localization and i18n quality workflow for multi-locale applications. Use when adding or changing user-facing strings, locale resources, plurals, formatting, RTL behavior, or when a UI redesign must remain complete and natural across all languages supported by the project.

luc4n3x Skill

Defines a compact preservation contract before risky changes to working systems. Use for cache, playback, persistence, sync, migrations, concurrency, networking, UI state machines, or any task where a narrow improvement could accidentally break adjacent behavior that currently works.

lukk17 Bundle

Git practice for a team: branching strategy, conventional commit messages, merge versus rebase, branch naming and cleanup, pull request content, and conflict prevention. Use when you say "what should I name this branch", "write the commit message for this", "merge or rebase here", "I have a conflict in this file", or "set up our git workflow". Not for issues, pull requests and releases on the hosting platform, use `github-ops`.

lukk17 Bundle

Test-driven development discipline covering the red-green-refactor loop with an enforced RED gate, the test pyramid, mocking boundaries, test naming and structure, and a CI coverage gate of around 90 percent line coverage of real logic. Use when you say "write this feature test first", "add tests for this bug fix", "our coverage gate is failing", "what should I mock here", or "refactor this without breaking behaviour". Not for browser journeys and the flaky-test policy, use `e2e-testing`.

zeroz-lab Skill

系统化根因调试——先建反馈循环再假设。当遇到 bug、测试失败、意外行为，或提到"调试""debug""为什么不工作""crash"

zeroz-lab Skill

按计划增量生成软件或内容产物。当 plan 已批准需要开始实现，或提到"实现""编码""开始做"

zeroz-lab Bundle

从模糊想法变成明确的 spec。当有一个模糊的想法需要结构化收敛，或提到"提炼""收敛""需求""spec"

zeroz-lab Bundle

证据驱动的创作设计总控。当需要定稿交互、视觉、排版设计，或提到"设计""最佳实践""证据""design"

zeroz-lab Skill

发布后文档同步。当代码已合并需要同步更新项目文档，或提到"文档同步""CHANGELOG""README 更新"

zeroz-lab Bundle

按产物类型审查。当软件、文档、文章、PPT 或视觉稿完成后需要质量把关，或提到"审查""review""质量检查"

zeroz-lab Skill

跨会话学习记忆。当发现项目模式、踩坑经验、偏好需要持久化，或提到"学习""记忆""记住""下次注意"

zeroz-lab Skill

保存工作上下文。当需要保存当前工作状态供后续 session 恢复，或提到"保存""save""checkpoint""挂起"

zeroz-lab Bundle

Unified runtime 激活门——只在用户显式进入 Unified 工作流、调用阶段命令或提到"Unified 启动/路由/初始化"时使用；不用于普通 repo 问答或未提 Unified 的直接任务

zeroz-lab Skill

功能完整性审查。当需要验证代码是否实现了 spec 的所有需求，或提到"spec compliance""功能完整性""需求覆盖"

zeroz-lab Skill

接收审查反馈。当收到代码审查反馈需要评估和实施，或提到"审查反馈""PR comment""修改意见"

zeroz-lab Skill

恢复保存的工作上下文。当新 session 需要继续之前的工作，或提到"恢复""restore""继续上次"

arcasilesgroup Skill

Observes session corrections, recoveries, and workflow patterns silently, then consolidates them into project-local observations on demand. Trigger for 'start observing', 'learn from this session', 'consolidate observations', 'review what was learned', 'observe this session'. Listening mode is passive; review mode extracts and writes. Not for cross-project learning; use /ai-learn instead. Not for skill rewrites; use /ai-skill-improve instead.

arcasilesgroup Skill

Measures AI system reliability over time by defining pass/fail criteria before implementation, running capability checks, and tracking regression via pass@k metrics. Trigger for 'how reliable is this', 'did my changes break anything', 'measure AI performance', 'define success criteria', 'eval this feature', 'check skill regression'. Not for code correctness; use /ai-test instead. Not for quality gates; use /ai-verify instead — evals measure AI task completion consistency.

jasperpwang Bundle

飞书画板：查询和编辑飞书云文档中的画板。支持导出画板为预览图片、导出原始节点结构、使用多种格式更新画板内容。 当用户需要查看画板内容、导出画板图片、编辑画板时使用此 skill。不负责：飞书云文档正文编辑、文档层级、图片/表格布局保护，这些统一交给 feishu-doc-workflow。

googlecloudplatform Skill

Focuses on on-demand recipe and detailed instructions for baking a perfect banana bread, including ingredient ratios, step-by-step baking workflow, and kitchen tools.

ocean326 Bundle

Use when the user wants to shape an ambiguous feature, product idea, workflow, or UX direction before implementation, especially when requirements, trade-offs, or success criteria are still unclear. Do not use for straightforward bug fixes, direct implementation requests with a clear spec, small scoped edits, routine refactors, or config-only changes.

ocean326 Bundle

Orchestrates BMAD workflows for structured AI-driven development. Use when initializing BMAD in projects, checking workflow status, or routing between 4 phases (Analysis, Planning, Solutioning, Implementation). Manages project configs, tracks progress through project levels 0-4, and coordinates with specialized workflows. Trigger on /workflow-init, /workflow-status, or when users need BMAD setup.

ocean326 Bundle

Attach a PersonalBrain repository to the current task using a minimal, upgrade-friendly context rooted at the PersonalBrain path. Use when Codex should treat a PersonalBrain vault as shared durable memory for routing, retrieval, external-project awareness, or thin writeback, especially for external repo work, cross-machine lookup, or query tasks. Prefer an explicit root when provided, but if the current workspace or one of its ancestors already contains the stable anchors AGENTS.md and 40_governance/catalog.jsonl, attach automatically instead of asking for the path. In this installation, when running outside PersonalBrain and no local match exists, fall back to <PERSONALBRAIN_ROOT> after verifying the same anchors. Avoid hardcoding internal page paths beyond those stable anchors.

ocean326 Bundle

Coordinate recoverable remote SSH compute from any local project by using the central Conductor runtime at <PERSONALBRAIN_ROOT>/.local/conductor, selecting a verified SSH route for either a workstation or a shared compute server, dispatching direct remote commands or scripts, and closing the job with local review. Use when Codex should run tests, builds, data processing, or other compute remotely over SSH instead of delegating to a second remote AI runtime, especially when the work may outlive the current thread and needs receipts, logs, and recoverable closeout.

ocean326 Bundle

Asynchronously close the loop on skills used in the current thread by routing to PersonalBrain's canonical `skill_skill_usage_close_loop` workflow, spawning one bounded background subagent, and appending per-skill evidence rows for later aggregate analysis. Use when a user explicitly asks to record, review, or retrospectively evaluate the performance of one or more skills used in the conversation without blocking the main task.

ocean326 Skill

Thin governor for the Transfer_Recovery mainline automation loop. Use when the task is recurring experiment control, state transition, ledger/docs/memory closeout, or handoff recovery. Do not use for open-ended method ideation or historical batch review.

sir-chawakorn Bundle

Systematic debugging workflow to find and fix bugs efficiently. Use this skill when troubleshooting errors, investigating issues, or when code doesn't work as expected.

sir-chawakorn Bundle

Git workflows including branching, merging, PR review, and conflict resolution. Use when managing version control, reviewing changes, or fixing merge conflicts.