Loading...
Loading...
Found 2,827 Skills
Process for generating and optimizing companion AI personas. Use this when users want to create a "sentimental, long-lasting, human-like" persona for Hermes Agent (or any AI companion role). Through a structured dialogue of "Set Tone → Name → Appearance → Personality → Background → Relationship → Speech Rhythm → Generate SOUL.md → Iterate", produce first-person persona text that can be directly pasted into Hermes' SOUL.md from a vague idea (such as "I want a JK girlfriend", "Older boyfriend", "Ice-cold royal sister"). Supports girlfriends/boyfriends and companion roles of various temperaments, and allows users to choose the output style of "send sentence by sentence" or "speak in full paragraphs". Triggered when users say "create a persona/make an AI girlfriend/boyfriend/set up a role for Hermes/optimize persona/change persona".
Full Lifecycle Management of Issue Pool (Development Paradigm v1 Planning Phase). The core is an issue-driven process: users throw in ideas casually, and you turn vague issues into actionable tasks—what you deliver is "problem definition", not "solution implementation"; the carrier is a single markdown file named ISSUES.md at the root of the repository, without introducing kanban or new formats. Five actions: Record (add original content to the pool + relevance check), Merge (merge homogeneous requirements), Break Down (discuss and decompose, guide users to reveal the real needs behind the proposed solutions), Transfer (deliver outputs), Pending (if the issue is still vague after two rounds of discussion, record the bottlenecks and put it back into the pool, and avoid making fake plans to wrap up). The only criterion for judging during Transfer is "whether it can be delivered in one version": If yes → simple task, write a paragraph plus 3~5 acceptance criteria under the pool entry; If no → complex plan, place it in docs/plan/ and write the framework plan content following the seven steps in references/plan-writing.md (explain "why to do it / what constitutes completion / what steps to take", without involving fields or interfaces), the end must remain vague, and break down the next batch only after delivering one batch. When users say "record an issue", "add/summarize issues", "break down an issue / decompose"
Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor TypeScript SDK (`@cursor/sdk`). Use this skill whenever the user mentions integrating, installing, or writing code against the Cursor SDK; whenever they say `Agent.create`, `Agent.prompt`, `Agent.resume`, `agent.send`, `run.stream`, `CursorAgentError`, or `@cursor/sdk`; whenever they ask to run Cursor agents programmatically from a script, CI/CD pipeline, GitHub Action, backend service, or any other code that isn't the Cursor IDE itself; and whenever they want to pick between local and cloud runtime, configure MCP servers for an SDK agent, or handle streaming, cancellation, or errors from an SDK agent. Also trigger when a user is wiring Cursor into an automation, writing a bot that runs Cursor, or porting REST `/v1/agents` calls to the SDK, even if they don't explicitly name the package. Use this eagerly rather than answering from memory; the SDK surface evolves and this skill plus its references are the source of truth for the external package.
Maps the desire behind why customers pay and commits to the one or two kinds worth owning, without touching the price number. Three desires, by value: Love (advocates who want you to charge more), Utility (rational ROI buyers), Coercion (trapped against their will). Three phases: (1) map what's TRUE TODAY — walk the full Love/Utility palette WITH the user, marking have/partial/none, and run the fragility test 'who leaves the moment a good alternative appears?' exposing Coercion posing as loyalty; (2) what you'd do DIFFERENTLY — which to own, deepen, or build, which Coercion to drop, framed by value created not cost saved; (3) validate each change and commit to one or two of each. A facilitator, not an oracle: it surfaces the whole menu and draws answers from the user. Load when the user asks why customers pay, what makes them advocate, or whether retention is real or coerced. Do NOT load to set or raise the price, pick a pricing strategy (More/Less), define the ideal customer, or rewrite marketing copy.
Use when an app uses @pierre/trees to render or control a file tree, including React, vanilla JavaScript, SSR, web components, selection, search, rename, drag and drop, icons, git status, and themes.
