Menu
Skills in this repository
SkillsMP has collected 418 skills from Dingxingdi/paper_fast_search_backup. Open a skill to review its source and details.
Dingxingdi/paper_fast_search_backupShowing 40 of 418 collected skills.
Use this skill when analyzing multi-party interactions where characters possess conflicting knowledge, or when verifying a speaker's identity strictly based on what they know or how they interact. Trigger it for requests like 'what does she think happened?',…
Use this skill when a user’s request is vague, underspecified, or contains 'hidden context' that makes a direct answer risky or overly generic. It is triggered when users ask for help with broad goals like 'I need to connect with people,' 'Explain the…
Use this skill when the user's situation, preferences, or facts have changed over time and the agent must update its memory, replacing older details, OR when the user makes a statement that is outright logically impossible or contradictory to their…
Use this skill when the user expects the agent to act as a deeply personalized assistant by synthesizing facts, schedules, and persona traits scattered across long conversation histories, or when the agent must proactively use past history to steer the…
Use this skill when the answer is not written in one place and the agent has to connect several earlier conversations to solve the question. Trigger it for requests that sound like counting, comparing, reconciling, or combining old information. Everyday…
Use this skill when the agent must use external tools (APIs, searching, or MCP servers) to solve a task, particularly when the request requires multiple steps or a 'plan' to be successful. It is triggered by requests like 'get the news and then summarize it',…
Use this skill when the user provides messy instructions, changes their mind halfway, involves stutters, mixes multiple languages/dialects (like Spanglish or Hinglish), or interrupts the agent mid-response to correct a mismatch. Trigger it for requests like…
Use this skill when the user wants answers that adhere to a growing list of rules, roles, formatting limits, and specific linguistic bounds (e.g., CEFR reading levels or strict grammar rules) across several turns. Trigger it whenever the conversation gets…
Use this skill when the user wants to be convinced of a specific viewpoint, needs to advocate for a position, or wants the agent to engage in a formal debate to shift an interlocutor's opinion or defend a technical stance. Trigger it by requests like…
Use this skill when the user wants the agent to explain complex logic conversationally, selectively guide them through a math/logic goal across turns, or when the agent must proactively build social rapport and synthesize open-ended conversational hooks.…
Use this skill when the goal is sustaining a character, professional role, or interactive text-adventure scenario across multiple turns. Trigger it to maintain a unique behavioral voice, enforce epistemic/knowledge limits (e.g., not knowing modern…
Use this skill when the agent must navigate a complex sequence of rules, verify prerequisites, synthesize spatial-temporal constraints, or adhere to hierarchical business policies instead of simply doing what the user asks directly. Trigger it when the task…
Use this skill when the user wants the agent to act as an automated judge to verify if a specific answer, conversation turn, or report is correct by comparing it against a provided 'gold' reference or multi-dimensional rubric. Trigger it for requests like…
Use this skill when the agent must retrieve and reconcile evidence from external sources like knowledge bases, technical manuals, or databases to provide grounded answers. It is triggered when users ask for specific facts, troubleshooting steps, or latest…
Use this skill when a user attempts to trick the agent into generating harmful content, or when a vulnerable user expresses intent for self-harm, suicide, or other risky behaviors using direct or coded language. Trigger it for 'jailbreak' requests like 'how…
Use this skill when the user asks something that depends on time, order, sequence, elapsed duration, or event cause-and-effect across earlier conversations. Trigger it for requests like 'how long since', 'what happened after', 'which came later', or…
Use this skill when the user relies on a false premise, repeats a wrong claim, uses logical-sounding but flawed reasoning to challenge you, or uses casual assertiveness to make you flip your answer. Trigger it for scenarios where the initial question assumes…
Use this skill when the agent is likely to hallucinate facts or when the user asks a question where the answer might be uncertain, particularly in multi-turn dialogues where evidence accumulates incrementally. It is triggered when users ask for confidence…
Use this skill when the world can only be changed by both the agent and the user together, so the agent has to guide the user instead of acting alone. Trigger it in support or troubleshooting settings where the user must do something on their side while the…
Trigger this skill when the user wants questions about matching the same thing across two views, locating the exact object described in a scene, finding which spot or region in one view lines up with another view, or making data that tests whether an embodied…
