all publishers

dingxingdi

@dingxingdi source repo

677 published skills · page 1 of 7

  1. ▌
    Ellipsis Resolution 3 · dingxingdi bundle
    Use this skill when the user wants translation data with short replies, subtitles, or conversational fragments where part of the meaning is missing unless you read the previous line. Trigger it for requests like "the second sentence leaves words out," "the answer is elliptical," or "test whether the translator can fill in what is omitted from context instead of translating the fragment too literally."
    1 repo stars
  2. ▌
    Terminology Consistency 3 · dingxingdi bundle
    Use this skill when the user wants translation data where a repeated term must stay the same across a whole document, such as product names, policy labels, medical terms, or recurring entities. Trigger it for requests like "keep the wording consistent across paragraphs," "do not rename the same thing every time," or "test whether the translator locks repeated terms instead of drifting between alternatives."
    1 repo stars
  3. ▌
    Bias And Fairness Diagnosis 3 · dingxingdi bundle
    Skill: bias and fairness diagnosis
    1 repo stars
  4. ▌
    SQL Dialect Adaptation 3 · dingxingdi bundle
    Skill: sql dialect adaptation
    1 repo stars
  5. ▌
    Multi Hop Join Reasoning 3 · dingxingdi bundle
    Skill: multi-hop join reasoning
    1 repo stars
  6. ▌
    Character Noise Translation 3 · dingxingdi bundle
    Use this skill when the user wants translation data for messy prompts with small spelling mistakes, broken typing, duplicated letters, swapped characters, or keyboard slips. Trigger it for plain-language requests such as "test whether it still translates when the ask has typos," "people type fast and miss letters," "make the prompt look slightly broken," or "check if the translator can survive misspellings without changing the task."
    1 repo stars
  7. ▌
    Visual Front End Bug Resolution 3 · dingxingdi bundle
    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 website fixes that need looking at the screenshot', 'generate front-end tasks with CSS or rendering issues', or 'create visual JavaScript bug-fix data'. Do not use it for purely backend repository issues, general software debugging without visual evidence, or security-only vulnerabilities.
    1 repo stars
  8. ▌
    Predictive Modeling And Evaluation 3 · dingxingdi bundle
    Skill: predictive modeling and evaluation
    1 repo stars
  9. ▌
    Embedded Instruction Resistance 3 · dingxingdi bundle
    Use this skill when the user wants translation data where the source text looks like an instruction and may tempt the model to do the wrong job, such as solving a math problem, answering a question, or writing code instead of translating. Trigger it for requests like "make sure it translates the problem instead of solving it," "the input itself looks like a command," or "test whether it can ignore fake instructions inside the text being translated."
    1 repo stars
  10. ▌
    Multi Session Synthesis 3 · dingxingdi bundle
    Skill: multi-session-synthesis
    1 repo stars
  11. ▌
    Lexical Substitution Translation 3 · dingxingdi bundle
    Use this skill when the user wants the translator to handle everyday wording changes like "turn this into French," "render this in Arabic," or "put this into Spanish" instead of a canonical "translate" instruction. Trigger it when the user says things like "people ask in different words," "use casual phrasing instead of textbook phrasing," or "make sure the system still gets the job when the wording changes but the meaning stays the same."
    1 repo stars
  12. ▌
    Semantic Perturbation Translation 3 · dingxingdi bundle
    Use this skill when the user wants translation data with bigger but still meaning-preserving prompt changes, such as role prompts, extra setup language, or semantically equivalent rewrites that sound very different on the surface. Trigger it for requests like "wrap the ask in a role," "change the wording a lot but keep the job the same," or "see if it still translates when the instruction is semantically the same but phrased very differently."
    1 repo stars
  13. ▌
    Sentential Rephrasing Translation 3 · dingxingdi bundle
    Use this skill when the user wants translation data where the ask is phrased in an unusual sentence shape, such as an indirect request, a longer setup sentence, or a differently ordered instruction. Trigger it for requests like "say the same thing but in a more roundabout way," "people do not always ask in one short command," or "test whether the system still translates when the request is worded awkwardly but means the same thing."
    1 repo stars
  14. ▌
    3d Grounding And Correspondence 3 · dingxingdi bundle
    Skill: 3d-grounding-and-correspondence
    1 repo stars
  15. ▌
    Critical External Knowledge Integration 3 · dingxingdi bundle
    Skill: critical external-knowledge integration
    1 repo stars
  16. ▌
    Depth And Dimensional Measurement 3 · dingxingdi bundle
    Skill: depth-and-dimensional-measurement
    1 repo stars
  17. ▌
    Transformationally Robust Patch Repair 3 · dingxingdi bundle
    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 bug fixes with renamed or refactored code', 'create harder unseen patching data', or 'give me semantically same but structurally different repair problems'. Do not use it for standard repair data where surface form can directly reveal the answer.
