panel-live-server
claudeMCP server that renders, validates and screenshots Panel apps and plots so the agent can see what it built. Runs Python locally; pairs with developing-with-holoviz.
14 skills
Every HoloViz Agent Skill in one plugin — Panel, hvPlot, HoloViews, Param, and more. Bundles contributing-to-holoviz, creating-custom-holoviz-skills, developing-with-holoviz.
Plugin holoviz from marketplace holoviz-skills in holoviz-dev/holoviz-skills. Commands read from the repo's manifest — 9 days ago.
contributing-to-holovizMaintain, contribute to, and write about HoloViz packages. Use when reviewing PRs, refactoring code, writing tests, docs or PR descriptions, writing a minimal reproducer or a Playwright repro of a browser-only bug, stripping LLM slop from prose, or writing a blog post or demo video about a HoloViz p
cleanupCode quality guidelines for HoloViz packages. Use when writing, changing, refactoring, or reviewing code in any HoloViz repository.
deslopStrip LLM slop from prose — rhetorical tics, false-profundity constructions, AI vocabulary, and boilerplate. Use when writing or reviewing any HoloViz prose (PR descriptions, docs, blog posts, READMEs, commit messages) to remove recognizable LLM patterns.
documentationDocumentation guidelines for HoloViz packages. Use when writing or reviewing docs, changelog entries, or API references in any HoloViz repository.
minimal-exampleWrite a minimal, self-contained, reproducible example for a HoloViz behavior or bug. Use when drafting a bug report, an issue reproducer, a PR "How to test" snippet, any code sample a maintainer must be able to paste and run unchanged, or a Playwright script that confirms a bug only visible in the b
outreachWriting about and showing HoloViz work for readers outside a PR or the docs, such as a post on blog.holoviz.org or a company blog, a short demo video for YouTube or LinkedIn, or a codebase explainer video for new contributors. Use when drafting, structuring, or reviewing a blog post, or when plannin
pr-descriptionWriting a clear pull request description for HoloViz packages. Use when drafting or reviewing the description, summary, or write-up of a PR in any HoloViz repository.
testingTesting guidelines for HoloViz packages. Use when writing tests, reviewing test coverage in PRs, or identifying missing edge cases in any HoloViz repository.
creating-custom-holoviz-skillsCreate new agent skills for the HoloViz ecosystem. Use when adding a skill to this repository — covers repo conventions, directory layout, routing skills, the docs pipeline, and the eval system.
developing-with-holovizRoute to HoloViz sub-skills. Use for ANY task involving interactive plots, dashboards, data apps, reactive parameters, or custom JS/Python components in the HoloViz ecosystem (Panel, hvPlot, HoloViews, Param) — including tasks that name Bokeh, Matplotlib, or Plotly, since HoloViz embeds those figure
holoviewsBuild interactive visualizations with HoloViews elements, opts, streams, and operations. Use when composing plots from element primitives (Curve, Points, Bars, NdOverlay), customizing Bokeh tools/tooltips/formatters, using DynamicMap, streams, or link_selections. Do not use for simple DataFrame plot
hvplotPlot DataFrames and datasets using a Pandas .plot()-like API for Pandas, Polars, Xarray, DuckDB, Dask, and GeoPandas. Use when the user asks to visualize, plot, or chart tabular or multidimensional data. Do not use for element composition, streams, or custom Bokeh tools/tooltips (use HoloViews).
panelBuild interactive dashboards, tools, and data apps with HoloViz Panel. Use when the user needs widgets, layouts, templates, or reactive server-side Python web applications. Do not use for standalone plots without widgets (use hvPlot).
paramDefine Python classes with typed, validated, reactive parameters using Param. Use when building classes with constrained attributes, reactive dependencies between values, or dynamic option cascading. Load alongside the Panel skill for any Panel app using Parameterized classes.
MCP server that renders, validates and screenshots Panel apps and plots so the agent can see what it built. Runs Python locally; pairs with developing-with-holoviz.
14 skills
Deep vulnerability scanning of your own code, run entirely inside your Claude Code session at a chosen effort tier, with every finding challenged before it is reported and the verification tally computed in code. Turns surviving findings into targeted patches, each verified by a panel of agents, that you apply when you choose.
1 skill · 9 agents · hooks
Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).
1 skill · hooks
Workflow-builder skill: design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool (CLAUDE_CODE_WORKFLOWS=1, /workflows). Every session opens with an intake question set; when the user is vague, a stdlib recommendation engine infers and proposes a topology with rationale instead of stalling. Ships 3 stdlib Python tools (intake recommendation engine, .js validator enforcing pure-literal-meta / no-non-determinism / guarded-loop / parallel-thunk rules, topology scaffolder), 3 references citing 7-8 authoritative sources each (API surface, orchestration patterns, decision + intake guide), templates + a runnable example, cs-workflow-architect persona agent + /cs-workflow-build slash command. Use when building, scaffolding, or running a custom Claude Code workflow or orchestrating sub-agents (fan-out, pipeline, loop, judge-panel).
1 skill · 1 command · 1 agent
A 股/港股/美股个股深度分析引擎 · 22 维数据 × 66 位大佬量化评委 · 22 种机构级分析方法 · 杀猪盘检测 · Bloomberg 风格报告 | A-share / HK / US deep-analysis engine with first-class Chinese-market coverage — the same names that cost Munger millions on Alibaba. 22 dims × 66-investor jury × 22 institutional methods · trap detection · Bloomberg-style report
5 skills · 20 commands · 1 agent · hooks
Thirteen Claude skills that run an Instagram account, including a scored hook panel, a viral research skill, a caption linter and a humanizer.
13 skills
All CCG skills in one install: bt-panel / seo-page-builder / adsense-site-auditor / scrapling, the verify-* quality gates + gen-docs, the Impeccable-fused frontend-design skill, and 60+ domain-knowledge references. Invoked as /ccg:<skill>.
16 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.