Agent skill

Add Prompt

by cyanheads in cyanheads/pubmed-mcp-server

Scaffold a new MCP prompt template. An agent skill from cyanheads/pubmed-mcp-server.

Apache-2.0Auto-check passedAgent Workflows

Install Add Prompt

skills CLI

$ npx skills add cyanheads/pubmed-mcp-server --skill add-prompt -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install cyanheads/pubmed-mcp-server add-prompt --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/cyanheads/pubmed-mcp-server.git skills-src && mkdir -p .claude/skills && cp -r skills-src/framework-skills/add-prompt .claude/skills/add-prompt && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "add-prompt" agent skill from https://github.com/cyanheads/pubmed-mcp-server/tree/main/framework-skills/add-prompt into .claude/skills/add-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-prompt", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/cyanheads/pubmed-mcp-server/tree/main/framework-skills/add-prompt

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add cyanheads/pubmed-mcp-server --skill add-prompt -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install cyanheads/pubmed-mcp-server add-prompt --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/cyanheads/pubmed-mcp-server.git skills-src && mkdir -p .agents/skills && cp -r skills-src/framework-skills/add-prompt .agents/skills/add-prompt && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "add-prompt" agent skill from https://github.com/cyanheads/pubmed-mcp-server/tree/main/framework-skills/add-prompt into .agents/skills/add-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-prompt", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add cyanheads/pubmed-mcp-server --skill add-prompt -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install cyanheads/pubmed-mcp-server add-prompt --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/cyanheads/pubmed-mcp-server.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/framework-skills/add-prompt .cursor/skills/add-prompt && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "add-prompt" agent skill from https://github.com/cyanheads/pubmed-mcp-server/tree/main/framework-skills/add-prompt into .cursor/skills/add-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-prompt", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/cyanheads/pubmed-mcp-server.git --path framework-skills/add-prompt

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add cyanheads/pubmed-mcp-server --skill add-prompt -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install cyanheads/pubmed-mcp-server add-prompt --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/cyanheads/pubmed-mcp-server.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/framework-skills/add-prompt .gemini/skills/add-prompt && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "add-prompt" agent skill from https://github.com/cyanheads/pubmed-mcp-server/tree/main/framework-skills/add-prompt into .gemini/skills/add-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-prompt", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install cyanheads/pubmed-mcp-server add-prompt

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add cyanheads/pubmed-mcp-server --skill add-prompt -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/cyanheads/pubmed-mcp-server.git skills-src && mkdir -p .github/skills && cp -r skills-src/framework-skills/add-prompt .github/skills/add-prompt && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "add-prompt" agent skill from https://github.com/cyanheads/pubmed-mcp-server/tree/main/framework-skills/add-prompt into .github/skills/add-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-prompt", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add cyanheads/pubmed-mcp-server --skill add-prompt -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install cyanheads/pubmed-mcp-server add-prompt --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/cyanheads/pubmed-mcp-server.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/framework-skills/add-prompt .opencode/skills/add-prompt && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "add-prompt" agent skill from https://github.com/cyanheads/pubmed-mcp-server/tree/main/framework-skills/add-prompt into .opencode/skills/add-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "add-prompt", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: add-prompt
GitHub stars: 158
Token cost: ~1.6k tokens
SKILL.md length: 461 words
Files: 1
Skills in repo: 30
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Scaffold a new MCP prompt template. An agent skill from cyanheads/pubmed-mcp-server.

Works in 5 steps: Gather the prompt's name, purpose, and… → Create the file at… → Register the prompt in the project's… → …
The user asks to add a prompt
SKILL.md covers Context, Steps, Template and Argument autocompletion, plus 1 more section
Calls bun

What it does

Add Prompt is an agent skill from cyanheads/pubmed-mcp-server. Scaffold a new MCP prompt template. Use when the user asks to add a prompt, create a reusable message template, or define a prompt for LLM interactions.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Prompt engineering and MCP servers. It works with Model Context Protocol. The repository describes itself as: Search PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms via MCP. STDIO or Streamable HTTP. The licence is Apache-2.0.