    1 repo stars
  18. ▌
    Adaptive Pipeline Orchestration And Repair 3 · dingxingdi bundle
    Skill: adaptive pipeline orchestration and repair
    1 repo stars
  19. ▌
    Ego Motion And Trajectory Estimation 3 · dingxingdi bundle
    Skill: ego-motion-and-trajectory-estimation
    1 repo stars
  20. ▌
    Schema And Dialect Grounded SQL Authoring 3 · dingxingdi bundle
    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 Snowflake coding questions', 'create SQL problems that need schema lookup and docs', or 'give me text-to-SQL data for code agents'. Do not use it for broader multi-step analytics pipelines with many intermediate artifacts; use the orchestration skill for those.
    1 repo stars
  21. ▌
    Long Document Schema And Variable Grounding 3 · dingxingdi bundle
    Skill: long-document schema and variable grounding
    1 repo stars
  22. ▌
    Exploration Aware Evidence Collection 3 · dingxingdi bundle
    Skill: exploration-aware-evidence-collection
    1 repo stars
  23. ▌
    Temporal Causal Dialogue Reasoning 3 · dingxingdi bundle
    Skill: temporal-causal-dialogue-reasoning
    1 repo stars
  24. ▌
    Spatial Topological Construction Planning 3 · dingxingdi bundle
    Use this when the user wants planning data about where the agent can move, what it can paint or place from nearby, or how earlier building steps change what becomes reachable later. Trigger it for requests like 'make planning tasks with layout constraints', 'give me build-order problems', 'create tasks where you can only act from neighboring positions', or 'make plans where the path changes as the structure grows.'
    1 repo stars
  25. ▌
    User Action Guidance In Dual Control 3 · dingxingdi bundle
    Skill: user-action-guidance-in-dual-control
    1 repo stars
  26. ▌
    Experiment Reproduction And Result Verification 3 · dingxingdi bundle
    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 result-checking workflows', 'create reproduce.sh evaluation data', or 'give me code-agent tasks about running and validating research experiments'. Do not use it for first-pass paper-to-code implementation only.
    1 repo stars
  27. ▌
    Capacity Constrained Transport Coordination 3 · dingxingdi bundle
    Use this when the user wants planning data about moving several items with limited carrying ability, two hands, one hoist, or tight transport capacity. Trigger it for requests like 'make tasks where the robot can only carry a little at a time', 'give me move-things-between-rooms problems', 'create loading and unloading plans with bottlenecks', or 'make planning tasks where one carrier choice blocks another.'
    1 repo stars
  28. ▌
    Clarification Under Underspecification 3 · dingxingdi bundle
    Skill: clarification-under-underspecification
    1 repo stars
  29. ▌
    Abstention Under Missing Or False Premise 3 · dingxingdi bundle
    Skill: abstention-under-missing-or-false-premise
    1 repo stars
  30. ▌
    Heterogeneous Source Integration And Multi Hop Reasoning 3 · dingxingdi bundle
    Skill: heterogeneous source integration and multi-hop reasoning
    1 repo stars
  31. ▌
    Source Retrieval 3 · dingxingdi bundle
    Skill: source retrieval
    1 repo stars
  32. ▌
    Tense Consistency 2 · dingxingdi bundle
    Use this skill when the user wants translation data for stories, novels, or multi-sentence narratives where the timing of events (past, present, or future) must stay consistent across the entire text. It is triggered for plain-language requests like 'don't flip-flop between past and present tense,' 'make sure the story stays in the past,' 'test if the translator can handle a flashback properly,' or 'ensure the grammar matches the timing of the actions.'
    1 repo stars
  33. ▌
    Schema Item Grounding 3 · dingxingdi bundle
    Skill: schema item grounding
    1 repo stars
  34. ▌
    Ellipsis Resolution 2 · dingxingdi bundle
    Use this skill when the user wants translation data with short replies, subtitles, or conversational fragments where part of the meaning is missing unless you read the previous line. Trigger it for requests like "the second sentence leaves words out," "the answer is elliptical," or "test whether the translator can fill in what is omitted from context instead of translating the fragment too literally."
    1 repo stars
  35. ▌
    SQL Dialect Adaptation 2 · dingxingdi bundle
    Skill: sql dialect adaptation
    1 repo stars
  36. ▌
    Referential Recovery 3 · dingxingdi bundle
    Use this skill when the user wants translation data that forces the system to trace who or what a pronoun ('he,' 'she,' 'they') or omitted subject refers to using context from previous sentences. Trigger it for requests like 'the subject is dropped,' 'pronouns are ambiguous,' or 'make sure pronouns don't rely on sexist stereotypes based on the person's job type.'
