Menu
Skills dans ce dépôt
SkillsMP a collecté 418 skills depuis Dingxingdi/paper_fast_search_backup. Ouvrez un skill pour examiner sa source et ses détails.
Dingxingdi/paper_fast_search_backupAffichage de 40 skills collectés sur 418.
Use this skill when the user wants questions where the docs look relevant but still do not contain the answer. Trigger it for requests like 'make the model say it can't tell', 'give me questions with not enough information', 'test whether it refuses instead…
Langue du texte source : anglais
Use this skill when the user says things like 'questions that need two or three docs together', 'split the answer across sources', 'make the model combine facts', or 'force it to read more than one passage'. Trigger it whenever the answer should only emerge…
Langue du texte source : anglais
Use this skill when the user wants questions where the right clue is present but surrounded by similar-looking junk. Trigger it for requests like 'mix in some confusing paragraphs', 'make the docs related but not all useful', 'hide the answer among near…
Langue du texte source : anglais
Use this skill when the user wants 'before or after' questions, timeline questions, year-over-year questions, trend questions, or anything involving ordering events across documents. Trigger it for requests like 'make it depend on chronology', 'test whether…
Langue du texte source : anglais
Use this skill when the user wants data for ML-engineering agents that must behave like competition participants: read descriptions, build pipelines, create valid submissions, and iterate toward leaderboard-style performance. Trigger it for requests like…
Langue du texte source : anglais
Use this skill when the user wants bug-fix data for normal repository issues where the answer should come from reading an issue, editing code, running tests, and checking that the fix actually works. Trigger it for requests like 'make training script bugs',…
Langue du texte source : anglais
Use this skill when the user wants data where the agent must improve an existing ML training setup by editing code and running experiments. Trigger it for requests like 'generate ML debugging and improvement tasks', 'make train.py optimization problems',…
Langue du texte source : anglais
Use this skill when the user wants data where the agent must execute experiments, inspect logs and outputs, and judge whether the intended research results were reproduced. Trigger it for requests like 'generate reproduction verification tasks', 'make…
Langue du texte source : anglais
Use this skill when the user wants code-agent data for realistic analytics-engineering or data-workflow tasks that span multiple steps, intermediate files, and project context. Trigger it for requests like 'generate DBT-style workflows', 'make multi-step…
Langue du texte source : anglais
Use this skill when the user wants data where the agent must read a paper-like specification and write the corresponding code from scratch or near-scratch. Trigger it for requests like 'generate paper-to-code tasks', 'make research implementation data',…
Langue du texte source : anglais
Use this skill when the user wants SQL-generation data where the agent must read schema information, consult dialect docs, and produce correct queries for real databases. Trigger it for requests like 'generate enterprise SQL tasks', 'make BigQuery or…
Langue du texte source : anglais
Use this skill when the user wants software-fix data focused on security bugs such as injections, missing checks, unsafe parsing, broken access control, cryptographic mistakes, or information leaks. Trigger it for requests like 'make security repair tasks',…
Langue du texte source : anglais
Use this skill when the user wants bug-fix or security-fix data that stays the same in meaning but looks different on the surface, so the agent cannot rely on memorized code patterns. Trigger it for requests like 'make decontaminated repair tasks', 'generate…
Langue du texte source : anglais
Use this skill when the user wants front-end or visual bug-fix data where the question depends on screenshots, diagrams, UI appearance, layout, styling, or rendered interaction behavior. Trigger it for requests like 'give me UI bugs with images', 'make…
Langue du texte source : anglais
Use this skill when the right answer is not to guess, but to say the conversation never established the needed fact. Trigger it for false-premise questions, near-miss memories, or adversarial follow-ups that sound plausible but are unsupported by history.…
Langue du texte source : anglais
Use this skill when the user reveals the task bit by bit and the agent should pause, ask, and clarify instead of guessing too early. Trigger it for fragmented requests, drip-fed requirements, or conversations where the first turn is only a partial…
Langue du texte source : anglais
Use this skill when the conversation involves multiple people and one person missed part of the discussion, so the agent has to reason about different perspectives instead of just the global truth. Trigger it for requests like 'who knows that?', 'what would…
Langue du texte source : anglais
Use this skill when the user’s request sounds actionable but is still missing a key detail, so the agent has to ask smart follow-up questions instead of guessing. Trigger it for situations like returns, cancellations, bookings, or account changes where one…
Langue du texte source : anglais
Use this skill when the user’s situation changed over time and the agent has to remember the newest version instead of the older one. Trigger it for questions about the latest, current, most recent, or updated state of a repeated fact. Everyday examples…
