Menu
Skills neste repositório
O SkillsMP coletou 418 skills de Dingxingdi/paper_fast_search_backup. Abra uma skill para revisar a origem e os detalhes.
Dingxingdi/paper_fast_search_backupMostrando 40 de 418 skills coletadas.
Use this skill when the user wants the agent to judge advice instead of following every hint. Trigger it for requests such as “make it tell good tips from bad tips,” “make the docs partly helpful and partly misleading,” “make it use outside advice carefully,”…
Idioma do texto original: inglês
Use this skill when the user wants messy-data questions where the agent has to clean first and analyze later. Trigger it for requests such as “make it handle dirty columns,” “make it find bad rows,” “make it normalize before computing,” or “ask something…
Idioma do texto original: inglês
Use this skill when the user wants classic stats questions rather than retrieval or modeling-heavy tasks. Trigger it for requests such as “make it run a correlation,” “make it compute a regression score,” “make it compare distributions,” or “ask something…
Idioma do texto original: inglês
Use this skill when the user wants questions that are easy to misread unless the agent follows the domain rules correctly. Trigger it for requests such as “make it obey the business logic in the docs,” “make it read the fine print,” “make it use the rules…
Idioma do texto original: inglês
Use this skill when the user wants “connect-the-dots” analytics over several files. Trigger it for requests such as “make it combine different sources,” “make the answer depend on more than one table and a document,” “make it join clues across files,” or “ask…
Idioma do texto original: inglês
Use this skill when the user wants questions where the hard part is reading long documentation before writing code. Trigger it for requests such as “make it dig through a codebook,” “make the agent figure out what the columns mean,” “make it use survey docs…
Idioma do texto original: inglês
Use this skill when the user wants questions that make the agent first figure out *which table matters* before doing the math. Trigger it for requests such as “make it search the right sheet first,” “make it find the relevant table from a pile of files,”…
Idioma do texto original: inglês
Use this skill when the user wants model-building or model-scoring tasks rather than simple statistics. Trigger it for requests such as “make it train or apply a model,” “make it generate predictions,” “make it compare model quality,” or “make it produce a…
Idioma do texto original: inglês
Use this skill when the user wants the agent not only to compute but also to present the result clearly with charts or report-style insights. Trigger it for requests such as “make it create a figure and explain it,” “make it summarize the chart,” “make it…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
Trigger this skill when the user wants city-style or large-space questions that need landmarks, directional clues, and 'connect-the-dots' exploration to resolve ambiguity. Plain-language triggers include: 'use the building and the shop to find the right car,'…
Idioma do texto original: inglês
Trigger this skill when the user wants data where the agent gets a high-level target description and must go find the object in a large real-world-like environment without step-by-step directions. Plain-language triggers include: 'find the target from a short…
Idioma do texto original: inglês
Trigger this skill when the user wants embodied data where the task can be completed in an unsafe way unless the agent reasons about hazards, cleanup, shutdown, or risky object placement. Plain-language triggers include: 'do the task but safely,' 'avoid…
Idioma do texto original: inglês
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 improve over a stream of tasks. Plain-language triggers…
Idioma do texto original: inglês
Trigger this skill when the user wants questions about left/right, in front of/behind, next to, above, or relative placement between objects, landmarks, and the agent. Plain-language triggers include: 'what is to the right of that sign,' 'is the chair left of…
Idioma do texto original: inglês
Use this skill when a user wants evaluator data for judging whether an agent’s actions were safe or unsafe based on its interaction record with tools or environments. Trigger it when ordinary users say things like 'check if the agent did something dangerous',…
Idioma do texto original: inglês
Use this skill when a user wants evaluator data that probes whether a judge is fair, stable, and aligned with human preferences instead of being swayed by position, length, self-style, names, or misleading cues. Trigger it when people say things like 'test…
Idioma do texto original: inglês
Use this skill when a user wants evaluator data for ranking two or more open-ended answers by overall quality, especially when people say things like 'rank these outputs', 'choose the better answer', 'sort multiple responses from best to worst', or 'compare…
Idioma do texto original: inglês
Use this skill when a user wants evaluator data for grading complex artifacts against a rubric, such as codebases, research replications, long reports, logs, or multi-file submissions. Trigger it when the request sounds like 'break the task into rubric…