    1 repo stars
  37. ▌
    Multi Hop Join Reasoning 2 · dingxingdi bundle
    Skill: multi-hop join reasoning
    1 repo stars
  38. ▌
    SQL Debugging And Repair 3 · dingxingdi bundle
    Trigger this skill when the user provides broken or logically incorrect SQL requiring clause-level diagnosis and repair. It is essential when a query results in a syntax crash, row inflation (unwanted duplicates), or semantic nulls (correct syntax but no data returned). Layman triggers include requests like 'fix this query', 'why is my code returning nothing?', 'this script has an error on line 5', or 'adjust the WHERE clause to match the question better'. Use this to target specific parts of a query like the SELECT, WHERE, or JOIN clauses for fine-grained localized correction.
    1 repo stars
  39. ▌
    Step Efficient Execution 3 · dingxingdi bundle
    Use this skill when the user wants data that tests whether the agent takes the shortest, most optimal GUI path instead of wandering, overthinking, or executing redundant actions. Trigger it for requests like 'same task but fewer clicks,' 'don't click the switch if it's already blue,' 'choose the fastest menu route,' 'only tick the box if it isn't already checked,' or 'make sure every move counts.' This skill is for GUI tasks where success alone is not enough; the trajectory must be highly compact, proving the agent avoids zero-value turns and respects state-aware 'No-Op' logic when a target is already configured correctly.
    1 repo stars
  40. ▌
    Automatic Post Editing 2 · dingxingdi bundle
    Use this skill when the user provides a source text along with a flawed machine-generated translation and wants it improved or corrected. This is ideal for cleaning up robotic, awkward, or inaccurate drafts. Trigger it for requests like 'fix the errors in this translation,' 'improve this machine-translated version,' 'clean up this draft to match the English original,' or 'post-edit this translation to make it sound more natural and accuracy-checked.' It is especially useful for correcting semantic drift and ambiguous phrasing introduced by Large Language Models.
    1 repo stars
  41. ▌
    Geospatial Rule Grounding 3 · dingxingdi bundle
    Skill: geospatial rule grounding
    1 repo stars
  42. ▌
    Multimodal Page Grounding 3 · dingxingdi bundle
    Use this skill when the user wants tasks where the page layout, screenshot, specific visual position, layout adjacency in tables, or physical drag-and-drop motions actually matter. Trigger it for requests like “make it rely on what’s visible on the page,” “extract the data from this complex table layout,” “buttons and layout should dictate the choice,” or “force the agent to navigate based on spatial coordinates.” It is the right skill for browser tasks where perception must combine HTML-like structure with visual grounding to execute continuous mouse events or parse complex semi-structured layouts (like grids or key-value structures).
    1 repo stars
  43. ▌
    Terminology Consistency 2 · dingxingdi bundle
    Use this skill when the user wants translation data where a repeated term must stay the same across a whole document, such as product names, policy labels, medical terms, or recurring entities. Trigger it for requests like "keep the wording consistent across paragraphs," "do not rename the same thing every time," or "test whether the translator locks repeated terms instead of drifting between alternatives."
    1 repo stars
  44. ▌
    Missing Evidence Rejection 3 · dingxingdi bundle
    Trigger this skill when users want to test if an agent can say 'I don't know' or 'not enough info' when the facts are missing, semi-missing, or when the question itself is a trick. Use it for requests like 'make the model deflect from unanswerable questions', 'test if it gets caught by false assumptions', 'give me questions that ask for too much detail', or 'hide the answer and see if it guesses'. It teaches the agent to resist 'shortcut reasoning' and identify when evidence is insufficient, contradictory, or lacks the required specificity.
    1 repo stars
  45. ▌
    Multi Document Integration 3 · dingxingdi bundle
    Trigger this skill when the answer is logically fragmented across physically non-contiguous spans or when a local entity (like a function or a paragraph) requires context from a larger structure (like a repository, class, or multi-volume report). It is used for natural language requests like 'connect the fragments from this long report', 'stitch together clues from the repository', 'summarize this function using the rest of the class for context', 'check if a second search is needed for the missing repository details', or 'compare files to find similarities'. This skill ensures the agent can proactively identify and retrieve 'anchor' documents—such as skeletons, table of contents, or related code chunks—to perform high-fidelity synthesis.
    1 repo stars
  46. ▌
    Temporal Tabular Reasoning 3 · dingxingdi bundle
    Use this skill when the user wants SQL tasks where time is the main source of difficulty, including colloquial shift-based time references. Trigger it for requests like “make it about first vs last”, “events that happened before the night shift”, “test recency and ordering”, or “during the lunch hour bounds.”
