understand-anything
claudeAI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
Build dashboards on the Open Pulse platform — a guided /open-pulse:new-dashboard wizard, query skills for Neo4j/SPARQL/OpenSearch/CHAOSS, the hub op-* skills, and the SDSC design-system skills.
Plugin open-pulse from marketplace open-pulse in sdsc-ordes/open-pulse-webkit. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.
frontend-devFrontend engineering mechanics for the pulseWebKit web app — design-skill-agnostic. Defines the `--op-*` token contract the app consumes, how to install a design skill's tokens, font-loading mechanics, canvas/D3 constraints, build-time injection, the required shared components, and the Playwright UI
new-dashboardGuided wizard that interviews the user and scaffolds an Open Pulse dashboard in src/your-web/ — first sets up the project structure and walks the user through creating .env (works in plugin mode on an empty project); asks about scope, design intent, drill-down themes, stack, and publishing; checks t
op-collectionsBrowse, search, and export the Open Pulse hub's indexed collections — ~50 DuckDB-backed datasets (github_repos, huggingface_models, zenodo_records, orcid_*, ror_*, infoscience_*, snsf_*, gitlab_*, …) — plus cross-store counts at /api/stats/. TRIGGER when the user wants to look up / list / search / e
op-crawlerRun, monitor, and control the Open Pulse GitHub crawler via the hub's crawler-jobs API — list jobs, inspect a job's progress, pause/resume/cancel/delete a job, preview the next crawl frontier, and resolve a job to its pipeline run. A crawl is launched as the `crawler` step of a pipeline quest. TRIGG
op-extractorRun and monitor the Open Pulse git metadata extractor (and the rest of the pipeline) via the hub's quest API — list/read quest recipes, launch a run, poll run status and step stats, stop a run, list archives. The GME is the `metadata_extractor` step of a quest. TRIGGER when the user wants to run/tri
op-searchSemantic / vector search (RAG retrieval) over the Open Pulse extractor indices — the Git Metadata Extractor service indexes every source (github_repos, zenodo_records, openalex, orcid, ror, infoscience, huggingface_*, gitlab_*, snsf, swissubase, …) into per-provider vector stores and serves embeddin
openpulse-dark-themeThe permanent-dark Open Pulse dashboard design theme — a delta on top of the `sdsc-ui-kit` brand system. Supplies the values for the `--op-*` token contract (assets/tokens.css), the light→dark translation of the SDSC brand, dark component/layout specs, and the dashboard-only visuals (attribution bar
query-chaossQuery the Open Pulse CHAOSS Metrics API — 35 community/popularity/quality metrics computed live per GitHub repository or per GrimoireLab project, over the Neo4j+SPARQL+OpenSearch stores. TRIGGER when the user asks for a ready-made health/community/popularity/quality metric on a repo or project — esp
query-neo4jRun a Cypher query against the Open Pulse Neo4j instance and get JSON rows back. TRIGGER when the user asks anything that requires reading from the graph database — exploring labels, counting nodes/relationships, listing repositories/contributors/commits, sampling properties, or running a Cypher que
query-opensearchQuery the Open Pulse OpenSearch cluster via the hub HTTPS gateway — SQL (SELECT/SHOW/DESCRIBE) or full search DSL (aggregations, filters). TRIGGER when the user asks anything that requires reading from the GrimoireLab/OpenSearch indices — counting docs, searching commits by enriched fields, running
query-sparqlRun a SPARQL query against the Open Pulse Oxigraph triplestore via the hub HTTPS gateway. TRIGGER when the user asks anything that requires reading from the RDF metadata graph — listing named graphs, counting triples, exploring a vocabulary/predicate, or running a SPARQL SELECT/ASK/CONSTRUCT they pa
sdsc-ui-kitUse this skill when building or styling web UI for Swiss Data Science Center (SDSC / datascience.ch) platforms — applying brand colours, typography (Space Grotesk + Switzer), buttons, form inputs, layout patterns, and dark mode. Framework-agnostic: the spec is expressed as CSS custom properties and
playwrightruns: npx -y @playwright/mcp@latest --browser chromium --headless --allowed-origins http://localhost:5173;http://localhost:4173;http://127.0.0.1:5173;http://127.0.0.1:4173
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Install the "AAS Data Analytics & Business Intelligence" workflow plugin from Agentic Awesome Skills.
16 skills
The official CCXT MCP server plus the ccxt-mcp usage skill — market data, balances and opt-in trading across 100+ crypto exchanges and prediction markets, with keys kept local.
1 MCP server
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 agents
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.