Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Catalog hygiene for Claude Code skill/agent plugins. Runs audits: inventory, per-skill scoring, embedding-based collision detection, and HDBSCAN taxonomy checks. Proposes PR-style resolutions without auto-applying.
npx claudepluginhub theagenticguy/agentic-plugins --plugin plugin-gardenerScore a single skill against the gardener rubric. Reads the skill's SKILL.md, references/, and templates/, then writes a 7-dimension scorecard with per-criterion rationales and a recommended-actions list. Isolated counterpart to /gardener: same rubric, one item at a time. Use when the user asks to audit a skill, score a skill, check if a skill is healthy, or wants to re-score after making changes.
Monthly catalog hygiene audit for Claude Code plugin marketplaces. Inventories every skill and agent, scores each against a 7-dimension rubric via parallel Opus Agents, detects description collisions via Bedrock Cohere v4 embeddings with pairwise cosine, and writes a delta report vs. the prior audit. Proposes resolutions; does not auto-apply. Use when the user asks to audit the catalog, run the gardener, find skill collisions, check plugin hygiene, generate a monthly audit report, or mentions catalog drift.
Propose description rewrites to resolve skill collisions. Given a collision pair from a gardener audit, reads both skills' descriptions, generates before/after rewrites with negative discriminators, and writes a proposal Markdown the user applies manually. Uses current Claude prompting discipline: positive imperatives, motivation clauses, scope explicit. Use when the user asks to fix a collision, rewrite a description, disambiguate two skills, or mentions resolving a gardener-flagged pair.
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
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.
Open-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Works with Claude Code, Kiro, Clawd CLI, Gemini CLI, Cursor, Continue, Hermes, and 17+ AI coding assistants. Now with Arabic, German, Spanish, and Chinese (Simplified & Traditional) support.
A growing collection of Claude-compatible academic workflow bundles for producing work at Nature-journal standard. Covers scientific figures (nature-figure), manuscript prose polishing (nature-polishing), manuscript drafting and methods writing (nature-writing), reviewer-style pre-submission assessment (nature-reviewer), citation retrieval and export (nature-citation), data availability statements and FAIR metadata (nature-data), paper-to-PPTX presentation conversion (nature-paper2ppt), literature search via MCP (nature-academic-search), paper reading and annotation (nature-reader), and peer-review response drafting (nature-response). Future releases planned: statistical reporting, cover letters, and review articles. Rules are derived from primary sources, including published Nature papers, journal author guidelines, and structured writing curricula.
ERPAVal — autonomous software development workflow for Claude Code. Comprehensive standalone bundle: the erpaval workflow plus 10 vendored companion skills (product-discovery, research, ultraplan, tech-stack-builder, product-strategy, working-backwards, customer-research, meta-prompt-optimizer, product-design-shared, agent-ux-patterns) so the six-phase Explore/Research/Plan/Act/Validate/Compound loop routes resolve out of the box. Designed to be forked.
Flagship skills for AI coding agents. Includes workbench-builder: disposable localhost Flask + sqlite3 + htmx + SSE workbenches with a two-way human↔agent loop — eval viewers, PR review rooms, document-redline surfaces, trace replays, and refactor cockpits, with no build step or deploy.
A public Claude Code plugin marketplace — installable skills and agents for AI coding agents.
Add the marketplace, then install a plugin:
/plugin marketplace add theagenticguy/agentic-plugins
/plugin install agentic-skills@agentic-plugins
/plugin install plugin-gardener@agentic-plugins
Flagship skills for AI coding agents.
| Skill | What it does |
|---|---|
workbench-builder | Builds disposable localhost workbenches — Flask + sqlite3 + htmx + Server-Sent Events apps that give an agentic coding/eval/PR/data session a live UI with no build step, no npm install, and no deploy. The signature move is a two-way human↔agent loop over one SQLite file: the human acts in the browser (htmx POST → SQLite → fragment + SSE invalidation), the agent acts from the terminal (httpx → SQLite → SSE), both seeing the same state update live with no reload. Ships recipes for eval viewers, PR review rooms, document-redline surfaces, trace replays, and refactor cockpits. |
Bundled MCP servers (plugins/agentic-skills/.mcp.json) — research and documentation tools that
back the skills. Each reads its key from an environment variable; the marketplace entry is
strict: false, so a missing key never blocks install — the server is simply skipped.
| Server | Purpose | Env var |
|---|---|---|
| context7 | Up-to-date library/API docs | CONTEXT7_API_KEY |
| deepwiki | GitHub repo Q&A | (none) |
| brave-search | Web search | BRAVE_API_KEY |
| tavily | Web search + extraction | TAVILY_API_KEY |
| exa | Neural web search | EXA_API_KEY |
| you | You.com search + research | YDC_API_KEY |
| awsknowledge | AWS documentation | (none) |
Catalog hygiene for Claude Code skill/agent plugins. Runs audits — inventory, per-skill scoring, embedding-based collision detection, and HDBSCAN taxonomy checks — and proposes PR-style resolutions without auto-applying.
.claude-plugin/marketplace.json # marketplace registry — lists every plugin
plugins/
agentic-skills/ # flagship plugin
.claude-plugin/plugin.json
.mcp.json # bundled MCP servers
skills/
plugin-gardener/ # catalog-hygiene plugin
.claude-plugin/plugin.json
skills/ references/ scripts/
tools/ # repo-wide validators and scaffolding
mise install # node, markdownlint-cli2, dprint
mise run fmt # format all markdown and JSON
mise run fmt:check # check formatting (CI-friendly)
mise run lint # lint all markdown
mise run lint:md:fix # lint with auto-fix
mise run validate # frontmatter + size + refs + freshness + versions
mise run build # full gate: lint + fmt:check + validate
mise run bump -- <plugin> patch # bump one plugin's version
mise run init:skill -- <plugin> <name> 'Description. Use when...' # scaffold a skill
CI runs mise run build on every push and pull request.