Agent Skills in category: Uncategorized

character-archetypes

Use when identifying, auditing, or tracking character archetypes in fiction. Trigger on: 'character archetype', 'archetype audit', 'what archetype is this character', 'archetype conformance', 'Hero's Journey character role', 'Jungian archetype', or archetype-based character analysis.

prose-mechanics

Use when auditing prose at the sentence level on stabilized drafts. Trigger on: 'audit prose', 'active voice', 'sentence variance', 'passive voice pass', 'parallel structure check', 'readability audit', 'prose mechanics', or sentence-level diagnostic work on fiction or nonfiction.

story-structure

Use when planning or diagnosing a novel's macro plot structure. Trigger on: 'story structure', 'plot point', 'inciting event', 'midpoint', 'structure audit', 'structure map', 'signpost scene', 'mirror moment', or macro-structure analysis.

fiction-workshop

Use when writing or editing novels, short stories, or any fiction manuscript. Trigger on: 'write fiction', 'edit my novel', 'developmental edit', 'line edit', 'character voice', 'plot hole', 'brainstorm', or fiction writing tasks.

narrative-nonfiction

Use when writing self-help books, memoirs, or prescriptive guides with story elements. Trigger on: 'self-help book', 'transformation arc', 'metaphor consistency', 'reader journey', 'exercise design', or narrative nonfiction projects.

bugbash

Systematically explore and test any software project (CLI, API, Backend, Library, etc.) to find bugs, usability issues, and edge cases. Produces a structured report with full reproduction evidence (exact commands, inputs, logs, and tracebacks) for every issue.

preact-buildless-frontend

Build-less ESM frontends that run directly in the browser without bundlers. Use this skill when creating static frontends, SPAs without build tools, prototypes, or when the user explicitly wants no Vite/Webpack/bundler. Covers import maps, CDN imports, cache-busting, hash routing, and performance patterns.

pull-llamacpp-model

Use when pulling or downloading a new llamacpp model. The active ROCm image (kyuz0/amd-strix-halo-toolboxes) fails to start in the ephemeral pull container without ROCm device access. Must temporarily switch to the standard CPU image.

run-llms

Set up and run local LLMs with Harbor. Use when the user wants to run models locally, install Harbor, start Open WebUI, llama.cpp, Ollama, vLLM, Docker Model Runner, MLX, or oMLX, pull GGUF or HuggingFace models, add SearXNG web search, Speaches TTS/STT, or Open Terminal code execution, launch Codex/Claude/Grok/OpenCode against a Harbor backend, or troubleshoot GPU, VRAM, and service startup.

tinygrad

Deep learning framework development with tinygrad - a minimal tensor library with autograd, JIT compilation, and multi-device support. Use when writing neural networks, training models, implementing tensor operations, working with UOps/PatternMatcher for graph transformations, or contributing to tinygrad internals. Triggers on tinygrad imports, Tensor operations, nn modules, optimizer usage, schedule/codegen work, or device backends.

turso-db

Install, configure, and work with Turso DB — an in-process SQLite-compatible relational database engine written in Rust. Use when the user needs to (1) install Turso DB, (2) create or query databases with the tursodb CLI shell, (3) use Turso from JavaScript/Node.js via @tursodatabase/database, (4) work with vector search or embeddings in Turso, (5) set up full-text search with FTS indexes, (6) configure transactions including MVCC concurrent transactions, (7) enable encryption at rest, or (8) use Change Data Capture (CDC) for audit logging.

timeboxed-iterating

agent-integration-testing

Use when the user requests integration testing, feature validation, or test plan execution

boost-modules

Create custom modules for [Harbor Boost](https://github.com/av/harbor/tree/main/boost), an optimizing LLM proxy. Use when building Python modules that intercept/transform LLM chat completions—reasoning chains, prompt injection, structured outputs, artifacts, or custom workflows. Triggers on requests to create Boost modules, extend LLM behavior via proxy, or implement chat completion middleware.

anneal

Use when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error swallowing, convention drift, cargo-cult patterns, and other LLM-introduced architectural decay — over a specified duration

article-factory

Produce a researched long-form article from a topic prompt via an orchestrated pipeline - research agent (first-person sources, working-definition gate), narrative-architecture outline, writer/cold-reviewer loop with an explicit ACCEPT/REVISE verdict contract, then a catalog-deslop pass with a regression gate. The orchestrator dispatches subagents only; the writer never judges its own draft. Use when the user says "article factory", "write an article about X", "run the article pipeline", or asks for a researched long-form piece produced end-to-end. For essays and micro posts in the user's own voice without a research stage, use the prose skill instead.

autoresearch

Runs autonomous keep/discard experiments on a codebase to optimize a single metric for a fixed duration, in the style of karpathy/autoresearch. Use when the user says "autoresearch" (optionally with a focus, e.g. "autoresearch the optimizer"), asks to run experiments on a repo overnight, to hill-climb or optimize a metric autonomously, or points at a repo with a karpathy-style program.md.

bughunt

Fully autonomous bug hunting pipeline — discover bugs in a scoped area using parallel subagents, independently triage each finding, fix confirmed issues with subagents, then audit all fixes against repo constraints and target platforms. Runs end-to-end without user interaction.

catalog-deslop

Catalog-then-fix slop removal on an existing prose draft. Parallel catalog subagents inventory four slop categories (theatrics, overwrought register, corrective antithesis, dramatic short sentences), fix subagents repair only what a catalog names, mechanical lint + frequency analysis bracket the run, and a regression gate (lint delta, word count, cold meaning check) decides whether the result ships. Use when the user says "deslop this draft", "catalog deslop", "strip the AI patterns from this file", or as the final stage of the article-factory and mosaic-writing skills. For writing or redrafting prose from scratch, use the prose skill instead - this skill only repairs an existing draft in place.

discipline

Bulletproof agent operating protocol. 15 failure-prevention rules distilled from 120+ real sessions and 10 agent definitions. Covers fabrication, constraint tracking, verification, scoping, retry discipline, and communication. Load before any task to prevent the most common agent failure modes.

factual-communication

Restate content as a flat list of atomic facts in the style of av/facts fact sheets. Use when the user says "just facts", "facts only", "as facts", "give me the facts", or replies with a bare "facts" / "facts?" to a previous message — then the scope is that message's content.

ideate

Timeboxed ideation on a topic where lens-driven proposers generate structurally different ideas, blind critics cull them, and pairwise judges rank the survivors on a tournament ladder instead of 1-10 scores, evolving the leaders until the clock runs out. Use when the user wants to brainstorm, explore ideas, discover features, generate options, or think through possibilities for a specified duration. Triggers on requests like "brainstorm X for 30 minutes", "ideate on X", "spend an hour thinking about X", "what features should we build", "explore options for X". Not for executing a task over time (timeboxed-iterating) or optimizing a measurable metric (autoresearch).

improve-skill

Improve an existing agent SKILL.md through one gated cycle: select the target (default this skill), snapshot the committed baseline, diagnose against skill-design-principles plus four rubric dimensions, apply exactly one focused change, and ship only if a different agent than the author PASSes with quoted evidence. Use when the user says "improve this skill", "improve-skill", "iterate on SKILL.md", or "apply skill-design-principles to a skill". Do not use for code slop over a duration (anneal), generic timeboxed work (timeboxed-iterating), graph orchestration (workgraph), metric hill-climb on a codebase (autoresearch), or stripping slop from existing prose (catalog-deslop).

make-video

mosaic-writing

Assemble a finished piece from human-written fragments via an orchestrated two-loop pipeline - an assembly loop (assembler + cold reviewer) that sequences the fragments into a draft, then a polish loop (polisher + cold reviewer), then frequency analysis and a catalog-deslop pass with a regression gate. Two modes with opposite fidelity contracts - stitch mode preserves the author's exact wording, narrative mode preserves every idea but may rewrite freely. Use when the user says "mosaic", "assemble my fragments", "stitch these notes into a post", or provides a fragments file to turn into a finished piece. For writing from a topic with research, use article-factory; for prose from scratch, use the prose skill.

sandcastle

Orchestrate AI coding agents (Claude Code, Codex, OpenCode) in isolated sandboxes using the @ai-hero/sandcastle SDK. Use when the user needs to (1) run agents AFK in Docker/Podman containers, (2) build multi-agent pipelines with plan-execute-review patterns, (3) run parallel agents on separate worktrees, (4) create iterative agent loops with maxIterations, (5) extract structured output from agent runs, (6) set up sandcastle in a new or existing project, or (7) write prompt files with template args and shell expressions.

superclaude

Configure and operate the Claude Code harness for large codebases. Builds CLAUDE.md hierarchies, scoped test/lint commands, file exclusions, codebase maps, hooks, skills, subagent strategies, and LSP/MCP wiring. Use when setting up Claude Code for a new repo, auditing an existing configuration, onboarding a team, or scaling from single-developer to org-wide deployment. Triggers on "set up Claude Code for this repo", "optimize my Claude Code config", "audit my CLAUDE.md", "make this codebase navigable", "configure hooks/skills/plugins".

timeframe-research

Build a timeframe-bounded research dossier by decomposing a topic into year orchestrators and month-level research passes that each write one condensed paragraph plus sources directly into a target file. Use when the user asks for a dossier, timeline, chronology, release history, or month-by-month research bounded by specific years or months. Not for timeless explainers or single-document summaries with no temporal scope.

use-coding-agents

workgraph

Orchestrate work as a cyclic directed graph of subagent-executed nodes with transition criteria on edges, budgeted cycles, and per-node gates (runtime verification, metric, or artifact). Use when the user says "workgraph", "run this as a graph", "graph this work", or when a goal has parallel branches, feedback loops, or mixed gate types that a linear loop cannot express. Every node is sized to a 64k context budget, so small goals run as a two-node do/verify graph and large goals scale out without caps. For clock-driven or metric-driven single loops, timeboxed-iterating and autoresearch remain lighter.

workmachine

architecting-backend

Guides backend development with hexagonal architecture, DDD, SOLID principles, and clean code practices. Use when user says "review my backend", "check architecture", "refactor this service", "design a new feature", or asks about dependency injection, code smells, or SOLID violations. Do NOT use for frontend code, React components, or infrastructure/DevOps tasks.

domain-driven-design

Domain-Driven Design reference for strategic and tactical modeling. Use when user says "model this domain", "design a bounded context", "create an aggregate", "what's a value object", "apply DDD", or asks about ubiquitous language, context mapping, entities, repositories, domain events, or aggregates. Do NOT use for infrastructure/DevOps, pure UI components, or simple CRUD without business rules.

react-clean-architecture

Clean Architecture for React Web with TypeScript and Vite. Enforces strict separation between Core (domain), Infrastructure (adapters), and UI layers. Use when user says "create a feature", "refactor this module", "review architecture", "add a use case", or asks about ports/adapters, Result pattern, viewModels, or dependency injection in React. Do NOT use for React Native, backend code, or simple UI-only components without business logic.

react-conventions

React and React Native coding conventions with TypeScript. Use when user says "create a component", "write a hook", "review my React code", "check conventions", or asks about naming, props patterns, accessibility, performance with React Compiler, or Tailwind/Uniwind styling. Do NOT use for backend code, Node.js, or architecture decisions.

security-guardian

Application security expert for vulnerability detection, code auditing, and secure design guidance. Covers OWASP Top 10, authentication, authorization, cryptography, and secrets management. Use when user says "security audit", "check for vulnerabilities", "review auth code", "is this secure", or asks about XSS, SQL injection, CSRF, or secret management. Do NOT use for general code review or architecture guidance.

jk

Manage Jenkins controllers with jk, including jobs, runs, logs, artifacts, credentials, nodes, queues, and plugins.

avivsinai

9411

template-skill

Replace with description of the skill and when Claude should use it.

inupowers

scientific-schematics

Create publication-quality scientific diagrams, flowcharts, and schematics using Python (graphviz, matplotlib, schemdraw, networkx). Specialized in neural network architectures, system diagrams, and flowcharts. Generates SVG/EPS in figures/ folder with automated quality verification.

ttawdtt

dolphindb-skill

DolphinDB/DolphinScript 的数据库、SQL、流计算、回测与排障技能。用户提到 DolphinDB，或仓库/代码出现 dfs://、createPartitionedTable、context by、streamTable、subscribeTable、createTimeSeriesEngine、DStream::、Backtest:: 等专有线索时调用；已有 DolphinDB 上下文时，即使本轮只说“分区表”“实时 K 线”“回测报错”也要使用。用于按目标 Server/插件版本核对官方 API、选择 OLAP/TSDB/PKEY/IOT，并生成可验证的代码与方案。明确只涉及其他技术栈且无 DolphinDB 上下文时不调用。

hugo2046

3612

project-understanding

Use when you need a fast, reliable architecture or impact view in a large unfamiliar repo, especially under time pressure or tight context budgets where manual grep or folder inference would be risky.

evil-skills

browser-automation

Reliable browser automation through explicit Chrome DevTools Protocol endpoints.

different-ai

60153

tapestry

This skill should be used when the user says "tapestry <URL>", "weave <URL>", "help me plan <URL>", "extract and plan <URL>", "make this actionable <URL>", or wants to extract content from a URL and create an action plan. Automatically detects content type (YouTube video, article, PDF) and orchestrates the full extract-to-plan workflow.

youtube-transcript

This skill should be used when the user provides a YouTube URL and wants to "download transcript", "get captions", "get subtitles", "transcribe video", or extract text content from a YouTube video. Handles manual subtitles, auto-generated captions, and Whisper transcription as fallback.

article-extractor

This skill should be used when the user wants to "download article", "extract article", "save blog post", "get article text", or provides a web URL and asks to extract the main content without ads, navigation, or clutter. Saves clean, readable text from web articles and blog posts.

ship-learn-next

This skill should be used when the user wants to "turn this into a plan", "make this actionable", "create an action plan", "implement the advice", or has learning content (transcript, article, tutorial) and wants concrete implementation steps. Transforms passive content into shippable iterations using the Ship-Learn-Next framework.