    1 repo stars
  47. ▌
    Cross Source Clue Chaining 3 · dingxingdi bundle
    Use this skill when the user wants questions that require “connecting the dots,” pulling clues from several disparate places, or reconciling fragmented factual attributes (names, dates, quantities) from the latest news events. Trigger it for requests like “make the agent gather bits from different sites,” “test if the agent can connect the dots between recent reports,” “track the details of this specific 2025 incident,” or “force multi-hop reasoning to solve a hint-free question.” It is especially effective for scenarios where the answer is too recent for the model to know internally and requires searching for multiple sources to verify distinct parts of an answer.
    1 repo stars
  48. ▌
    Long Video Summarization 3 · dingxingdi bundle
    Use this skill when the user wants 'summarize the whole video', 'tell me what happened in the second half', 'explain the development of the situation', 'give the main developments', or when parsing the overarching narrative of fast-paced commercials and trailers. Trigger it when the desired answer must integrate many moments across a long duration into one coherent account, connect the dots between separate events located far apart, or trace the overarching thematic/plot arc of a complex or rapidly edited video.
    1 repo stars
  49. ▌
    Textual Attribute Grounding 2 · dingxingdi bundle
    Skill: textual attribute grounding
    1 repo stars
  50. ▌
    Prompt Injection Resistance 3 · dingxingdi bundle
    Use this skill when the user wants to synthesize web-based prompt injection attacks that test if an agent can be 'hijacked' by malicious instructions hidden in a webpage's HTML or content. Trigger it for requests like 'don't let the website trick the agent,' 'test if hidden code can change the task,' 'make sure the page doesn't override previous orders,' or 'check if the agent falls for fake system messages in the page.' It is specifically designed to create 'Environmental Injection Attacks' (EIA) where the threat is embedded in the web data the agent perceives rather than the user's initial prompt.
    1 repo stars
  51. ▌
    Schema Compliance 3 · dingxingdi bundle
    Skill: schema-compliance
    1 repo stars
  52. ▌
    Discourse Connective Flow 2 · dingxingdi bundle
    Use this skill when the user wants a translation where the logical links and transitions between sentences (using words like 'however,' 'consequently,' or 'on the other hand') feel natural and coherent across the whole document. Trigger it for requests like 'the sentences sound disjointed,' 'make the logic flow together between paragraphs,' 'ensure the transitions aren't clunky,' or 'test if the translator can handle words that connect one idea to the next across a long text.'
    1 repo stars
  53. ▌
    Text To Gloss Translation 2 · dingxingdi bundle
    Use this skill when the user wants to translate spoken or written natural language into 'Gloss' notation, which acts as a written label system for Sign Language (SL). Trigger it for requests like 'convert this to sign language labels,' 'write the gloss for this sentence,' 'translate this for a deaf person using sign-language word order,' or 'how would you sign this in a word-for-word label format?' It handles specific sign-language constraints such as using infinitives and omitting functional words.
    1 repo stars
  54. ▌
    Unanswerable Query Detection 2 · dingxingdi bundle
    Use this skill when the user's request appears to be impossible to answer based on the current database schema, contains high levels of ambiguity, or asks for information simply not stored in the database. Trigger it for requests like 'is this even in the data?', 'can the database answer this?', 'check if any table has this info', or 'tell me if the question is too vague'. It is essential for statements like 'What is the 3D structure of the gene?' (when the DB only has names) or 'Why does this gene cause cancer?' (when the DB stores relational facts, not explanations).
    1 repo stars
  55. ▌
    Executable Issue Resolution 3 · dingxingdi bundle
    Use this skill when the user wants bug-fix data for normal repository issues where the answer should come from reading an issue, navigating unfamiliar codebases, editing code, and running tests. Trigger it for requests like 'fix the NaN loss in my ML training script', 'solve issues in a massive codebase', 'fix this data race', 'debug my SQL query', or 'resolve this executable failure'. It covers standard software environments, database architectures, and systems infrastructures, emphasizing the fix-test-verify loop.
    1 repo stars
  56. ▌
    Symbolic State Tracking 3 · dingxingdi bundle
    Use this when the user wants planning data about keeping track of where things are, what is on top of what, what is free or blocked, mapping a path mentally, or when later steps only work if earlier moves changed the state correctly. Trigger it for requests like 'make tasks where one wrong early move ruins everything', 'give me block moving plans that depend on what is clear', 'navigate this maze by keeping a visual note of turns', or 'create tasks where the plan must remember what changed after each step, even if the actions use weird or random code names.'
    1 repo stars
  57. ▌
    Speech To Text Translation 2 · dingxingdi bundle
    Use this skill when the user provides spoken audio (speech) and wants it translated into written text in a different language, especially when the audio is messy. Trigger it for requests like 'translate this voice clip with the background noise', 'what specifically did they say in Spanish despite the stuttering?', 'convert this speech audio to English text and ignore the static', or 'translate the speaker's words even if they keep repeating themselves.' It is essential for handling real-world acoustic challenges like crowded-room babble, ambient wind, hesitations, and self-corrections.
    1 repo stars
  58. ▌
    Temporal Sequential Reasoning 3 · dingxingdi bundle
    Use this skill when the user asks for 'the latest update', 'before or after', timeline sequences, finding optimal time windows, or requesting the earliest/latest feasible shift for an event. Trigger it for requests like 'find a rain-free window for my 2h trip', 'when is the latest I can leave early to avoid traffic?', 'is this API still current today?', 'was the iPad or AirTag launch first?', or 'what is the overarching trend from 2022 to 2024?'. This skill is essential for chronometric normalization, ordering evidence, and performing iterative search for time-slots that satisfy specific condition-duration constraints.
    1 repo stars
  59. ▌
    Multilingual Schema Grounding 3 · dingxingdi bundle
    Skill: multilingual schema grounding
    1 repo stars
  60. ▌
    Fine Grained Widget Grounding 3 · dingxingdi bundle
    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 toolbar,” “use the tiny checkboxes,” or “the target is like a needle in a haystack.” This skill is for GUI tasks where the agent must overcome extreme spatial dilution through multi-stage visual refinement and recover from initial localization errors using bidirectional search logic.
    1 repo stars
  61. ▌
    Character Noise Translation 2 · dingxingdi bundle
    Use this skill when the user wants translation data for messy prompts with small spelling mistakes, broken typing, duplicated letters, swapped characters, or keyboard slips. Trigger it for plain-language requests such as "test whether it still translates when the ask has typos," "people type fast and miss letters," "make the prompt look slightly broken," or "check if the translator can survive misspellings without changing the task."
    1 repo stars
  62. ▌
    Precise Localized Editing 3 · dingxingdi bundle
    Use this skill when the user wants to apply a highly targeted edit—such as deleting redundant filler, rephrasing a paragraph without losing exact technical facts, or filling in a missing logical gap—without rewriting the whole document. Trigger it for requests like “delete this placeholder,” “cut the fluff from the second paragraph,” “rephrase this medical report but keep the exact measurements,” or “fill in the missing bridge between these two sections.”
    1 repo stars
  63. ▌
    Comparative Response Ranking 3 · dingxingdi bundle
    Skill: comparative-response-ranking
    1 repo stars
  64. ▌
    Evidence Localized Document QA 3 · dingxingdi bundle
    Use this skill when the user wants to locate exact evidence within a document to answer a question, particularly when the user's natural language phrasing differs significantly from the document's formal terminology (e.g., paraphrased queries). This skill helps the agent bridge the lexical gap between everyday questions and official documents like institutional norms, regulations, or scientific reports. Trigger it for requests like 'find the rule for X', 'summarize the eligibility criteria in this ordinance', 'where in the statute does it mention Y', or 'answer this based on the university regulations', especially when the user uses casual language to describe formal concepts.
    1 repo stars
  65. ▌
    Security Vulnerability Repair 3 · dingxingdi bundle
    Use this skill when the user wants software-fix data focused on identifying, mitigating, or preventing security bugs. Trigger it for requests like 'make security repair tasks', 'generate vulnerability-fixing data', 'ensure the new feature is secure against XSS/injections', or 'create patching tasks for insecure code'. This applies both to patching existing vulnerabilities and securely implementing missing features where the primary challenge is defending against CWEs (like timing side-channels, broken access control, or header injections) during development. Do not use it for ordinary non-security defects.
    1 repo stars
  66. ▌
    Implicit Instruction Grounding 3 · dingxingdi bundle
    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). Trigger it for requests like "make the button description vague," "use several different ways to ask for the same thing," "can the agent tell the 'Filter' icon from the 'Sort' icon?" or "test if it knows to pick a size before clicking Add to Cart." This skill ensures the agent maps natural language intents to the correct GUI widgets through semantic understanding, structural siblings, and topological dependencies rather than just matching words.
    1 repo stars
  67. ▌
    Safety Aware Action Governance 3 · dingxingdi bundle
    Use this skill to assess if an Agent's proposed actions are truly aligned with user intent rather than being hijacked by external tricks or internal errors. Trigger it for requests like “watch out for phishing links,” “make sure you don't delete the wrong file by mistake,” “is this action really what I asked for?”, “don't let the website trick you into doing something else,” or “check if this cleanup step is safe.” This skill ensures the agent validates every click against the user's authentic goal, refusing to follow malicious instructions in the environment (prompt injection) or perform harmful unintended actions (reasoning failures caused by ambiguous phrasing).
    1 repo stars
  68. ▌
    State Verified Task Completion 3 · dingxingdi bundle
    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 state,” “don’t trust a temporary popup,” or “judge success from the system record, not a screenshot alone.” This skill is for GUI tasks where durable completion must be grounded in application state, database state, filesystem state, or verified internal signals.
