Loading...
Loading...
Found 111 Skills
AI SDLC change-impact and lifecycle recovery workflow. Use when a requirement, acceptance criterion, decision, API contract, risk assumption, or other traced source changed after downstream artifacts were created and an AI assistant must identify stale artifacts, affected lifecycle stages, and evidence-backed reopen or revalidation actions without silently rewriting authoritative state. Supports `--quick-flow` for focused trace scanning and `--full-flow` for strict state and source-evidence gates.
Clean and finalize authorized natural-language text intended for readers by auditing suspicious invisible Unicode and rewriting prose while preserving facts and meaning. Use in Cursor when the user asks to clean, humanize, polish, or finalize articles, manuscripts, reports, documentation, emails, product copy, UI text, Markdown, or HTML prose, or when an installed Cursor Rule explicitly requires this workflow. Do not use for code-only tasks or undisclosed authorship evasion; leave code, commands, identifiers, paths, APIs, formulas, citations, required disclosures, and verbatim quotations unchanged.
Design, review, and improve Claude/Codex skills based on Anthropic's "The Complete Guide to Building Skills for Claude". Use when creating a new skill, rewriting SKILL.md frontmatter and workflows, fixing under-triggering or over-triggering, designing scripts/references/assets, building test cases, or preparing a skill for upload/distribution.
Complete Git expertise system for ALL git operations. PROACTIVELY activate for: (1) ANY Git task (basic/advanced/dangerous), (2) Repository management, (3) Branch strategies and workflows, (4) Conflict resolution, (5) History rewriting/recovery, (6) Platform-specific operations (GitHub/Azure DevOps/Bitbucket), (7) Advanced commands (rebase/cherry-pick/filter-repo). Provides: complete Git command reference, safety guardrails for destructive operations, platform best practices, workflow strategies, reflog recovery techniques, and expert guidance for even the most risky operations. Always asks user preference for automatic commits vs manual control.
Skill for in-depth rewriting of Chinese articles. Must be triggered when users request "rewrite", "rephrase", "polish and restructure", "expand", "translate and rewrite", "adapt to WeChat Official Account/Zhihu style", "make this article more suitable for publication", or "optimize the expression or structure of this article". Supports three input types: inline text, file path, and URL; supports three modes: quick, standard, and publish; can supplement the latest information as needed and generate 5 title candidates. This skill should also be used even if users only say "revise this article", "translate into Chinese and rewrite", or "help me organize this into a publishable article".
Use when creating, rewriting, pruning, or reviewing `AGENTS.md` or `CLAUDE.md`, especially to remove repo summaries, stale rules, and other low-signal global instructions. Trigger when deciding what belongs in always-on agent files versus a task-specific skill.
Complete RAG and search engineering skill. Covers chunking strategies, hybrid retrieval (BM25 + vector), cross-encoder reranking, query rewriting, ranking pipelines, nDCG/MRR evaluation, and production search systems. Modern patterns for retrieval-augmented generation and semantic search.
This tool is designed for publishing HTML articles to WeChat Official Account drafts, especially when you need features like cover upload, automatic cover generation, body image URL replacement, CSS variable compatibility, or configuring draft metadata such as author and comment settings.
A skill for writing and revising Japanese business documents to make them easy to read and understand. It can be used for creating and proofreading business documents such as meeting minutes (including transcribing to minutes), research/analysis reports, internal guides/manuals, research notes, discussion papers, proposals, reports, emails, and slide outlines, as well as following instructions like 'write from the conclusion', 'clarify the argument', 'keep headings concise', and 'explain technical terms in an easy-to-understand way'. It also supports removing AI-like tones (direct, indirect, or colloquial feedback such as 'AI-like', 'unnatural', 'make it more natural Japanese', 'mechanical', 'make it sound human', 'monotonous', or phrasing like 'it would be possible to...', as well as cases where the document was said to be written by AI or suspected of being so), improving hard-to-read or unclear sentences (such as incorrect word order, long sentences, unclear meaning, incorrect comma placement, etc.), writing new note articles, blog posts, and essays (including requests to write from scratch on any topic), rewriting and polishing existing sentences, diagnosing and scoring AI-like tones (requests without rewriting, such as 'Did AI write this?', 'Score the AI-like tone', 'Judge how AI-like this is'), and requests to learn and profile one's own writing style (including requests to write in one's own style by reading past sentences). It also addresses readability principles such as removing forbidden words, avoiding monotonous rhythm, homogeneous paragraph structure, literal translation of English syntax, as well as word order, commas, one meaning per sentence, and the distance between subject and predicate. The structuring of technical documents or formatting of Markdown itself (such as one sentence per line, quote blocks, footnote notation, etc.) is not covered—this falls under another skill, and this skill specializes in the naturalness, readability, and comprehensibility of text.
Skill for Homepage Check-up and Profile Rewriting in *Xiaohongshu Operation Manual · AI Workbench*. Triggered when users want to optimize the first impression of their homepage, account profile, nickname, avatar description, pinned notes, sense of trust, and positioning expression. Inputs can include homepage screenshot descriptions, nicknames, profiles, pinned notes, account positioning, products/services, and target users. Outputs include homepage diagnosis, problem priority, profile rewriting, and pinned note suggestions. If users focus on asking about the conversion path from content to private messages, purchases, reservations, experiences, or transactions, use xiaohongshu-conversion-path.
Generate or remediate documentation with human-quality writing and style adherence. Use when creating new documentation, rewriting AI-generated content, or applying style profiles. Do not use for slop detection only (use slop-detector) or learning styles (use style-learner).
Audit, write, and improve developer documentation using Google's Developer Documentation Style Guide and Technical Writing courses. Use this skill for any documentation work, even when the user names no style guide: "audit our docs", "review this README", "write a README", "getting started guide", "how-to or tutorial", "API reference", "docstrings", "CLI help text", "changelog or release notes", "migration guide", or "our docs are confusing". Also use it when writing docs from code, rewriting a doc for clarity, fixing headings, procedures, or code samples, or enforcing consistent voice and terminology across a docs set — prefer it over editing documentation unaided. Covers reader and doc-type fit, second person and active voice, procedures, headings, lists and tables, code samples and placeholders, link text, notices, the word list, timeless docs, and accessibility. For code comments and naming, see clean-code. For marketing or landing-page copy, see storybrand-messaging.