When your agent uses it

The user asks to add a prompt
Create a reusable message template
Define a prompt for LLM interactions

Example prompts

“/add-prompt”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

Gather the prompt's name, purpose, and arguments from the user's request — ask only if genuinely absent
Create the file at src/mcp-server/prompts/definitions/{{prompt-name}}.prompt.ts
Register the prompt in the project's existing createApp() prompt list (directly in src/index.ts for fresh scaffolds, or via a barrel if…
Run bun run devcheck to verify
Smoke-test with bun run rebuild && bun run start:stdio < /dev/null — the Core services constructed log record must list the new prompt in…

What it can do on your machine

Read from SKILL.md and the folder at commit 79145a6. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- bun
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Add Prompt loads about 1.6k tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 461 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~41
When it runs · the whole SKILL.md, loaded when a task matches: ~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cyanheads/pubmed-mcp-server at commit 79145a6, republished under its Apache-2.0 licence (© cyanheads). 461 words, ~1,596 tokens.

Download SKILL.mdSave it as .claude/skills/add-prompt/SKILL.md (or your agent's skills folder).

name: add-prompt
description: Scaffold a new MCP prompt template. Use when the user asks to add a prompt, create a reusable message template, or define a prompt for LLM interactions.
metadata.author: cyanheads
metadata.version: 1.5
metadata.audience: external
metadata.type: reference

Context

Prompts use the prompt() builder from @cyanheads/mcp-ts-core. Each prompt lives in src/mcp-server/prompts/definitions/ with a .prompt.ts suffix. The standard registration pattern uses a definitions/index.ts barrel that collects all prompts into an allPromptDefinitions array for createApp(). Fresh scaffolds start with direct imports in src/index.ts — the barrel is introduced as definitions grow. Match the pattern already used by the project you're editing.

Prompts are pure message templates — no Context, no auth, no side effects. generate can be sync or async (returns PromptMessage[] | Promise<PromptMessage[]>).

Steps

Gather the prompt's name, purpose, and arguments from the user's request — ask only if genuinely absent
Create the file at src/mcp-server/prompts/definitions/{{prompt-name}}.prompt.ts
Register the prompt in the project's existing createApp() prompt list (directly in src/index.ts for fresh scaffolds, or via a barrel if the repo already has one)
Run bun run devcheck to verify
Smoke-test with bun run rebuild && bun run start:stdio < /dev/null — the Core services constructed log record must list the new prompt in its prompts field (the message text shows only counts); if it doesn't, the prompt never reached createApp()

Template

typescript

/**
 * @fileoverview {{PROMPT_DESCRIPTION}}
 * @module mcp-server/prompts/definitions/{{PROMPT_NAME}}
 */

import { completable, prompt, z } from '@cyanheads/mcp-ts-core';

export const {{PROMPT_EXPORT}} = prompt('{{prompt_name}}', {
  description: '{{PROMPT_DESCRIPTION}}',
  // title is optional — human-readable display name surfaced in prompts/list.
  // title: '{{PROMPT_DISPLAY_TITLE}}',
  // args is optional — omit entirely for prompts with no parameters.
  // When present, all fields need .describe(). Only JSON-Schema-serializable types allowed.
  // Wrap any field with completable() to enable argument autocompletion.
  args: z.object({
    // All fields need .describe()
    // language: completable(z.string().describe('Language'), async (partial) => matchingLanguages(partial)),
  }),
  generate: (args) => [
    {
      role: 'user',
      content: {
        type: 'text',
        text: `{{PROMPT_TEMPLATE_TEXT}}`,
      },
    },
  ],
});

Multi-message prompt

typescript

generate: (args) => [
  {
    role: 'user',
    content: {
      type: 'text',
      text: `Here is the ${args.type} to review:\n\n${args.content}`,
    },
  },
  {
    role: 'assistant',
    content: {
      type: 'text',
      text: 'I will analyze this carefully. Let me start with...',
    },
  },
],

Registration

typescript

// src/index.ts (fresh scaffold default)
import { createApp } from '@cyanheads/mcp-ts-core';
import { {{PROMPT_EXPORT}} } from './mcp-server/prompts/definitions/{{prompt-name}}.prompt.js';

await createApp({
  tools: [/* existing tools */],
  resources: [/* existing resources */],
  prompts: [{{PROMPT_EXPORT}}],
});

If the repo already uses src/mcp-server/prompts/definitions/index.ts, add the prompt to that barrel the way it holds the existing ones — it must end up in the array passed to createApp(). A bare export … from line registers nothing on its own. The standard barrel shape:

typescript

import { {{PROMPT_EXPORT}} } from './{{prompt-name}}.prompt.js';

export const allPromptDefinitions = [/* existing prompts */, {{PROMPT_EXPORT}}];

Argument autocompletion

Wrap any args field with completable() (re-exported from @cyanheads/mcp-ts-core) to enable argument autocompletion. The SDK auto-installs completion/complete handling and advertises the completions capability when any registered prompt has a completable argument — no other changes are needed.

typescript

import { completable, prompt, z } from '@cyanheads/mcp-ts-core';

export const codeReview = prompt('code_review', {
  description: 'Review code for issues.',
  title: 'Code Review',
  args: z.object({
    language: completable(
      z.string().describe('Programming language'),
      async (partial) => ['typescript', 'python', 'rust'].filter((l) => l.startsWith(partial)),
    ),
    code: z.string().describe('Code to review'),
  }),
  generate: (args) => [
    { role: 'user', content: { type: 'text', text: `Review this ${args.language} code:\n${args.code}` } },
  ],
});

completable() is transparent to the linter — it does not affect describe-on-fields or schema-serializable rules. All completable-wrapped fields still require .describe() on the underlying schema.

For an optional argument, wrap the inner schema and apply .optional() outside: completable(z.string().describe('…'), cb).optional(). The SDK unwraps .optional() before checking for a completer, so completable(z.string().optional(), cb) type-checks but never completes.

Show full SKILL.md (144 more words)Show less

Checklist

File created at src/mcp-server/prompts/definitions/{{prompt-name}}.prompt.ts
Prompt name passed to prompt() uses snake_case
description field set (lint warns if absent, but devcheck won't hard-fail — verify it's present)
title field set if a human-readable display name is needed in prompts/list
All Zod args fields have .describe() annotations — or args omitted entirely for no-parameter prompts
args fields use only JSON-Schema-serializable Zod types (no z.date(), z.transform(), z.bigint(), z.symbol(), z.custom(), etc.)
If using completable(), the underlying schema still has .describe() on each wrapped field
JSDoc @fileoverview and @module header present
generate function present and returns at least one { role, content: { type: 'text', text } } message
No side effects — prompts are pure templates
Registered in the project's existing createApp() prompt list (directly or via barrel)
bun run devcheck passes
Smoke-tested with bun run rebuild && bun run start:stdio < /dev/null; the Core services constructed record lists the new prompt in its prompts field

Files

Just SKILL.md in framework-skills/add-prompt of cyanheads/pubmed-mcp-server.

Open the folder on GitHubat commit 79145a6

Compare with similar skills

Add Prompt next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Add Prompt compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Add Prompt this skillcyanheads/pubmed-mcp-server	158	—	~1.6k	Automated safety check: Pass	Apache-2.0	yesterday
Workflow Schema Tuningbreaking-brake/cc-wf-studio	5.4k	—	~1.3k	Automated safety check: Pass	Custom licence	4 days ago
Cco Overheadegorfedorov/claude-context-optimizer	114	—	~606	Automated safety check: Pass	MIT	11 days ago
MCP Developmentrohitg00/awesome-claude-code-toolkit	2.7k	—	~1.2k	Automated safety check: Pass	Apache-2.0	5 mo ago
Spring AI MCP Server Patternsgiuseppe-trisciuoglio/developer-kit	357	—	~2.7k	Automated safety check: Notes	MIT	1 mo ago
Agentforce GenerateSalesforceAIResearch/agentforce-adlc	114	1 repos	~7.4k	Automated safety check: Pass	Custom licence	28 days ago

