Loading...
Loading...
Found 802 Skills
DingTalk Schedule and Calendar. This skill is used when users mention "DingTalk schedule", "calendar", "create schedule", "new meeting", "video conference", "DingTalk meeting", "meeting room", "book meeting room", "meeting room availability", "available meeting room", "check-in", "check-out", "check-in link", "check-out link", "recurring schedule", "repeating schedule", "recurrence", "query schedule", "schedule list", "modify schedule", "delete schedule", "availability", "busy/free status", "querySchedule", "calendar", "dingtalk schedule", "schedule reminder". Supported features: Schedule CRUD under primary calendar, user busy/free status, video conference, meeting room availability and schedule binding, check-in/check-out and corresponding links, recurrence rules; Features requiring Calendar.Calendar.Write permission such as subscribing to public calendars can be found in api.md.
Use when the user asks how to look up 지하철 분실물 or 유실물 by 역명/물품명. v1 is an 안내형/하이브리드 skill that structures the official LOST112 + 서울교통공사 flow conservatively.
Invoke this when users react disproportionately intensely to losing (or about to lose) something, or feel an urgent need to "break even" and fail to cut losses after a loss. Typical trigger signals: sunk cost trap, gambler's doubling down, irrational bidding in auctions, inability to abandon failed projects with heavy resource investment. Not applicable to general investment valuation (use value-assessment) or herd behavior (use misjudgment-checklist).
Annie Duke's Decision Quality framework applied to a business decision. Spawns a team of specialist agents — Resulting Auditor, Calibrator, Pre-Mortem Analyst, Quit Strategist, Process Architect — who each apply a distinct lens from Duke's framework to evaluate whether a decision is sound regardless of outcome. The lead synthesizes into a stacking analysis: which biases are operating, which process flaws exist, and the honest Duke verdict. Use when the user says "duke this", "is this a good bet", "should I quit", "evaluate this decision", or faces any high-stakes choice under uncertainty and wants rigorous decision-process analysis. Works as a standalone analysis or after /office-hours.
Provides image recognition capabilities for non-multimodal models (such as pure text models like deepseek-v4-pro, GLM-5.1, mimo-v2.5-pro, etc.). This skill is automatically triggered when the main model cannot recognize images, when users send screenshots/design drafts/UI screenshots for analysis, or when users say 'Look at this image', 'Analyze this screenshot', 'What's wrong with this image'. It also applies to any scenario where users paste images but the current model does not support image input. Supports simultaneous recognition of multiple images, with primary-backup fallback achieved by configuring multiple image recognition models. It can also be manually triggered using the commands /skill:vision-support or /vision. Iron Rule: The models configured for this skill are only used for image content recognition and will never participate in main logical reasoning. Note: If the current model is itself a multimodal model (such as Claude Sonnet 4, GPT-4o, Gemini, etc. that can directly recognize images), do not use this skill; let the main model recognize directly.
Review changes starting from a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (Does the code comply with the coding standards documented in this repository?) and Spec (Does the code meet the requirements from the source issue/PRD?). The two reviews run in parallel sub-agents and report side by side. This applies when users want to review a branch, PR, in-progress changes, or request a "review since X".
Build and refine the project's domain model. Suitable for users who want to clarify domain terms or ubiquitous language, record architectural decisions, or when other skills need to maintain the domain model.
Implement a piece of work based on PRD or a collection of issues.
Applicable when you need to resolve ongoing git merge/rebase conflicts.
Ask which skill or process is suitable for the current scenario; it is the router for all skills in this repository.
Shared vocabulary for designing deep modules. Suitable for users who want to design or improve module interfaces, identify deepening opportunities, decide where to place seams, make code easier to test or more navigable for AI, or when other skills require vocabulary for deep modules.
Continuously question users about their plan or design. Suitable for scenarios where users want to stress-test their plan before building, or when using any "grill" trigger phrases.