Operate Feishu/Lark as the logged-in user via the @yoreland/lark-cli-mcp MCP server — messaging (send/read/reply/search), people & chat lookup, cloud documents (search/read/create/update), Drive & Wiki, and Bitable (multi-dimensional tables). Use whenever the user wants to (1) send/read/reply/search Feishu messages…
Answer questions about monthly sales performance from the local sales database. Query revenue, deals, and gross margin by year/region/segment; detect significant revenue drops; escalate anomalies for human review. Keywords: sales, revenue, deals, margin, anomaly, region, segment, enterprise, mid-market, EMEA, North…
Read and analyse a Salesforce Apex debug log — exceptions/FATALERROR, governor-limit consumption (SOQL/DML/CPU/heap), the execution call tree, and slow or repeated code units — then ground every finding in the org graph (map the log's code units/methods to qnames and explain WHY with trace/governor/analyzefield). Use…
VisualQ Quality MCP workflows for coding agents — VRT/FRT gates, rolling health, onboarding, Jira QA. Use when the user asks about VisualQ, VRT, FRT, PR quality gates, merge blockers, or site quality scores.
Audit a public website's SEO and GEO readiness with the Yueliu MCP, extract traceable first-party brand evidence, prepare deterministic GEO measurement questions, and produce a prioritized action plan. Use when a user asks for a website audit, AI-search readiness review, brand evidence check, GEO question set, or…
Use this skill for repositories managed through the git-mcp server when the task involves Git inspection, staging or committing, branches, remotes, rebase, cherry-pick, stash, bisect, worktrees, Git Flow, LFS, release tagging, PR preparation, or recovery. Prefer git-mcp tools over shell git commands, including when…
Use when a user wants to keep a note, or when an LLM dialogue produces a reusable concept, method, prompt, decision, troubleshooting pattern, reference, boundary, distinction, example, or rule worth turning into a fillable personal knowledge-base note.
Use when Codex should automate Google NotebookLM through the local notebooklm-py CLI or help install/configure NotebookLM automation. Trigger for requests mentioning NotebookLM, /notebooklm, notebooklm-py, creating NotebookLM notebooks, adding URLs/PDFs/YouTube/files as sources, asking a NotebookLM notebook questions…
Grounded retrieval over ingested structured-document corpora (legal codes, contracts, regulations, specs, manuals) with hierarchical breadcrumb citations, via the ScribblesLM MCP server. Not a web/general-knowledge tool.
Score a fresh inbound conversation against a qualification rubric, tag it, and prepare a routing recommendation and reply draft without sending anything.
NiftyPM Project Management skill for AI agents — teaches agents to be an effective Project Manager/assistant using the NiftyPM MCP tools. Covers the full NiftyPM hierarchy (Portfolios, Projects, Task Lists, Tasks, Subtasks, Milestones, Dependencies, Docs, Files, Goals), domain-specific workflows for academic research…
Manage MCP servers with mcp-hub — discover/search servers, add and configure them from their docs, wire secrets to the OS keychain, reload, verify, and troubleshoot. Use when adding/removing/configuring an MCP server in mcp-hub, when the user says "add mcp to mcp hub", or asks how to find or manage MCP servers.
Search the web and extract content from webpages using curl and bash/bat. Use when the user wants to search the web, look something up online, read a webpage, or extract information from a URL.
Use this skill when conducting a professional LLM fine-tuning engagement in Zero-Data mode via the MCP server fine-tuning-os. Triggers on: prestation de fine-tuning LLM, livraison de modèle affiné, pipeline Zero-Data, orchestration des 64 outils fine-tuning-os, cycle de vie entraînement (préparation / données…
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: