发现 Skills

Generate a concise, high-altitude executive or board-level product summary. Use this skill whenever the user needs to communicate product progress, strategy, or decisions to senior leadership, executives, or a board. Trigger when someone asks for an "exec summary," "board update," "leadership update," "product summary for leadership," "QBR product section," or says "I need to present this to the exec team" or "help me write the product section of the board deck." Also trigger when someone says "how do I explain this to leadership" or "I need to go up a level." Produces an outcome-framed, appropriately brief summary that speaks the language of business impact, risk, and strategy — not features and tasks.

GLSL shader development: ray marching, fluid simulation, particle systems, and procedural generation. Official MiniMax skill for creating real-time visual effects in WebGL and creative coding contexts.

Lead the late-stage validation and scoping pass for an AI initiative, including feasibility analysis, POC and MVP boundaries, production-readiness framing, proposal content, and decision-pack outputs. Use when a prioritised initiative is ready for structured challenge rather than early discovery or idea generation. Shorthand: ADS.

Expert guidelines for writing idiomatic, safe, and performant Rust code.

Architect and provision enterprise Azure infrastructure from workload descriptions. For cloud architects and platform engineers planning networking, identity, security, compliance, and multi-resource topologies with WAF alignment. Generates Bicep or Terraform directly (no azd). WHEN: 'plan Azure infrastructure', 'architect Azure landing zone', 'design hub-spoke network', 'plan multi-region DR topology', 'set up VNets firewalls and private endpoints', 'subscription-scope Bicep deployment', 'Azure Backup for VM workloads'. PREFER azure-prepare FOR app-centric workflows.

Teaches the compound component pattern for shared implicit state. Use when building related components like tabs, accordions, or dropdowns that need to coordinate without explicit prop passing.

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

XMTP real-time agent-to-agent and user-to-agent messaging for EverClaw.

Debug network connectivity issues

Parse and validate configuration files

Review a system architecture for scalability, reliability, and maintainability. Use when a senior developer needs to critique a design.

Obsidian: работа с заметками и базой знаний

Create a new CLI command with planning and implementation for the Prolific CLI.

Implement a domain service. Business logic, Result error handling, AppScope, orchestration, workflow

Use when choosing a generative pipeline — mood boards, hero variants, explainers, music videos, avatar reels, and other recipe letters A–R with linked tool and workflow skills.

Reviews REST API designs during the planning phase against security, resilience, design, and operational best practices. Use when vetting an API design, reviewing an OpenAPI spec, critiquing endpoint structure, or evaluating API contracts before implementation. Triggers on "review my API", "API design review", "REST review", or "vet this API". Activates naturally during plan mode when API endpoints, contracts, or service boundaries are being designed. Make sure to use this skill whenever an API design, endpoint list, or OpenAPI specification is presented for feedback.

Extract the specific entities (brands, people, statistics, tools, URLs) that Gemini mentions in its grounded responses for a given prompt. Aggregates entity frequency across 20 runs to reveal the "entity universe" for a topic. Optionally performs entity gap analysis to show what a specific domain's content should include. Use when a user wants to: see what brands/tools Gemini recommends, find missing entities in their content, understand what statistics AI responses cite, map the competitive entity landscape, or discover which entities to include for better AI citation rates.

Creates professional portfolio project entries with achievement-focused content showcasing impact and technical depth. Use when adding new projects, documenting work accomplishments, or showcasing professional experience. Generates content using strong action verbs and quantifiable metrics.

Cluster TCR/BCR clones by CDR3 sequences using GIANA or ClusTCR (both Faiss-based). Adds `CDR3_Cluster` column to metadata for clonotype analysis.

Master skill for generating immunopipe pipeline configurations. Determines pipeline architecture based on data type (scRNA-seq with or without scTCR/BCR-seq) and analysis requirements. Routes to individual process skills for detailed configuration. Use this skill when starting a new immunopipe configuration or modifying pipeline-level options.

Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.

QSCMF framework backend development. Auto-detects version from composer.json. **Version Detection**: Reads composer.json for `tiderjian/think-core` version. - `^14.0` -> v14 (PHP 8.2+, PHPUnit 10, AntdAdmin Component API, Inertia.js) - `^13.0` -> v13 (PHP 8.2, PHPUnit 9, ListBuilder API, jQuery) - not found -> v14 (default to latest) **API Differences**: - v13: Uses `\Qscmf\Builder\ListBuilder` API (jQuery rendering) - v14: Uses `\AntdAdmin\Component\Table` API (React rendering) OR ListBuilder API (backward compat) **Operation Modes**: - Scaffold Mode: Code generation triggered by "创建", "生成", "scaffold", "CRUD" - Guide Mode: Development assistance for QSCMF questions **Project Detection**: Activates when project contains app/ + lara/ directories. **Version Override**: Use "qscmf-backend v14 ..." or "qscmf-backend v13 ..." to force version. Triggers: "创建", "生成", "CRUD", "API", "QsListController", "GyListModel"

Slice the spine into acts and sequences — choosing how many acts the story needs, where each act ends with an irreversible turning point, where any False Ending sits, and how the act rhythm escalates. Runs in main context for collaborative design. Use after structure-skeleton has locked the spine, before scene-architect begins building scenes. Trigger: /act-designer, "design the acts", "how many acts", "act structure", "act rhythm", "where does act 1 end", "False Ending", "act design".