471 个 · 按相关度排序
Review newly added comments, docstrings, and changelog entries so future readers can understand the current code. Revise development history, redundant explanations, and unclear shorthand while preserving constraints that the code cannot explain on its own.
中文简介正在准备中。当前显示英语简介。
Analyze a long novel through its opening chapters, chapter summaries, plot causality, reader emotions, pacing, relationships, settings, and prose style. Produce reusable writing references, continue partial analyses, or fill gaps in existing reports using available evidence.
中文简介正在准备中。当前显示英语简介。
Draft and edit Chinese or English prose, technical instructions, and product copy. Preserve meaning and the author's voice while removing repetition and formulaic AI wording, with support for release notes, social posts, and localization reviews.
中文简介正在准备中。当前显示英语简介。
Edit headlines, marketing copy, and product text into clear, concrete prose. Provides examples for removing empty claims, repetitive phrasing, and excessive formatting while preserving the writer’s voice and avoiding invented facts.
中文简介正在准备中。当前显示英语简介。
Polish academic English or translate Chinese drafts using Nature and Nature Communications writing patterns. Review section logic before refining sentences, preserve the author's evidence and claims, and provide revised prose with brief notes explaining the main changes.
中文简介正在准备中。当前显示英语简介。
Draft or restructure scientific manuscripts using Nature-style argument patterns, starting from supplied results, figures, notes, or Chinese drafts. It organizes sections, connects claims to evidence, and identifies missing inputs while keeping conclusions within the research's demonstrated limits.
中文简介正在准备中。当前显示英语简介。
Draft and revise research papers, thesis sections, and responses to reviewers, primarily in Chinese or in English on request. Organize arguments around supplied evidence while preserving formulas, citations, terminology, and measured results.
中文简介正在准备中。当前显示英语简介。
Review English prose for formulaic phrases and other patterns associated with AI writing, then make targeted edits while preserving meaning and voice. Choose findings only, a rewritten version, or direct edits to a prose file.
中文简介正在准备中。当前显示英语简介。
Refine AI-assisted academic drafts into natural scholarly prose while preserving citations, statistics, and methodological details. Choose how extensively to revise and which sections to edit, then review a report comparing the original and revised text.
中文简介正在准备中。当前显示英语简介。
Proofread academic manuscripts in LaTeX, Markdown, or plain text for typos, grammar, and unclear wording. Review proposed changes one at a time before applying them, while preserving arguments, citations, equations, and code.
中文简介正在准备中。当前显示英语简介。
Edit medical research manuscripts for clearer, more natural academic prose. Address inflated claims, vague wording, inconsistent terminology, and repetitive sentence patterns while preserving scientific meaning, supplied data, appropriate caution, and the author's established writing style.
中文简介正在准备中。当前显示英语简介。
Proofread applied microeconomics manuscripts across prose, equations, tables, notes, and references. The workflow combines specialized reviews into a prioritized report with exact locations, suggested corrections, consistency checks, and items requiring author verification.
中文简介正在准备中。当前显示英语简介。
Draft a pull request description that explains the problem, implementation, trade-offs, and testing. It combines source-backed reasoning, validated Mermaid diagrams, and actual validation output into one Markdown file reviewers can assess on its own.
中文简介正在准备中。当前显示英语简介。
Review a branch diff for tests that do not protect meaningful behavior, prose that adds no useful information, and unnecessary code structures. When editing is authorized, simplify the changes and verify them with focused tests.
中文简介正在准备中。当前显示英语简介。
Use when polishing the prose of an Accounting, Organizations and Society (AOS) manuscript — sustained argumentative writing that carries theory and evidence together, a self-contained abstract, disciplined length despite the absence of a hard cap, and full anonymization for double-anonymized review. Polishes prose; it does not run the submission preflight (aos-submission).
