Loading...
Loading...
Found 10,863 Skills
Produces human-sounding text that avoids detectable AI writing patterns. Activates on any writing task — tweets, emails, articles, bios, captions, reports, copy, messages, LinkedIn posts, cover letters, README files, or any content where the output must not read as AI-generated. Enforces banned vocabulary, structural variety, punctuation discipline, accuracy rules, and voice calibration. Use when the user says "write," "draft," "rewrite," "make this sound human," "anti-slop," "not AI," or any variation of wanting authentic-sounding output.
Escribe o cambia el playbook de objeciones y el tono de cierre, sin tocar ninguna otra parte del kit.
Use when the user asks to "pick which social channels to run", "should we be on X platform or 小红书", or "plan our organic social channel portfolio"; produces an audience/objective-first portfolio with capability/access matrix, cadence-budget reality check, declared ECHO operating profile, boundary routing, and proposed-state registry events. Not for recording canonical channel facts — use channel-registry. 社媒渠道选择/渠道组合规划/平台能力矩阵/自然社媒
Structures and organizes Storybook files for scalability using battle-tested patterns from Cassondra Roberts' "A Storybook format that scales with you". Covers story definitions, template composition, controls/args, visual regression with Chromatic, component documentation, and CSF conventions. Activates on any Storybook question — file structure, controls, args, or component documentation.
Build, review, debug, migrate, or plan TanStack Form v1 React forms with current docs. Use for @tanstack/react-form, @tanstack/form-core, useForm, form.Field, createFormHook, createFormHookContexts, withForm, withFieldGroup, formOptions, form.Subscribe, useSelector, useStore, validators, Standard Schema validation, Zod, Valibot, ArkType, Effect Schema, async validation, dynamic validation, array fields, FormGroup, linked fields, listeners, SSR, TanStack Start, Next.js, Remix, devtools, UI libraries, accessibility, and production form composition.
Generate a git commit message compliant with Conventional Commits 1.0.0 (and the de facto @commitlint/config-conventional rules) from currently staged changes. Outputs Korean by default, or another language if the user explicitly requests it. Trigger when the user asks for a commit message — e.g. "/conventional-commits", "write a commit message", or any equivalent. Scope is limited to producing the message text; executing `git commit` is outside this skill's responsibility.
Use this skill when designing to prevent errors of intention — wrong actions taken because the user's model of the situation was wrong. Trigger when designing for ambiguous information, novel situations, complex decisions, or contexts where users may proceed with confidence based on a wrong understanding. Sub-aspect of `errors`; read that first.
Migrate WPF applications to WinUI 3 — namespace replacement (System.Windows → Microsoft.UI.Xaml), control mapping (DataGrid→ListView, WrapPanel→ItemsRepeater, TabControl→TabView), threading (Dispatcher→DispatcherQueue), imaging (System.Drawing→BitmapImage), MVVM conversion to CommunityToolkit.Mvvm, and DynamicResource→ThemeResource. Use when converting WPF code, replacing WPF namespaces, or fixing migration build errors.
Use whenever the user asks to "humanize", "make this sound more human", "rewrite to avoid AI detection", "make this less AI-sounding", "add a human voice", or "write like a person". Also use when the user pastes text and asks why it reads as robotic, generic, flat, or AI-like, or when generating new text in a register where AI tells (em dashes, semicolons, hedges, banned vocabulary like "delve", "leverage", "robust") would damage credibility.
Adaptive PLAN.md executor that preserves cook-quality implementation while choosing between direct main-agent work and sub-agent delegation. Runs a phase directly through cook when delegation has no material parallelism, context, or capability benefit; otherwise dispatches disjoint assignments through encode-agent prompts, discloses agent type, model, effort, scope, and rationale before each dispatch, and acceptance-reviews every returned diff. Expects prep to have created PLAN.md + HANDOFF.md and composes with cook, encode-agent, encode-docs, and handoff. Triggers: "/cater".
Map the edge of the learner's understanding with a short graded quiz. Start broad, then binary-search every strand a lesson will need. Use when the user runs /probe or /skill:probe, or says quiz me, pretest, what do I already know, diagnose my understanding, probe me, or find the edge before teaching.
Orca orchestration coordinator runbook for orchestrator sessions only: bind the Run created by /orca-tasks, dispatch ready tasks one-worktree-one-branch, drive the task DAG, watchdog check --wait, gate failures, auto-merge green PRs, release workers. Also has a quick path for 1-2 task runs without a plan. Invoke with /orca-orchestrate.