Productivity

jazeer888 Skill

TODO — one sentence describing when Claude should trigger this skill.

jcmais Skill

Prepare node-libcurl for a release — merge develop into master, decide the version bump, and convert the [Unreleased] CHANGELOG section into a dated version section. Use whenever Jonathan asks to "prep a release", "prepare a release", "do release prep", "merge develop into master", "cut a release", "ship a new version", or anything similar in this project. Also use when he says "we're shipping vX.Y.Z" or asks for help deciding what version number to use for the next release. Do NOT bump the package.json version and do NOT create tags — the release workflow handles those.

jeffercb1 Bundle

Convierte transcripciones de reuniones en JSON estructurado para automatización de workflows. Extrae actores, triggers, datos y pasos del flujo desde lenguaje natural.

jetbrains Bundle

Guides building, debugging, extending, and managing JetBrains YouTrack apps and workflows. Used when scaffolding, modifying, validating, uploading, downloading, enabling, disabling, or inspecting a YouTrack app, workflow rule, app endpoint, or manifest. Also use when creating GitHub release automation or publishing a YouTrack app to JetBrains Marketplace.

jfernandez Bundle

Cut a new versioned release of bpftop — pick the version, open a version-bump PR, sign-tag the merge commit on main, and draft GitHub release notes in the project's established format. Use whenever the user says "cut a release", "release X.Y.Z", "ship X.Y.Z", "time to release", "tag a new version", "bump to X.Y.Z", "let's do a release", or otherwise initiates a release. Trigger even when the user only asks for one step ("what version should we bump to?", "make the release PR", "tag it") — load this skill so the broader workflow context is available, and only do the step the user asked for.

jguer Skill

Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.

horiastanxd Skill

Searches the Awesome Claude Skills list to suggest skills, collections, authoring tools, or docs matching the user's need. Use when the user asks where to find a skill for a specific task, which collection is worth installing, or what the official Anthropic resources are.

huiyonghkw Bundle

当用户要求检查、体检、回归、验收、解释或诊断会勇禾口王内容工作流 Harness，或维护、移植、打包、开源这个 Harness 检查器 Skill 时使用。统一调用仓库现有的 verify.sh、harness-check、Runtime Governance、Hook、Task Contract、Safety Gate、Episode、可观测性和失败台账检查，并分别报告本地、暂存区、CI 自动化结果与真实宿主烟测边界。

humansignal Bundle

Draft a Label Studio XML labeling configuration from a plain-English description of the annotation task, validate it locally and against the user's running Label Studio instance, then — only after explicit approval — push it to that instance as a new project or as an update to an existing project. Use when the user asks to "build a labeling config / interface / template for X", "set up a Label Studio project for Y", "make me an XML config for Z", or shares a labeling brief and wants the result deployed.

hummer98 Skill

This skill MUST be used for shell state mutations — cd, export, unset, git checkout, git switch. Use `ctxd chdir <path>`, `ctxd env-set KEY=val`, `ctxd git-switch <branch>` instead of raw Bash. The `update-config` skill is for Claude Code settings.json/hooks/permissions only — NOT for shell environment variables. Never run raw `cd`, `export`, `unset`, `git checkout`, or `git switch` in Bash. Also never substitute `cd` with `ls <path>`, or `git switch` with `git status` — even when the user says "教えて" / "確認して" / "see if", the requested mutation is mandatory and the JSON envelope is the deliverable. Each ctxd command emits one structured JSON envelope (cwd, env diff, branch / dirty / ahead / behind) in a single observation. Trigger whenever the user asks to change directory, switch git branches, or set/unset environment variables for the running task. Examples - "cd to /tmp", "switch to main branch", "set LOG_LEVEL=debug as env var", "環境変数にセット", "ブランチに切り替え", "ディレクトリに移って".

husnainpk Bundle

This skill should be used when finding, tracing, or understanding code in a repository with SymDex available. Trigger it for requests like "where is this defined?", "who calls this?", "what route handles this path?", "show me the file outline", "search this codebase by intent", or any task that would otherwise rely on broad Read/Grep/Glob exploration.