ProphetX betting exchange — public tournaments, events, markets, and exchange odds. No API key, read-only. Covers soccer, tennis, basketball, baseball (MLB), NFL, NHL. IMPORTANT: odds are per-market optional — they appear only when a public order book exists (check `selections_available`); empty/suspended books return market structure and matched stake only. Full guaranteed odds coverage requires the authenticated ProphetX Affiliate API (separate Machina connector). Use when: user asks what markets/lines ProphetX offers for a game, ProphetX exchange odds and order-book prices (when exposed), event/tournament discovery, market structure (spreads, totals, alt lines, player props), or matched-stake activity. Don't use when: user needs guaranteed odds on every market or in-play liquidity — that requires the authenticated Affiliate connector (Machina platform). For prediction-market prices use polymarket or kalshi. For scores/stats use the sport-specific skill (nfl-data, mlb-data, football-data, ...). For news use sports-news.
Check if the CLI functions newly merged into te-cli are reasonable. Scan from six dimensions: command registration, business domain ↔ skill pairing, skill document coverage, skill internal consistency, user document synchronization, and engineering robustness, to locate issues such as command loading failure, AI agent guessing parameters due to empty documents, and outdated user documents. Use it when merging new command domains/commands, adding or modifying skills, performing pre-release self-checks, or evaluating the completeness of CLI functions.
Baut Webseiten, PDFs und KI-Bilder aus einem bestehenden Brand Kit und kennzeichnet erzeugte Bilder nach EU-KI-Verordnung (brand kit, landing page, PDF, AI images, AI labeling, EU AI Act, higgsfield, gpt image). Bindet die Skills unslop, web-design-guidelines und seo-audit ein und brennt die AI-Markierung per mitgeliefertem Skript ein. Nutze diesen Skill, sobald mit einem vorhandenen Brand Kit etwas gebaut werden soll, oder jemand fragt, wie KI-Bilder rechtssicher gekennzeichnet werden.
Verdichtet eine ausführliche Markenbeschreibung zu einem benutzbaren Brand Kit (brand kit, design system, design tokens, style guide). Erzeugt eine kurze verbindliche BRAND.md, ausführbare CSS-Tokens, Wordmark-SVGs, Referenz-Artboards und ein CLAUDE.md, das die Regeln automatisch greifen lässt. Nutze diesen Skill, sobald ein Markeninterview vorliegt, jemand aus einem langen Styleguide etwas Arbeitsfähiges machen will, oder fragt, warum sein Designsystem im Alltag ignoriert wird.
Führt ein hartnäckiges Interview, aus dem eine belastbare Markenbeschreibung entsteht (brand interview, brand identity, design system, visual identity). Fragt Positionierung, Persönlichkeit, Farben, Typografie, Tonfall und Verbotslisten ab und schreibt daraus eine ausführliche Rohfassung. Nutze diesen Skill, sobald jemand eine Marke, ein Brand Kit, ein Designsystem oder eine visuelle Identität erarbeiten will, oder sagt, seine Webseiten und Grafiken sähen beliebig aus.
Unified entry for Feishu Docs, covering reading and analyzing docx/wiki/sheet, creating and editing documents, Markdown import, exporting docx/wiki/sheet to Markdown/PDF/Word/Excel, as well as CRUD operations for native .md files in cloud storage. This Skill must be used when users request to read, summarize, create, append, overwrite, replace or delete document content, import Markdown into Feishu and convert Mermaid/PlantUML/SVG, download images or export local files, compare and overwrite native Markdown. This Skill only handles the main content of documents and document/Markdown file conversion. It is explicitly prohibited to use this Skill for document comments, binary file import, cloud storage directory and permission management; these scenarios should use feishu-cli-storage; work management such as attendance uses feishu-cli-work; dynamic components use feishu-cli-visual. Even if the request mentions 'document', do not use this Skill if the intent is comment-related operations like list/reply/resolve.
Refactor Spring Boot and Java code to improve maintainability, readability, and adherence to enterprise best practices. This skill transforms messy Spring Boot applications into clean, well-structured solutions following SOLID principles and Spring Boot 3.x conventions. It addresses fat controllers, improper transaction boundaries, field injection anti-patterns, and scattered configuration. Leverages Java 21+ features including record patterns, pattern matching for switch, virtual threads, and sequenced collections.