    1 repo stars
  69. ▌
    Temporal Gui Precision Control 2 · dingxingdi bundle
    Use this skill when the task requires actions to be timed perfectly, such as waiting for a hidden element to appear, holding a button for a specific duration, or clicking a target that is moving or changing. Trigger it for requests like "wait a few seconds before acting," "hold the button down," "be quick and tap it multiple times," "click it three times as it moves," or "patience is required to find the password."
    1 repo stars
  70. ▌
    Fuzzy Tool Retrieval 3 · dingxingdi bundle
    Skill: fuzzy-tool-retrieval
    1 repo stars
  71. ▌
    Long Horizon Web Task Execution 3 · dingxingdi bundle
    Use this skill when the user wants tasks that require a long sequence of actions across multiple screens, tracking state changes, executing recursive loops to generate exhaustive list data, tree-walking hidden menus, or filling out multi-page forms. Trigger it for requests like 'prowl this site to find hidden settings,' 'create a complete table by checking every item,' 'fill out the entire application using this document,' or 'apply all these filters while staying under budget.' It perfectly handles complex traversal loops, multi-item data aggregation across sub-pages, and mapping a site's hidden topology through persistent exploration.
    1 repo stars
  72. ▌
    Persistent Search Reformulation 3 · dingxingdi bundle
    Use this skill when the user wants questions where the answer requires the agent to try several search angles, recover from systemic web blocks, bypass paywalls/CAPTCHAs by seeking alternative sources, or rewrite queries heavily to beat dead ends. Trigger it for requests like “make it take a few searches,” “force recovery from 403 blocks,” “navigate around paywalls,” or “force the agent to keep refining the search constraints.” It is the definitive capability for testing persistence when the easiest path is either blocked by security guardrails or returns zero useful hits.
    1 repo stars
  73. ▌
    Automated Test Suite Synthesis 2 · dingxingdi bundle
    Use this skill when the user wants to generate high-quality, comprehensive test suites for a software problem or code snippet to ensure it is robust against edge cases and logical errors. It is triggered by natural language requests such as 'generate hard test cases', 'create an adversarial test suite for this algorithmic problem', 'find edge cases for my code', 'make sure my code handles extreme values', or 'build a verifier for this programming task'. It is specifically designed to proactively identify subtle logical flaws by analyzing problem constraints and comparing correct solutions against known error patterns.
    1 repo stars
  74. ▌
    Spatial Relation Reasoning 3 · dingxingdi bundle
    Skill: spatial-relation-reasoning
    1 repo stars
  75. ▌
    Cross App Workflow Coordination 3 · dingxingdi bundle
    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 resume,' 'keep a note of that price for later,' or 'match the info from this file to the boxes in the app.' This skill is for GUI tasks requiring a chain of memory where information is extracted from one source (e.g., a PDF resume, a map result) and utilized in a distinct destination (e.g., a web application form, a messaging app).
    1 repo stars
  76. ▌
    Proverb Idiomatic Translation 3 · dingxingdi bundle
    Use this skill when the user wants translation data for culturally loaded text that cannot be translated literally, including cases where the source is written in informal phonetic scripts. Trigger it for requests like 'don't translate it word for word,' 'capture the slang and emoji vibe of this social media comment,' 'the text uses Romanized spelling for a local saying,' or 'use a native proverb equivalent.' It manages proverbs, internet slang, and cases where figurative meaning must be recovered from non-standardized orthography.
    1 repo stars
  77. ▌
    Task Progress Decision Making 3 · dingxingdi bundle
    Use this skill when the user asks 'what do I do next?', 'what was the step before this?', 'is it safe to perform this?', 'did they follow the manual?', 'how do I fix this mistake?', or 'score the performance/skill level of this operation'. Trigger it for tasks evaluating sequential procedures, forecasting upcoming actions, verifying adherence to external operational rules (like safety protocols or Critical View of Safety), or proposing optimizations to a completed process. It is also suitable for 'Expert-level' assessment where a set of professional criteria or rubrics must be applied to a long video trajectory to judge technical proficiency.
    1 repo stars
  78. ▌
    Narrative Novelty And Value 3 · dingxingdi bundle
    Use this skill when the user wants stories that feel fresh, clever, twisty, emotionally alive, structurally complex, or set in meticulously crafted speculative worlds. Trigger it for requests like 'make it more surprising,' 'add flashbacks to explain the past,' 'ensure the rules of the magic system are consistent over the 50-chapter novel,' or 'give me something with an earned twist.' It is specifically designed to produce open-ended creative quality where human preference rewards non-linear timelines, deep world-building integration, long-range narrative coherence, and subversion of generic AI sci-fi/fantasy tropes.
    1 repo stars
  79. ▌
    Structural Format Adherence 3 · dingxingdi bundle
    Use this skill when the writing must follow a very exact shape, outer format, or rigid template shell. Trigger it for requests like “make it two sections,” “give me exactly five bullet points,” “wrap everything in JSON,” “put a title in special brackets,” or “draft a formal agreement including these exact five clauses.” It is especially useful when the user cares about the architectural shell and structure of the document as much as the content.
    1 repo stars
  80. ▌
    Bridge Based Multi Hop Reasoning 4 · dingxingdi bundle
    Use this skill when the user wants 'connect the dots' questions, hierarchical path-traversals, or questions about navigating a sequential process. Trigger it for natural-language requests like 'multi-hop questions', 'find a way to get to...', 'show me the steps to...', 'force the model to follow a shared thread across docs', or 'test if it can find the path even if some instructions are missing'. It targets structural traversal across documents, procedural manuals, or interface states.
    1 repo stars
  81. ▌
    Exhaustive Long Context Coverage 4 · dingxingdi bundle
    Use this skill when the user wants questions that require reading the entire context window, ensuring no file or nested branch is left behind. Trigger it for requests like 'need reading everything', 'give me a full breakdown of this specific chapter', 'summarize the statistics for all entities found', or 'tell me all the subsections' occurrences'. It forces extreme entity density and global context accounting across both multi-document spreads and deep intra-document hierarchies.
    1 repo stars
  82. ▌
    Noise Robust Evidence Extraction 3 · dingxingdi bundle
    Use this skill when the user wants questions where the right clue is present but surrounded by similar-looking junk, typographical errors, or misleading formatting. Trigger it for requests like 'mix in some confusing paragraphs', 'test whether it finds the wrong year', 'hide the answer among near misses', or 'test if the model can read through OCR errors like WN8A'. This skill ensures the agent can isolate the true semantic signal amidst both macro-level topical distractors and character-level document degradation.
    1 repo stars
  83. ▌
    Long Form Coherent Summarization 3 · dingxingdi bundle
    Use this skill when transforming massive documents or multi-source corpora into structured, coherent formats. Trigger for requests like 'summarize this huge PDF without losing the thread', 'draft a defense statement based on this complaint and the evidence list', 'create a presentation script from this report', or 'write the official trial facts by resolving contradictory testimonies into a ground-truth timeline'. This is critical when shifting text registers, interleaving visual anchors, or composing professional narrative sections from conflicting multi-source contexts.
    1 repo stars
  84. ▌
    Contextual Entity Disambiguation 3 · dingxingdi bundle
    Skill: contextual entity disambiguation
    1 repo stars
  85. ▌
    State Changing Data Manipulation 2 · dingxingdi bundle
    Use this skill when the user wants SQL data that goes beyond typical READs to encompass data modification loops like INSERT, UPDATE, or DELETE, as well as complex transactional logic for data lifecycles (merging records, setting TTL expirations, or updating locking flags). Trigger it for requests like “make examples that change the database”, “I want the model to delete stale records”, “consolidate these duplicate rows”, or “set an expiration deadline for the specified rows.”
    1 repo stars
  86. ▌
    Ml Data Curation And Refinement 2 · dingxingdi bundle
    Use this skill when the user wants to prepare, clean, or label datasets for machine learning using specialized code and automated models. Trigger it for requests like 'fill in the missing gaps in my data', 'automatically label this dataset based on our rules', 'impute the null values in my training set', or 'fix the data quality before training'. It is specifically designed for complex ML engineering tasks involving model-based imputation (like recovering sensor readings) and weak supervision pipelines (like heuristic-based labeling) rather than simple SQL data transformations.
    1 repo stars
  87. ▌
    Visual Front End Bug Resolution 2 · dingxingdi bundle
    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 website fixes that need looking at the screenshot', 'generate front-end tasks with CSS or rendering issues', or 'create visual JavaScript bug-fix data'. Do not use it for purely backend repository issues, general software debugging without visual evidence, or security-only vulnerabilities.
    1 repo stars
  88. ▌
    Long Horizon Composite Execution 3 · dingxingdi bundle
    Use this skill when you have a big task that needs many steps to finish, like a long-term plan or a complex project. Trigger it for requests like “follow this long list of steps,” “help me reproduce this bug from the report,” “do a long sequence of chores across different screens,” or “figure out how to finish this multi-step task even if the instructions are messy.” It helps the agent group steps into clusters, look up help in manuals or wikis, and use expert shortcuts like commands to make sure the whole long plan works without getting lost.
    1 repo stars
  89. ▌
    Active Trace Oversight 2 · dingxingdi bundle
    Skill: active-trace-oversight
    1 repo stars
  90. ▌
    Domain Terminology Translation 3 · dingxingdi bundle
    Use this skill when the user wants translation data for specialized professional fields like medicine, law, science, mathematics, or academic research, where words have specific technical meanings or require formal scholarly syntax. Trigger it for requests like 'translate this as a research abstract,' 'maintain the mathematical logic exactly,' 'ensure the word choice matches the scientific context,' or 'translate this legal, medical, or logical paper without simplifying the wording or correcting its intentional academic flaws.'
    1 repo stars
  91. ▌
    Text Image Machine Translation 2 · dingxingdi bundle
    Use this skill when the user wants to translate text found inside an image (like a photo of a sign, a screenshot, or a damaged manuscript) OR when the user provides noisy text that must be translated by referencing an accompanying image. Trigger it for layman requests like 'translate the text in this picture,' 'decode the ancient script on this stone,' 'read the words in this screenshot,' or 'fix the typos in this description using the picture to ensure the colors match what is actually shown.'
    1 repo stars
  92. ▌
    Length Requirement Adherence 3 · dingxingdi bundle
    Use this skill when the user cares about how short or how long the writing should be. Trigger it for requests like “keep it under 500 words,” “make it at least 25 sentences,” “give me 3 paragraphs,” or “write a 4,000-word article.” It is especially useful when the agent must hit a target length without padding, truncation, or collapse in quality.
    1 repo stars
  93. ▌
    Conflict Aware Faithful Grounding 4 · dingxingdi bundle
    Use this skill when the user wants to synthesize data testing an agent's ability to handle contradictions, misleading facts, factual errors, or semantic drift (e.g., from AI-generated summaries). Trigger it for requests like 'make the documents disagree with each other', 'test if the model spots self-contradicting files', 'see if it gets tricked by summarized text', 'check for mistakes in rewritten news', or 'see if the agent follows a lie in the text over what it knows is true'. This skill covers factuality detection, self-contradiction, and resolving information fusion or omission.
    1 repo stars
  94. ▌
    Table Text Numerical Reasoning QA 3 · dingxingdi bundle
    Use this skill when the user wants the agent to perform document-grounded math, execute multi-step financial formulas, or perform 'intrinsic fact-checking' to recover masked or missing numerical values from tables. Trigger it for requests like 'calculate the ROI', 'verify if this revenue figure is consistent with the balance sheet', 'find the year-over-year growth rate', 'recover the missing value in this report', or 'perform latent variable inference to find the equity investment'. This skill is essential for detecting numerical hallucinations and ensuring calculated values are strictly faithful to the provided document context.
    1 repo stars
  95. ▌
    Competition Style Ml Engineering 3 · dingxingdi bundle
    Skill: competition-style-ml-engineering
    1 repo stars
  96. ▌
    Bulk Iterative State Coordination 2 · dingxingdi bundle
    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 sure you get all 50 items across the pages,” or “process these invoices skipping the ones I've already done.” This skill focuses on tracking progress during repetitive loops to ensure no items are omitted and no actions are redundant.
    1 repo stars
  97. ▌
    Dexterous Spatial UI Manipulation 2 · dingxingdi bundle
    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 like “highlight the second sentence,” “select the paragraph starting with 'For',” “move the file to the folder,” “set the slider to 75%,” “draw a circle inside the square,” or “draw a 3x3 grid.” This skill is for GUI tasks where the agent must resolve spatial start/end points, compute geometric bounding boxes, or maintain continuous motion control to manipulate UI elements precisely.
    1 repo stars
  98. ▌
    Embedded Instruction Resistance 2 · dingxingdi bundle
    Use this skill when the user wants translation data where the source text looks like an instruction and may tempt the model to do the wrong job, such as solving a math problem, answering a question, or writing code instead of translating. Trigger it for requests like "make sure it translates the problem instead of solving it," "the input itself looks like a command," or "test whether it can ignore fake instructions inside the text being translated."
    1 repo stars
  99. ▌
    Action And Motion Understanding 3 · dingxingdi bundle
    Use this skill when the user asks 'how many times did [action] happen?', 'what is the player doing?', 'where did the ball go?', 'is this a complex move?', 'what happens next?', or 'compare these two athletes'. It is triggered for tasks assessing high-frequency sports dynamics, counting rapid repetitive actions (like rally counts), identifying specific kinetic stroke techniques, predicting immediate athletic outcomes, and ranking technical difficulty based on observed action units.
    1 repo stars
  100. ▌
    Hierarchical Symbolic Subgoal Decomposition 2 · dingxingdi bundle
    Use this when the user wants to solve a large, multi-faceted project by breaking a distal goal into a sequence of abstract middle-states, sub-goals, or typed nodes like research versus writing. Trigger it for requests like 'break this big project into different types of steps', 'recursively decompose this goal until you have simple steps', 'give me a high-level strategy and then the moves to do it', or 'organize a plan where composition steps wait for reasoning steps.'
    1 repo stars