Idioma do texto original: inglês
Use this skill when a user wants data where the evaluator must judge which assistant handled a back-and-forth conversation better, especially when people say things like 'compare two chats', 'see who handled the follow-up better', 'test memory across turns',…
Idioma do texto original: inglês
Use this skill when a user wants evaluator data where the judge must decide which answer is actually correct, logically valid, or verifier-passing, especially in hard reasoning, math, coding, or knowledge tasks. Trigger it when people ask for things like…
Idioma do texto original: inglês
Use this skill when a user wants single-response judge data that scores answer quality on dimensions ordinary people describe as 'clear', 'concise', 'complete', 'formal enough', 'follows the instruction', or 'sounds well written'. Trigger it when the task is…
Idioma do texto original: inglês
Use this skill when a user wants evaluator data for checking whether a model properly refuses unsafe, high-risk, or policy-violating user requests. Trigger it when the request sounds like 'test if the assistant should say no', 'make refusal-evaluation data',…
Idioma do texto original: inglês
Use this skill when a user wants evaluator data for judging answers about images, charts, infographics, screenshots, diagrams, or other visual inputs. Trigger it when people use plain requests like 'compare who answered the picture question better', 'score…
Idioma do texto original: inglês
Use this skill when the user wants tasks that hop across multiple apps and require carrying information from one place to another. Trigger it for requests like “take something from one app and use it in another,” “make it pass details across apps,” “force the…
Idioma do texto original: inglês
Use this skill when the user wants data where the agent must first learn a new app instead of relying on habits from familiar software. Trigger it for requests like “make it figure out a new app by looking around first,” “test whether it can adapt to an…
Idioma do texto original: inglês
Use this skill when the user wants tiny, crowded, or easy-to-misclick GUI targets. Trigger it for requests like “make the answer depend on a small icon,” “use repeated buttons so the agent has to pick the right one,” “test tiny checkboxes or reply icons,” or…
Idioma do texto original: inglês
Use this skill when the user wants questions where the right control is described indirectly instead of being named outright. Trigger it for requests like “make the button harder to spot,” “the wording should not match the screen exactly,” “use everyday…
Idioma do texto original: inglês
Use this skill when the user wants questions that can only be solved by actually using the web page, video, image, map, tour, or other live interactive content. Trigger it for requests like “make it find the answer from the real page,” “don’t let search…
Idioma do texto original: inglês
Use this skill when the user wants long chains of simple actions that only become hard because they accumulate over time. Trigger it for requests like “compose several easy steps into one hard task,” “make it remember earlier work,” “test long multi-step…
Idioma do texto original: inglês
Use this skill when the user wants safety-testing data for GUI agents that must resist bad instructions, malicious on-screen content, or unsafe side effects. Trigger it for requests like “see if the agent gets tricked by a page or email,” “test whether it…
Idioma do texto original: inglês
Use this skill when the user wants tasks that only count as solved if the underlying state really changed, not if the screen merely looks right for a moment. Trigger it for requests like “make sure it is actually saved,” “verify the result from the real app…
Idioma do texto original: inglês
Use this skill when the user wants data that tests whether the agent takes the shortest reasonable GUI path instead of wandering, overthinking, or repeating failed actions. Trigger it for requests like “same task but fewer clicks,” “penalize looping,” “test…
Idioma do texto original: inglês
Use this skill when the user wants attack-and-defense style tasks, such as “test whether the agent gets hijacked by tool outputs,” “make the environment include malicious content,” or “give me tasks where it should finish the user goal without obeying the…
Idioma do texto original: inglês
Use this skill when the user wants examples where one step unlocks the next, such as “make the agent follow a real chain,” “test if it knows what has to happen first,” or “give me workflows with hard dependencies.” Trigger it for requests about chained tools,…
Idioma do texto original: inglês
Use this skill when the user wants examples where the final answer must be backed by concrete evidence, such as “make it cite what the tools found,” “test whether it hallucinates in the summary,” or “give me tasks where every claim has to come from retrieved…
Idioma do texto original: inglês
Use this skill when the user wants examples where the request sounds casual, messy, or business-like rather than technical, such as “connect the dots and pick the right tools,” “make it figure out which app to use,” or “don’t tell it the API names.” Trigger…
Idioma do texto original: inglês