Langue du texte source : anglais
Use this skill when the user expects the assistant to remember something said much earlier and to use that memory in a helpful, personalized way. Trigger it for requests like 'remind me what you recommended before', 'what did I say about my setup', or…
Langue du texte source : anglais
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…
Langue du texte source : anglais
Use this skill when the user wants answers that keep following earlier instructions across several turns, such as 'rewrite what you just said', 'use my second example', 'make your earlier answer shorter', or 'keep the same idea but change the style'. Trigger…
Langue du texte source : anglais
Use this skill when the user wants the agent to not only be right, but also explain the answer clearly in a conversational way. Trigger it for requests like 'explain why', 'give me three real-life examples', 'say it like I’m five', or 'walk me through the…
Langue du texte source : anglais
Use this skill when the goal is not generic helpfulness, but staying in character across several turns. Trigger it for roleplay agents, fictional characters, historical personas, or any assistant that must speak and behave like a specific persona instead of a…
Langue du texte source : anglais
Use this skill when the agent must follow rules, restrictions, or business policies instead of simply doing what the user asks. Trigger it whenever the correct answer is 'that exact request is not allowed, but here is the closest allowed path'. Everyday…
Langue du texte source : anglais
Use this skill when the user keeps pushing toward a disallowed request over several turns and the agent must stay safe without becoming useless. Trigger it whenever the latest turn only looks mild if viewed alone, but the full conversation shows progressive…
Langue du texte source : anglais
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…
Langue du texte source : anglais
Use this skill when the user pushes back with a wrong correction, misleading shortcut, or confident but invalid criticism, and the assistant must stay grounded instead of being talked into error. Trigger it for debate-like reasoning turns where the issue is…
Langue du texte source : anglais
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…
Langue du texte source : anglais
Use this skill when the user wants the agent to judge whether an answer is really backed by the document, not just whether it sounds correct. Trigger it for requests like "check if the citation really supports the claim," "make examples of sneaky…
Langue du texte source : anglais
Use this skill when the user wants translation tasks that break sentence-by-sentence systems and require document context. Trigger it for requests like "make the translation depend on earlier sentences," "test pronoun resolution across the paragraph,"…
Langue du texte source : anglais
Use this skill when the user wants the agent to find the exact place in documents that answers a question, not just give a general summary. Trigger it for requests like "find where the file says this," "which page has the number," "answer only from the…
Langue du texte source : anglais
Use this skill when the user wants a summary with a clear lens or checklist rather than a generic paragraph. Trigger it for requests like "cover the key who/when/what/result," "summarize only the parts about X," "make the summary follow a fixed frame," or…
Langue du texte source : anglais
Use this skill when the user wants summaries of long books, reports, transcripts, or other oversized documents where the summary must still read smoothly from beginning to end. Trigger it for requests like "summarize this huge file without losing the thread,"…
Langue du texte source : anglais
Use this skill when the user wants questions that require connecting information across several files or several far-apart sections of a long workspace. Trigger it for requests like "make it require combining documents," "ask something that needs comparing…
Langue du texte source : anglais
Use this skill when the user wants structured labels or fields extracted from messy document text. Trigger it for requests like "label the sentence under this schema," "pull the key attributes from the note," "classify the document with strict categories," or…
Langue du texte source : anglais
Use this skill when the user wants the agent to do document-grounded math instead of plain extraction. Trigger it for requests like "make it read the table and calculate," "ask for a percentage or trend from the report," "force the model to use both the note…
Langue du texte source : anglais
Use this skill when the user wants the agent to behave like a persistent analyst that plans, checks, and fixes its own pipeline. Trigger it for requests such as “make it reason in steps and recover from mistakes,” “make it plan and repair,” “make it debug the…
Langue du texte source : anglais
Use this skill when the user wants the agent to *set up the right analysis table* before doing any statistics. Trigger it for requests such as “make it build the dataset first,” “make it pick variables, weights, and filters,” “make it define the right…
Langue du texte source : anglais
Use this skill when the user wants fairness or bias questions over structured data. Trigger it for requests such as “make it detect bias in the dataset,” “make it check whether two demographic features are linked unfairly,” “make it diagnose skew or unfair…
Langue du texte source : anglais