SuperAPI AI DirectoryFind an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-22 00:14
13,937 results
Reverse-import an existing novel. Reverse-parse an already-written novel (work-in-progress or completed) into the standard project directory structure, compatible with the subsequent writing workflows of story-long-write / story-short-write; internally reuse story-long-analyze / story-short-analyze…
Long-form web fiction deconstruction. In-depth deconstruction of the golden three chapters, character design architecture, payoff design, and pacing control of hit long-form novels. Single deep-deconstruction pipeline: after running the golden three chapters (Stage 1), produce a quick preview report and ask whether to continue with the full deconstruction; upon confirmation, resume from Stage 2 with chapter-by-chapter summaries, aggregate analysis, setting relationships, and summary report, with all artifacts persisted to disk...
Long-form web novel writing. From outline to main text, assists the creation of Chinese long-form web novels, including worldbuilding, characters, genre contracts, plotline management, branch deduction, and author style distillation. Trigger methods: /story-long-write, /写长篇, "help me start a book", "write an outline", "branch deduction", "author style distillation", "switch writing method", "daily update", "continue writing", "keep writing", "revise chapter X", "rework", "rewrite chapter X".
Multi-perspective adversarial review. In full/lean mode, when reviewer agents are already deployed, spawn them in parallel; when agents are missing/abnormal or spawn fails, automatically degrade to solo, and when reference files are unreadable, use the built-in rubric fallback. Trigger methods: /story-review, /审查, "审查一下", "帮我审一下".
Web fiction writing toolset infrastructure deployment. Provides built-in adapters for Claude Code / OpenCode / Codex / ZCode / TRAE Code / WorkBuddy / CodeBuddy Code / OpenClaw / Reasonix; Web AI / general Agents can use skills +…
Short-form web fiction ranking scan. Analyze popular short-form data from platforms such as Zhihu Yanyan, Qimao, Heiyan, and Dianzhong to capture trending genres. Trigger methods: /story-short-scan, /short-form scan, "what's hot in short-form," "Zhihu story rankings."
Short-form web fiction writing. Assists short story creation, from conception to finished draft, focusing on emotional tension and pacing control. Trigger methods: /story-short-write, /write-short, "help me write a short story", "write a Yanyan story".
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser…
Authoring unified specification packages across Business/Development/Design teams via staged elaboration (L0 Vision, L1 Requirements, L2 Team Detail, L3…
Get the latest updates from followed YouTube creators/podcasts. List new videos from the past two days, including title, publish time, and a brief description. Trigger words: "get podcast updates", "what new podcasts are there recently", "YouTube updates", "podcast updates", "what new podcasts are there". Used for daily checking whether followed AI/tech podcasts have new content updates.
Professional WeChat Official Account article creation assistant. Use when users provide website links, text materials, or images and need to create WeChat Official Account articles. Supports multiple writing styles—corporate official account copy, personal technical blogs, community event recaps, product reviews, etc. Skilled at in-depth content creation on AI/technology topics, and can also produce standardized corporate promotional copy. Enriches content through search tools, optimizes titles and structure. When users mention "Official Account", "WeChat article", "write a tweet"...
Review Supabase docs changes locally in your `supabase/supabase` checkout — either an open PR (triage, classify, verify) or your own branch before opening a PR…
Activate deep research mode for systematic investigation. Use when the user asks to research, investigate, explore, or needs current information with citations.
Use when writing, compressing, or refactoring a BK-CI skill, for example tightening `description`, unifying the main file skeleton, offloading heavy content to `reference/`, and solidifying progressive disclosure rules. Prefer this when the user wants to add or standardize a skill.
Conduct structured business discussions with users using materials: align on the problem and goals, record facts and assumptions, break through old judgments through evidence collision and heterogeneous interpretations, continuously converge, and deliver a one-page conclusion. Used for business bottlenecks, discussions of complex materials, deep insights, and discussion tasks requiring cognitive breakthroughs.
Use when an author has received peer-review comments and scores for an academic paper and needs to diagnose underlying reviewer concerns, decide whether a…
Regression-check citation anchoring (citations stay in the same subsection) to prevent “polish drift” that breaks claim→evidence alignment.
Use when `paper-review` has claims plus evidence gaps and needs the final referee-style report.
De-slot and harmonize paper voice across `sections/*.md` without changing meaning or citation keys.
Writing self-loop for surveys: run the strict section-quality gate, then rewrite only the failing `sections/*.md` files until the report is PASS.
Turn an ML/AI research idea into a concrete method design. Use for objectives, architecture, inference, assumptions, ablations, and implementation handoff.
Design hypothesis-driven ML/AI experiments before running. Use for ablations, baselines, metrics, controls, seeds, logging, and claim-evidence matrices.
Use when generating or updating a project README.md or CHANGELOG.md.
Summarize a research project conducted with Asta skills and submit it to the asta-research-challenge repository. Use when the user wants to reflect on a…