gitnexus-guide
Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples:…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
gitnexus-pdg-query
Use when querying or extending GitNexus's PDG control/data-dependence surface (the `pdg_query` MCP tool, CDG/REACHING_DEF edges), or reasoning about "what…
pmem-style-generation
Generate a manuscript with a personal imprint based on the Style Profile in powermem. First neutrally extract the core information of the material, then pull the style Profile to assemble a Compiler Prompt to drive the large model's output. Use this when the user mentions "help me write an article", "write in my style", "generate an article", "write a tweet", "write a Xiaohongshu post", "write a WeChat official account article", or provides material and requests creation…
workflow-creator
Guide users to create standardized Talos workflows. Triggered when users want to create a new workflow, design an AI coding process, build a multi-stage agent pipeline, or say "help me create a workflow", "design a process", "automate XX", "create a pipeline", "build a workflow".
mcp-oauth-setup
Implement MCP server authentication with OAuth Dynamic Client Registration (RFC 7591), Authorization Server Metadata Discovery (RFC 8414), and generalized…
conversation-memory
Search and recall past conversations from Claude Code history and Cursor agent transcripts. Gives your AI agent memory across sessions so you never re-explain…
using-decision-tree
Which skill or recipe owns this task, in what order. Invoke BEFORE doing by hand any task the kernel routing index does not name (.pdf read or fill, test plan,…
see
Analyze images and videos via ZenMux API (Gemini backend). Use for: any video (local or URL), image URLs, webpages with embedded video (e.g. YouTube), or local…
memory-audit
Comprehensive health check across CC auto-memory and agent-studio memory systems — detects orphans, duplicates, staleness, and threshold violations
xlsx
Excel spreadsheet generation using openpyxl and xlsxwriter. Convert Claude output, data analysis results, and tabular data into formatted .xlsx files with…
automation-memory
Resolve and maintain recurring Codex automation memory safely. MUST use whenever prompts include Automation:, Automation ID:, or Automation memory:, especially…
configure-ecc
Interactive installer for Everything Claude Code — guides users through selecting and installing skills and rules to user-level or project-level directories,…
iterative-retrieval
Pattern for progressively refining context retrieval to solve the subagent context problem
cmd-code-what
Catch the user up on what the agent has been doing in the current session with 3-5 ultra-tight bullet points. Use when the user invokes /cmd-what, asks "what…
cmd-codex-review-unstaged
Get a second opinion on what Claude just implemented from Codex (codex exec headless mode). Pipes Claude's summary plus the working-tree diff to codex, asks…
cmd-skills-review
Audit personal skills for redundancy, verbosity, weak triggers, and overlap. Runs a Claude→Codex review loop, presents per-item approval checkboxes, then…
payment-plan-drafter
Propose a fair installment plan for a client who can't pay in full, plus the email to offer it. Use when the user says "payment plan", "installment plan",…
gsd-browser
Open GSD native browser automation for AI agents. Use gsd-browser when the user needs real Chrome/Chromium control: navigate pages, inspect localhost, click,…
cess
Apply Counterexample-Supplemented Sketches (CESS) to open-world agent and software synthesis. Use when a user mentions CESS, Sketch-CE,…
om-create-ai-agent
Build, override, or extend a typed Open Mercato AI agent (chat or structured-object) using the unified AI framework — declare `ai-agents.ts`, register tool…
connector-review
Review an OpenMetadata connector against golden standards. Runs multi-agent analysis covering architecture, code quality, type safety, testing, and…
building-mcp-server-on-cloudflare
Builds remote MCP (Model Context Protocol) servers on Cloudflare Workers with tools, OAuth authentication, and production deployment. Generates server code,…
vercel-agent
Vercel Agent guidance — AI-powered code review, incident investigation, and SDK installation. Automates PR analysis and anomaly debugging. Use when configuring…
convex-agent
Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.