SuperAPI AI DirectoryFind an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-01 00:15
14,525 results
Synthesize the findings of multiple research agents into a coherent, structured research report. Resolve contradictions, extract consensus, and create a unified narrative. Use this skill when multiple research agents have completed their research, findings need to be combined into a unified report, and contradictions exist among the findings.
Comprehensive weekend city travel investigation skill for Chinese cities. Use this skill PROACTIVELY whenever the user wants to research a city for weekend or…
Writer voice profile — an MBTI-inspired adaptive assessment that captures a person's cross-genre writing taste and style preferences. Use when the user wants…
Refactoring existing articles or drafts using a code-refactoring metaphor — extract information units (facts, claims, examples, metaphors) into a neutral…
Writer voice profile — an MBTI-inspired adaptive assessment that captures a person's cross-genre writing taste and style preferences. Use when the user wants…
Professional Background Research for a specific real, living person using public sources. Use for identity and professional-background questions, meeting or…
Generate platform-specific content drafts conditioned on your persona
Evaluate content drafts with virtual followers and get TOP 5 recommendations
Scan trending topics in your domains and get content recommendations
Audit where one fact lives in many places and report the canonical source of truth plus a consolidation plan — read-only. Use when the same fact, spec,…
By default, write or rewrite clear, unambiguous technical descriptions, operating steps, error messages, technical reports, and tool descriptions in Chinese. Preserve terminology, conditions, risks, strength of obligation, and facts; suitable for tasks that simplify technical output, eliminate ambiguity, or specify asd-ste100-zh. Not for creative or marketing copy, and does not provide ASD-STE100 Chinese compliance certification.
Use due-diligence-style search to find legally authorized ebook sources and acquisition paths for a specified book, prioritizing confirmation of Chinese translations, non-scanned electronic editions, GitHub/GitBook repositories with explicit authorization, PDF, EPUB, MOBI, Kindle, Markdown, online reading, and library borrowing. Trigger when the user uses /find-ebook or…
Legacy compatibility entry for faithfully reposting official account articles; it no longer executes independently or owns rules, and new tasks are uniformly routed to the repost pipeline of lov-article-creator. Use when, and only when, a legacy task explicitly names this Skill; do not discover for…
TGW prompt optimization algorithm Skill. Used to streamline an existing complete executable prompt, and without changing the original intent or capability boundaries, compress redundant rules, repeated expressions, defensive instructions, and low-value examples in the order of "question the requirements, delete, simplify, accelerate, templatize, report." Trigger methods: prompt optimization, prompt streamlining, streamline prompt, compress prompt, prompt subtraction, optimization algorithm, make this prompt shorter, /TGW-prompt…
Draft a blog post from ideas and resources. Use when users want to write a blog post, create content from research, or draft articles. Guides through research,…
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision…
Evidence-driven architecture research for understanding real systems and making technical decisions. Use when doing architecture landscape studies,…
Apply MCAF documentation guidance for docs structure, navigation, source-of-truth placement, and writing quality. Use when a repo’s docs are missing, stale,…
Search markdown knowledge bases, notes, and documentation using QMD. Use when users ask to search notes, find documents, or look up information.
Have a sub-agent with no context read the finished Japanese explanation, and find and fix the places that cannot be read without context using six types (referent not determined, renaming and coined terms, borrowed words, negation of what no one said, restating in the conclusion, drift in the scope of the claim). Failures that the writer cannot see because they have the context, and that are first discovered through someone else's review, are...
Adjust line breaks and blank lines in Japanese explanatory text. Break lines for each sentence (done mechanically), and insert blank lines for each group of sentences that shares one role (a judgment call). Do not change the content of sentences; handle only how the fixed sentences are arranged. Use in the following situations: - Japanese explanations meant for people to read (READMEs, commentaries, reports, Discord or Qiita…
Guide for writing idiomatic, maintainable Makefiles following modern best practices. Enforces safety headers (SHELL, .SHELLFLAGS, .DELETE_ON_ERROR),…
Use the user's already signed-in official ChatGPT website account, especially GPT-5.5 Pro / ChatGPT Pro, to perform product research, market research,…
Batch download WeChat public-account article bodies, historical article lists, original-article filtering, history counting conventions, read counts, likes/shares and other metrics, comments, and comment replies. Use when the user asks to batch fetch mp.weixin.qq.com articles, export WeChat public-account history,…