iamzifei Bundle

Personal GTD (Getting Things Done) coach that helps users achieve their annual goals. Use when users mention goals, plans, daily tasks, productivity, time management, task tracking, reviews, or need help breaking down objectives into actionable steps. Automatically remembers user's goals and progress across conversations. Supports multiple languages. 新手引导：输入 `/gtd 新手`、「这个怎么用」「第一次用」「能干嘛」时，走 SKILL.md 的〈新手上路〉，不要直接开始干活。

ibrahim-3d Bundle

Generate, edit, or create any image — photos, illustrations, icons, thumbnails, hero images, banners, placeholder visuals, website graphics, social media assets, product shots, logos, diagrams, or any visual content. Use this skill whenever the task involves creating an image, populating a UI with visuals, generating placeholder or mockup images, editing or retouching a photo, applying style transfer, composing multiple images, or producing any graphic asset. Triggers on requests like "generate an image", "create a visual", "make a placeholder", "add a hero image", "design a thumbnail", "edit this photo", "create website graphics", "populate with images", or any task requiring image creation or manipulation.

grxkun Bundle

Prevent Claude from touching files or systems beyond what the task actually requires. Use this skill when fixing bugs, making changes, refactoring, or editing anything — especially when you want Claude to stay focused on the specific problem. Triggers on: fix this, change this, update, refactor, edit, clean up, adjust, or any request to modify existing code or files.

guwidoe Bundle

Lobster workflow runtime for deterministic pipelines with approval gates. Use when: (1) Running multi-step automations that need human approval before side effects, (2) Monitoring PRs/issues for changes, (3) Processing data through typed JSON pipelines, (4) Email triage or batch operations, (5) Any workflow that should halt and ask before acting. Lobster saves tokens by running deterministic pipelines instead of re-planning each step.

gyozanisonline Bundle

Build a reusable writing-voice profile from a person's real writing, then draft new text in that voice on demand. Use this whenever someone wants Claude to "write like me", "sound like me", "capture my voice/tone/style", "clone my writing", "build a voice profile", "make a brand voice", "create a persona voice", or stop getting generic AI-sounding drafts. Trigger on ANY of: "write this in my voice", "make it sound like me", "this doesn't sound like me", "set up my writing style", "give my assistant/brand a voice", or a request to draft an email / post / message that should sound like a specific real person or persona. Two modes: BUILD a profile from real samples, and DRAFT using an existing profile. Always prefer this skill over winging a "sound like you" request, because voice captured from real samples beats voice guessed from a vibe.

halfwhey Bundle

Use this skill whenever you need to interact with tmux — sending commands to panes, reading their output, watching a TUI app like vim, htop, or lazygit, or managing sessions and windows. Reach for it any time the user says "run this in the terminal", "check that pane", "send a command to the shell", or when you spawn a background task that you'll need to monitor. Always use this skill when tmux is involved — it provides reliable pane identification, delta output reading, and safe key-sending that prevent common mistakes.

hamen Skill

The standard gated workflow for shipping ANY repository change: plan → plan-review → implement → cross-review → merge → verify, with two human approval gates. Use whenever the user asks to implement, build, add, fix, or ship a change to a repo ("new feature", "let's implement X", "ship X", "fix this bug and open a PR"). Do NOT use for read-only work: diagnosis, code review, or answering questions.

hamsterider-m Bundle

Issue-driven development workflow. Manage GitHub Issues as SSOT for all dev tasks — create, worktree, code review, PR, and status tracking.

hanzoskill Bundle

Dispatch coding tasks to OpenCode or Claude Code on Perry workspaces. Use for development work, PR reviews, or any coding task requiring an isolated environment.

hao-ai-lab Skill

Workflow for finding and fixing instruction-throughput bottlenecks in warp-specialized CuTeDSL kernels (FA4-style). Use when a kernel underperforms its roofline and you need to decide between reordering, eliminating, or re-pipelining work.

haoxilin Bundle

CUMCM（全国大学生数学建模竞赛）真题全流程实战手册。用于完整打一场数模竞赛（环境准备→读题自查→建模出图→LaTeX论文→交叉审阅→填表→AI自查表终审→清理打包），内含题意理解红线、数值严谨性守则、去AIGC特征清单、写作规范、LaTeX编号与图表规范、2026 AI合规与终审核查框架。触发于用户开始完整做真题、备赛训练、即将正式参赛，或要求按AI自查表对成品论文终审整改。**启动关键词**：国赛、数学建模竞赛、真题全流程、按竞赛标准走完流程、备赛、环境检查/检查环境/准备环境、按自查表审查——命中任一即启动，启用后第一步自动执行环境检查。

harivansh-afk Bundle

Non-interactive X11 desktop control for AI agents. Use when the task involves controlling a Linux desktop - clicking, typing, reading windows, waiting for UI state, or taking screenshots inside a sandbox or VM.

edward-sh88 Skill

Trigger the moment the user explicitly asks to drop politeness and get the raw truth about something they made or are planning — an app idea, business plan, pitch deck, portfolio, YouTube/content concept, essay, or code. Key phrases: "brutally/radically/1000%/tausendprozentige honest", "zero sugar", "no sugar-coating", "don't sugarcoat it", "sag's ungeschönt", "keine Watte", "Schönreden bringt mir nichts", "mach mich fertig", "reiß das auseinander", "roast this", "tear this apart", "does this suck", "don't spare my feelings", "what would you honestly say if you weren't trying to be nice/polite". Also trigger when the user says AI, editors, or reviewers keep praising their work while real outcomes (rejections, silence, no traction) say otherwise. Still trigger when the request is wrapped in project detail, numbers, or backstory — that is context for the roast, not plain feedback. Skip only bare "give me feedback/proofread this" asks with zero honesty framing, and skip whether a deadline/task will be met.

edwinhu Skill

This skill should be used when the user asks to "check email", "read inbox", "send email", "reply to email", "search emails", "archive email", "snooze email", "star email", "add label", "forward email", "download attachment", "switch email account", "use snippet", "search contacts", "ask ai about email", "find email about", "what did someone say about", or needs to interact with Superhuman email client. For calendar, events, and scheduling use the morgen skill instead.

edwinjj1 Bundle

Search-first 3D printing workflow — finds real specs before modeling, generates manifold-safe models for Bambu Studio / PrusaSlicer / Cura / Fusion 360

egalano Bundle

Interactive tutorial that walks the user through designing, writing, testing, and distributing their own Skill for Claude. Use when the user says "teach me how to build a skill", "help me make a skill", "walk me through skill creation", "I want to learn skills", "/build-a-skill", or asks about SKILL.md structure, YAML frontmatter for skills, progressive disclosure, skill distribution, or how to package a workflow as a reusable skill. Covers fundamentals, planning, technical requirements, instruction writing, testing, distribution, and common patterns.

elvisun Bundle

Design a loss function and harness for a long-running /goal optimization run (loss-function development, LFD). Use when the user wants to set up an autonomous optimization loop, distill a product from public artifacts, turn a spec into an optimization target, or asks to design a /goal. Observes the existing environment, interrogates the task, ingests or generates the spec, builds a blinded eval, generates and verifies the harness, red-teams the target for cheats, and emits goal.md ready to launch. Re-invoke in patch mode when a running loop cheated and the loss function needs patching.

eran-tookii Skill

Manage your AI team. /crew = roster, /crew init = generate shared project reference, /crew add [name] "[domain]" = new member, /crew 1-on-1 [name] = check-in, /crew [name] [task] = assign task, /crew done [name] = close session, /crew remove [name] = remove member.

erickhchan Skill

Use when the user mentions Otter, Otter.ai, or wants to find, search, download, export, or manage meeting notes, transcripts, recordings, or audio from calls, standups, syncs, or interviews.

ericsun787 Bundle

STM32通用程序开发完整流程，基于STM32CubeCLT命令行工具链。涵盖工具链安装、 HAL库配置、项目构建、固件编译和ST-Link烧录。适用于STM32F1/F4/H7等系列， 解决编译错误、链接错误、烧录失败等常见问题。

jordanhubbard Skill

Structured development workflows for AI-assisted coding. Use when starting new features, fixing bugs, following TDD, refactoring code, or any development task that benefits from planning and structure. Activate it when users mention to build, enhance or fix code.

jovd83 Bundle

Turn approved product requirements, acceptance criteria, architecture plans, and repository context into executable implementation task plans. Use when a project needs test-first, dependency-aware tasks with traceability, file targets, validation commands, parallel work markers, open questions, and downstream skill-routing before coding starts.

jovd83 Bundle

High-performance routing engine for AI AgentSkills. Classifies user intent, scans for specialized skills, and generates optimal dispatch decisions (HANDOFF, SEQUENCE, or NO_MATCH). Use this to manage complexity in large skill environments and ensure the best-equipped skill handles every task.

joye61 Skill

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).

jpoindexter Bundle

Use when the user invokes /use followed by a task, asks "which skills apply to this", or hands over any non-trivial task where installed skills might exist but haven't been loaded — especially when about to work from memory in a domain the skill inventory covers.