Shape agent capabilities into your workflow.

Hydra is a Claude Code skill for reviews that benefit from several independent perspectives, such as architecture decisions, security-sensitive changes, and difficult refactors. Standard mode uses four advisors plus a chairman; deep mode expands to six advisors, three reviewers, and optional Codex participation. The final report traces recommended actions back to finding IDs and asks for cost confirmation before running.

OSOP Agent Rules installs platform-specific instructions for 18 coding-agent environments, including Cursor, Codex, Windsurf, Aider, Cline, and Claude Code. After a multi-step task, the agent writes an `.osop` workflow and an `.osoplog` execution record containing nodes, dependencies, status, duration, and tool usage. The files can be viewed in the OSOP visual editor or used to generate reports.

Doc Harness records project rules, current work, file locations, and past phases in a maintained set of Markdown documents so a new agent can resume from files alone. Its Claude Code version provides commands to initialize, check, sync, flush, recall, and resume projects, while Kimi CLI installation is also supported; the documentation system requires no database or external memory service.

This Claude Code skill uses BBDown to save a single Bilibili video or batch-download an uploader's videos as high-bitrate M4A files. It can embed available subtitles, names files with the date, title, and BV identifier, and skips completed downloads for resuming. BBDown must be installed, and some content requires a valid logged-in cookie.

Scan a codebase, dataset, research collection, or documentation project and turn it into a structured knowledge base. After you approve the proposed architecture, it generates three levels of LLM-friendly context packs, a project-specific Python compiler, and an interlinked Obsidian wiki with search and lint commands.

no-slop is a constraint skill that shapes prose during drafting instead of rewriting it afterward. Its thirteen rule groups cover inflated vocabulary, promotional tone, vague attribution, formulaic structures, participle chains, synonym swapping, excessive formatting, and other recognizable AI-writing habits. It can activate automatically for prose in Claude Code and also includes setup guidance for Cursor and Codex.

Memory Palace organizes persistent context for Claude Code and Cowork into a compact PALACE.md index, topic wings, dated notes, and tunnels between related subjects. New sessions can load the hot cache first and read deeper context only when needed. Its local CLI supports initialization, search, health checks, statistics, maps, archiving, and import or export, while optional hooks can autosave significant findings.

The repository currently bundles two installable skills for content and product teams. The GEO blog skill guides article structure, frontmatter, schema, and a pre-publication checklist intended to make content easier for AI answer engines to cite. The Laws of UX skill applies established psychology and usability principles when designing or reviewing web apps, dashboards, landing pages, forms, and navigation. Teams can install the full collection or select an individual skill through Skillshare.

The skill brings 13 frameworks into Claude Code for decisions around sales compensation, competitive moats, fundraising, go-to-market strategy, hiring, pricing, and AI-agent deployment. It can activate automatically when those topics arise or be invoked directly. The material was synthesized programmatically from more than 200 interview episodes rather than presented as a searchable transcript archive.

A deterministic analyzer first extracts the file tree, imports, definitions, and module connections without sending source code to an LLM. One model call then assigns architectural roles, detects the overall pattern, and chooses a layout. The resulting graph opens in an interactive visualizer with multiple views and branch-based experiments that can add or remove nodes and edges without changing the base map.

Vingo embeds technical-English practice into conversations with Claude for Vietnamese speakers. It explains unfamiliar terms in everyday Vietnamese, corrects pronunciation and grammar, and uses escalating comedic roasts to make mistakes memorable, targeting beginners, founders, product or design roles, and developers who want clearer spoken tech vocabulary.

Provide a website URL and Agentizer crawls its brand and product content, then generates a Next.js agentfront with chat, voice, interactive browsing, and conversational conversion flows. It can run through Claude Code, Codex, or a standalone CLI and deploy through Vercel and Cloudflare. The generated experience requires Gemini and OpenAI API credentials.

Use 396 named bash scripts that map directly to Twenty CRM REST endpoints for CRUD, filtering, batch operations, duplicate merging, attachments, and more than 30 object types. Agents can discover the right script and inspect its expected JSON before execution, reducing malformed requests. The toolkit works as a Claude or OpenClaw skill, through MCP, or in shell automation, and requires bash, curl, jq, and a Twenty API key.

Enter a GitHub username to turn public repositories, languages, commit patterns, and README details into a shareable satire piece in one of several tech-persona parody styles. Roaster Kit works as a Claude skill, slash command, or standalone CLI and supports multiple output formats. Its rules restrict material to public data, prohibit identity-based jokes, and soften third-party or learner roasts when consent is absent.

wechat-article-down opens a WeChat Official Account URL through chrome-devtools MCP, waits for the article to render, scrolls through lazy-loaded media, and extracts the body plus metadata. It converts the HTML to Markdown and saves images, audio, and optionally video alongside the article, with batch processing supported. Node.js 16 or newer and browser automation are required, while video downloads additionally use yt-dlp.

xiaoer-artstudio-design packages the 小耳 Art Studio aesthetic as a methodology rather than a page template. Agents can load principles for whitespace, typography, palette, layout rhythm, hand-drawn SVGs, motion, and trilingual copy, plus machine-readable tokens and remix guidance. Optional interaction recipes cover a physics garden, spring-like text, and a pencil cursor, and the kit is portable across Claude Code, Hermes, other agent frameworks, or raw LLM prompts.

Follow a deployment runbook from DigitalOcean droplet provisioning through Python 3.11 setup on Ubuntu 24.04, non-interactive Hermes installation, profile and workspace linking, credential migration, and OAuth callback caveats. It finishes by running the gateway as a lingering systemd user service for an agent that needs to stay online.

Use PRCSS to scaffold an end-to-end product design project, plan a single phase, or generate one design-method card. After a four-question kickoff, it produces structured Markdown based on a seven-phase workflow, ready to paste into a wiki, kanban board, document, or Figma without locking the team to a specific tracker.