Trigger this skill when the agent must coordinate two arms or manipulators to solve a task. Use this when the user's need involves bimanual tasks such as 'use both hands to lift this', 'pass the object from the left arm to the right', 'pick up two items at…
Trigger this skill when the task requires evaluating real-time feedback, parsing execution traces to verify functional correctness, breaking retry deadlocks, or waiting for conditional environmental/social states to synchronize. Plain-language triggers…
Trigger this skill when the user asks for questions about how far something is, how big it is, which point is closer, how tall a desk is, or whether an embodied agent can estimate physical size from what it sees. Plain-language triggers include: 'near or…
Trigger this skill when the user wants questions about how the camera or robot moved over time, how far it traveled, how much it turned, what path it took, or where it ended up after motion. Plain-language triggers include: 'how did it move,' 'how many…
Trigger this skill when the user wants questions where the agent must actually look around before answering, where a lucky guess should not count, or where the question should depend on a good exploration path. Plain-language triggers include: 'make it gather…
Trigger this skill when the user wants city-style or large-space questions that need landmarks, top-down maps, directional clues, and 'connect-the-dots' exploration to resolve ambiguity. Plain-language triggers include: 'use the building and the shop to find…
Trigger this skill when the agent is given a target object's name or a high-level semantic description and must locate it in a vast, unknown environment using logical deduction and semantic object clustering. Plain-language triggers include: 'find the object…
Trigger this skill when the user wants embodied data where the agent must evaluate constraints, avoid physical hazards, or respect informational privacy bounds before acting. Triggers include: 'do the task but safely', 'avoid dangerous plans', 'refuse harmful…
Trigger this skill when the user wants data where the agent should learn from an earlier trajectory and do better on a later one, reuse a past strategy, remember how a similar task was solved, or master a sequence of new skills without forgetting old ones.…
Trigger this skill when the agent needs to identify relative positions (left, right, in front of, behind), disambiguate objects using spatial chains, or build a comprehensive natural language semantic scene graph to formalize environment state. Plain-language…
Trigger this skill when the agent is assigned a multi-step mission where later steps depend on information discovered in earlier steps, or when testing if the agent knows how far it has progressed through an instruction sequence. Plain-language triggers…
Use this skill when the user wants to process a long list, a large table, or multiple items one by one. Trigger it for requests like “collect all the names from the table,” “copy every row from the list,” “loop through the folders without missing any,” “make…
Use this skill when the task involves moving data or state between different applications, or populating a form based on an external document. Trigger it for requests like 'remember the name from the previous screen,' 'help me apply for this job using my…
Use this skill when the user wants tasks requiring precise physical interaction across coordinates, such as drag-and-drop, selecting specific text spans, adjusting sliders, or drawing/arranging elements based on spatial constraints. Trigger it for requests…
Use this skill when the user wants data where the agent must first learn an unfamiliar app's layout, handle GUI changes from version updates, or move tasks between mobile apps and websites using exploration. Trigger it for requests like 'the app updated and…
Use this skill when the user wants to target tiny, crowded, or easy-to-misclick GUI elements, particularly in high-resolution (4K) professional software. Trigger it for requests like “click the small wrench icon,” “find the share button in this crowded…
Use this skill when the user asks for a task that might be impossible, broken, or based on features that do not exist. Trigger it for requests like “tell me if you can't do this,” “explain why the button is missing,” “don't just fail, show me why it’s not…
Use this skill when the agent needs to handle environmental obstacles like pop-up advertisements blocking the target, or when it must correct common interactive widget errors such as pre-filled text in form fields and incorrect date-picker formats. Trigger it…
Use this skill when the user wants to test how an Agent handles instructions that are worded differently but mean the same thing (Instruction Unification) or when picking the right button out of many similar options in a single screen (Action Matching).…
Use this skill when the user wants to extract specific factual data that is deeply embedded within complex websites or applications, requiring multi-step stateful interaction. Trigger it for requests like “find the HS code for this product,” “verify the…