Use when the user wants a security/exposure check on a domain or website they own or are authorized to test — "audit my site", "what's my attack surface look like", "did anything change on my domain", etc. Drives the nirikshak MCP tools (fullsurfacescan, and the individual checks) and turns raw output into a…
Use Guardian MCP tools to monitor, intervene, and analyze ML training. Covers 35 tools across monitoring, checkpoint analysis, recovery, dashboard config, and cross-experiment queries. Use when the user asks about training status, anomalies, checkpoints, experiments, model analysis, or when Guardian MCP server is…
Summarize a chapter, section, topic, report, or knowledge collection into source-backed notes with Chilon Recall. Use for study notes, structured chapter overviews, topic synthesis, and requests that need explicit source coverage and evidence limits.
Standard operating procedure for an auditable, headless HEC-RAS workflow via the hec-ras MCP server — how to plan, copy, edit boundaries, run, QA-gate, read results, compare, plot, audit, and safely stop. Use FIRST whenever an agent is handed a HEC-RAS project (.prj folder) or a results file (.p##.hdf) plus a…
Debug local Windows dev problems (port conflicts, HTTP 5xx, slow machines, hanging tests, crashes) via WinKit MCP. Use whenever user mentions local app broken, port in use, localhost not responding, machine slow, BSOD/crash, or asks about WinKit/workspace/dev server. Always use for Windows local diagnostics.
Check grade standing across Canvas courses and answer what-if questions like what score is needed on the final for an A. Use when the user asks about grades, GPA impact, whether they can still pass, or what they need on remaining work.
Official Stripe MCP integration for Prime Agent. Connects to Stripe's remote MCP server at https://mcp.stripe.com with OAuth and exposes live Stripe API, billing, reporting, and documentation tools. Use for Stripe test-mode setup, products, prices, customers, subscriptions, billing portal configuration, webhook…
This skill should be used when the user wants to turn a client's raw documents — invoices, purchase bills, bank statements, credit/debit notes, cash receipts — into TallyPrime vouchers via PNPC-MCP-Tally-Prime, e.g. "process this client's document folder", "import these invoices into Tally", "draft vouchers from this…
Explain substantial completed code changes as a guided technical walkthrough with Mermaid diagrams and an efficient, dependency-aware review order. Use after implementing a feature, bug fix, or refactor, or when the user asks what changed, how the new flow works, or which generated code to review first. Do not use for…
Route design-related HTML artifact tasks (landing pages, portfolios, prototypes, decks, content pages, web tools, social cards, info-interactive) to the right artifact skill, and decide whether to use design-system-reference, design-system-generation, or export. Use for any UI/visual/HTML design work.
Self-report every agent action to the agent-obs observability MCP server. Use in EVERY session where the agent-obs MCP server is connected - start a session at task start, log every tool call (Read, Write, Edit, Bash, Glob, Grep, etc.), end the session at task completion, and answer "how did my last session go"…
Complete reference for all 15 BulkPublish platforms — post types, media requirements, required fields, character limits, and platformSpecific options. ALWAYS consult before creating posts.
Design OPC UA information models grounded in real companion specifications (DI, Machinery, Robotics, LADS, Scales, …) using the OPC UA Modeler MCP server — look up types, their members and valid optionals, resolve namespace dependencies, and find engineering units before writing any model, instead of guessing from…
Convert a Claude session, research artifact, or markdown blob into a designed PDF: cover page, auto-generated table of contents, styled body, page-numbered footer. One tool call.
Maintain evidence-backed project state across conversations, branches, reviews, and research cycles. Use when an AI coding agent must reconstruct or consolidate fragmented project documentation, reconcile conflicting history against code/tests/contracts/Git, classify active and completed work, verify completion…
Audit web pages for performance optimization following PageSpeed Insights guidelines. Use when analyzing page performance, optimizing web applications, reviewing performance metrics, implementing Core Web Vitals improvements, or when the user mentions page speed, performance optimization, Lighthouse scores, or Core…
Use the Web Search Neo MCP server for free web search without API keys, resilient multi-engine fallback, HTTP page fetching, the user's current signed-in Chrome with AI-group tabs, isolated browser profiles, accessibility-level page inspection, form filling and upload, page console and network diagnostics…
Delegation and answer evaluation workflows for the Pinecone Assistant. Uses assistantchat as a sub-agent (Pinecone handles retrieval and synthesis internally) and evaluateanswer to validate answer correctness and completeness against ground truth. Use when Claude's context window is the primary constraint or when…
Use PicassoWeb MCP tools to inspect rendered websites, collect precise replication evidence, and verify replicas. Apply when choosing or sequencing PicassoWeb tools; do not use it for general-purpose browser automation.
★not rated 2▲
+1 1mo agoA43 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: