By korchasa
Procedural engineering knowledge (deep-research, fix-tests, draw-diagrams, write-prd, etc.)
Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from the current session — pick one IDE, fan out across several, or compare models. You are a courier that relays the other runtime's stdout verbatim, do not synthesise your own answer. Use on "run in <ide>", "compare <ide> vs <ide>", "try on <model>", "which IDE handles X better", "run across models".
Analyze total token usage including conversation history, system prompts, and active rules to estimate cost.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Multi-directional deep research with sub-agents, scoring, source verification, and cited synthesis. Use for comprehensive research, deep analysis, or evidence-backed answers. Produces executive summary + markdown report. Supports search tools, playwright-cli, and MCP.
Use when a flowai benchmark fails and you need the cause from run artifacts before editing. Reads judge-evidence.md, the sandbox SKILL.md, and scenario mod.ts; classifies the failure against a known taxonomy; produces an evidence-grounded report (no fixes). Do NOT trigger for passing benchmarks or generic skill iteration.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Generated Claude Code plugin marketplace for the AssistFlow framework.
This repository is a generated mirror. Every commit on main is produced by CI in korchasa/flowai on each framework-v* release. Do not edit files by hand outside README.md and LICENSE — they will be overwritten on the next release.
/plugin marketplace add korchasa/flowai-plugins
/plugin install flowai-core@flowai-plugins
/reload-plugins
Skills are invoked under the plugin namespace, e.g. /flowai-core:commit, /flowai-core:plan, /flowai-core:review. The flowai- prefix is stripped from skill / command directory names during build to avoid /flowai-core:flowai-commit-style double prefix.
Pilot scope (this repository): flowai-core only. Remaining packs (devtools, engineering, deno, typescript, memex) continue to ship via the flowai CLI. Multi-pack rollout will land in subsequent framework releases.
Plugin layout per pack:
.claude-plugin/plugin.json — manifest. version omitted; the git commit SHA of this repository is the version key, so one framework release maps to exactly one plugin update.skills/<name>/SKILL.md — both agent-invocable skills and user-only commands (commands carry disable-model-invocation: true).agents/<name>.md — subagents with Claude-native frontmatter.hooks/hooks.json — only when the pack ships hooks (not present in flowai-core).Claude Code plugins execute arbitrary code at your user privilege. Only install marketplaces and plugins from sources you trust. The contents of this repository are produced verbatim from public, auditable source: see korchasa/flowai (framework/<pack>/) and the build pipeline at scripts/build-claude-plugins.ts.
File issues and pull requests against the source repository: https://github.com/korchasa/flowai. This repository accepts no direct contributions other than infrastructure changes to README.md / LICENSE.
MIT — see LICENSE.
npx claudepluginhub korchasa/flowai-plugins --plugin flowai-engineeringDeno-specific skills (CLI, deploy, configure commands)
Skill and agent authoring tools (engineer-skill, engineer-command, benchmarks, etc.)
Memex — long-term knowledge bank for AI agents. Skills that ingest sources, answer questions with citations, and audit the bank for orphans, dead links, and contradictions.
TypeScript-specific setup skills (code style, strict mode)
Firefox browser UI for Claude Code sessions with real-time sync and browser automation
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Comprehensive SEO analysis plugin for Claude Code. 25 sub-skills (21 core + 1 orchestrator + 1 framework + 2 extension mirrors) and 18 sub-agents cover technical SEO, content quality, schema, sitemaps, Core Web Vitals, local SEO, backlinks, AI/GEO, ecommerce, hreflang, SXO, clustering, drift monitoring, and Google APIs. Includes optional MCP extensions, SPA-aware rendering, portability, and hardened SSRF/DNS-rebinding safe fetchers.
Modern R development skills for Claude Code - tidyverse patterns, rlang metaprogramming, Bayesian inference, performance optimization, and more