Pm Claude Skills runs on your own machine — the client starts it, so there is no endpoint to ping. 2 426 installs a week from npm. Last commit 16 Sep 2026.
1174 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.
We read the source, 17 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
postinstall: node bin/postinstall.mjs
else pr = await api('POST', `/repos/${REPO}/pulls`, { title: `Update ${changes.length} pm-skill(s) to latest`, head: BRANCH, base, body });
const png = path.join(__dirname, s.out);
import { readFileSync, writeFileSync, readdirSync, existsSync, statSync } from 'node:fs';
const r = await fetch(`https://api.telegram.org/bot${token}/${method}`, {
el('tracks').innerHTML=TRACKS.map(t=>{
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add pm-claude-skills -- npx -y pm-claude-skills
{
"mcpServers": {
"pm-claude-skills": {
"args": [
"-y",
"pm-claude-skills"
],
"command": "npx"
}
}
}
[mcp_servers.pm-claude-skills]
command = "npx"
args = ["-y", "pm-claude-skills"]
{
"mcpServers": {
"pm-claude-skills": {
"args": [
"-y",
"pm-claude-skills"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"pm-claude-skills": {
"args": [
"-y",
"pm-claude-skills"
],
"command": "npx"
}
}
}
Search the HeyClaude directory of Claude Code agents, MCP servers, skills, and tools.
Search and retrieve agent instruction files: system prompts, skills, workflows, and safety filters.
Try other agents, models, and skills from your familiar AI workflow through a local MCP server
Visual workflow memory: search, read, and freeze MindFlows workflows from any agent.
Real-time cost awareness for MCP agent workflows
Cloudflare Workers MCP server: agent-workflow-engine
Composable skill packets, harvests, workflow routing, and release/audit rubrics over MCP.
MCP server for AIShelf - allows AI model to choose workflows, rules, skills, and prompts for a task
Answers built from our own checks of this server.