中文简介正在准备中。当前显示原文说明。
Use when the user mentions GPT Image 2.0 or GPT Image 2.5, gpt-image-2, gpt-image-2.5, gpt_image_2_5, GPT-Image-2 prompts, the Flare / Sunburst variants, a transparent-background image, or wants to generate an image with GPT Image 2.0 or 2.5. Covers when to prefer GPT Image 2.5 over 2.0 (transparent background, xhigh/max quality, extra aspect ratios — from platform and OpenAI facts), the CLI-vs-MCP disagreement on gpt_image_2, the three-format prompt taxonomy (Format A structured JSON for UI mockups and layout-dense images; Format B dense cinematic prose for single-subject scenes; Format C auto-derive meta-prompt for theme-only concepts), per-format craft patterns, output conventions, the 6-item pre-delivery checklist, and cross-surface workflow context (companion static-ads-workflow.md for ad recreation; higgsfield-marketing-studio cross-surface-workflow.md §3 for ms_image / DTC Ads Higgsfield-native alternative).
中文简介正在准备中。当前显示原文说明。
Write and read the between-session handoff file so a fresh agent with no memory can pick up where the last one stopped without re-deriving context. Structured prose, not JSON — the model writes prose better.
中文简介正在准备中。当前显示原文说明。
One-shot efficiency audit of a file, diff, or whole repo across BOTH axes at once: over-engineered code (reinvented stdlib, needless abstractions, speculative config) AND bloated prose (verbose comments, padded docstrings, redundant doc sections). Neither a pure code-minimizer nor a pure prose compressor does both in one pass. That's the point. Ranked report, biggest saving first; changes nothing. Use when the user says "chisle audit", "/chisle-audit", "audit this for bloat", "what can I cut", "review this PR for over-engineering and verbosity".
中文简介正在准备中。当前显示原文说明。
Reviews lyrics and prose for AI-written patterns (abstract noun stacking, over-explained metaphors, cliche escalation, missing idiosyncrasy, prose AI tells). Advisory Warning/Info severity — flags issues, does not block or rewrite. Use when reviewing lyrics for authenticity or before generation to catch AI-sounding language.
中文简介正在准备中。当前显示原文说明。
Decision rubric for when an LM agent should write-and-run code (Program-of-Thought / code interpreter) versus reason in natural language: classify each step as deterministic- computable (emit + execute code, feed the result back) vs judgment (stay in prose). Use when designing or debugging an agent step that does arithmetic/parsing/data transforms, when prose reasoning hallucinates a computation (under-coding), or when a sandbox round- trip is wasted on a judgment task (over-coding). Search keywords: code interpreter, agent does math wrong, calculator hallucination, when to run code vs reason, program of thought, PoT, tool vs reasoning.
中文简介正在准备中。当前显示原文说明。
Polish, translate, diagnose, and restructure technical manuscript text into IEEE-style academic English using routed failure-mode guidance. Use for IEEE abstracts, introductions, related work, methods, experiments, conclusions, figure captions, rebuttals, Chinese-to-English technical writing, AI-like or template-like academic prose, and engineering prose that needs clearer problem logic, contribution framing, method rationale, evidence discipline, natural author voice, or reviewer-ready wording.
中文简介正在准备中。当前显示原文说明。
Runs parallel prose and craft review agents against a voice profile. Use when checking generated content for AI patterns and voice drift before publishing.
中文简介正在准备中。当前显示原文说明。
This skill should be used when the user asks to "line edit", "edit my prose", "polish this chapter", "tighten the prose", "improve the sentences", "copyedit", "proofread", "proof pass", "check grammar and punctuation", "dialogue punctuation", "make the voices distinct", "everyone sounds the same", "read it aloud", "read-aloud pass", "text to speech", or wants a sentence-level quality pass on drafted chapters that preserves the author's voice. NOT for creating the style sheet, recording character voices, or checking voice consistency (use voice-style).
中文简介正在准备中。当前显示原文说明。
This skill should be used when the user asks to "create a style sheet", "style guide", "house style", "keep the voice consistent", "voice drift", "British or American spelling", "character voices", "lint the prose", "prose check", "filter words", "said-bookisms", "overused words", "repeated phrases", "similar character names", "voice fingerprints", or wants to record and enforce the voice and surface conventions of a story project. NOT for rewriting dialogue to make the voices distinct when everyone sounds the same (use line-editing), or a character's profile or arc (use character-management).
中文简介正在准备中。当前显示原文说明。