Similar skills

Workflow Schema Tuning
breaking-brake/cc-wf-studio
Guides edits to cc-wf-studio's workflow schema so AI agents generate better workflows, treating schema text as prompt engineering rather than validation.
5.4k GitHub stars~1.3k tokensUpdated 4 days ago
Agent WorkflowsAuto-check passed
Cco Overhead
egorfedorov/claude-context-optimizer
Audit the fixed context overhead every session starts with — system prompt, MCP tools, agents, CLAUDE.md, memory — measured from real transcript usage
114 GitHub stars~606 tokensUpdated 11 days ago
Agent WorkflowsAuto-check passed
MCP Development
rohitg00/awesome-claude-code-toolkit
MCP server development including tool design, resource endpoints, prompt templates, and transport configuration
2.7k GitHub stars~1.2k tokensUpdated 5 mo ago
Agent WorkflowsAuto-check passed
Spring AI MCP Server Patterns
giuseppe-trisciuoglio/developer-kit
Provides Spring Boot MCP server patterns that create Model Context Protocol servers with Spring AI by defining tool handlers, exposing resources, configuring prompt templates, and setting up…
357 GitHub stars~2.7k tokensUpdated 1 mo ago
Agent WorkflowsAuto-check: notes
Agentforce Generate
SalesforceAIResearch/agentforce-adlc
Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script.
114 GitHub starsUsed in 1 repo~7.4k tokens
Agent WorkflowsAuto-check passed
Hcls Build Agent
aws-samples/amazon-bedrock-agents-healthcare-lifesciences
Official
A skill your agent uses when a developer wants to build a new healthcare or life sciences agent, structure tools and system prompts for an HCLS workflow, or create a Strands agent with…
274 GitHub stars~885 tokensUpdated 9 days ago
Research & ScienceAuto-check passed

Questions about Add Prompt

What does Add Prompt do?

Scaffold a new MCP prompt template. An agent skill from cyanheads/pubmed-mcp-server. Add Prompt is an agent skill from cyanheads/pubmed-mcp-server. Scaffold a new MCP prompt template.

When should I use Add Prompt?

Add Prompt fits situations like: the user asks to add a prompt; create a reusable message template; define a prompt for LLM interactions.

How do I install Add Prompt in Claude Code?

Run `npx skills add cyanheads/pubmed-mcp-server --skill add-prompt -a claude-code`. Or copy the skill folder (framework-skills/add-prompt in cyanheads/pubmed-mcp-server) into .claude/skills/add-prompt in your project. Claude Code loads it when a task matches its description.

How do I install Add Prompt in Codex?

Run `npx skills add cyanheads/pubmed-mcp-server --skill add-prompt -a codex`. Or copy the skill folder (framework-skills/add-prompt in cyanheads/pubmed-mcp-server) into .agents/skills/add-prompt in your project. Codex loads it when a task matches its description.

Can I use Add Prompt in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cyanheads/pubmed-mcp-server --skill add-prompt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/add-prompt, .gemini/skills/add-prompt, .github/skills/add-prompt and .opencode/skills/add-prompt in your project.

What does Add Prompt need to run?

Going by SKILL.md and its folder, Add Prompt needs the command-line tools its instructions call (bun).

Does Add Prompt access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Add Prompt safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Add Prompt use?

Add Prompt is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Add Prompt use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Add Prompt?

Skills that share tags, products or a category with Add Prompt: Workflow Schema Tuning (breaking-brake/cc-wf-studio, 5.4k stars), Cco Overhead (egorfedorov/claude-context-optimizer, 114 stars), MCP Development (rohitg00/awesome-claude-code-toolkit, 2.7k stars) and Spring AI MCP Server Patterns (giuseppe-trisciuoglio/developer-kit, 357 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Add Prompt?

cyanheads (a GitHub user) maintains it in cyanheads/pubmed-mcp-server, which has 158 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 9, 2026.

Source: cyanheads/pubmed-mcp-server on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Add Prompt

Install Add Prompt

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Context

Steps

Template

Multi-message prompt

Registration

Argument autocompletion

Checklist

Files

Compare with similar skills

Similar skills

Workflow Schema Tuning

Cco Overhead

MCP Development

Spring AI MCP Server Patterns

Agentforce Generate

Hcls Build Agent

More from cyanheads/pubmed-mcp-server

Add App Tool

Add Resource

Add Service

Add Test

API Auth

API Mirror

Questions about Add Prompt

Install Add Prompt

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Context

Steps

Template

Multi-message prompt

Registration

Argument autocompletion

Checklist

Files

Compare with similar skills

Similar skills

More from cyanheads/pubmed-mcp-server

Related

Questions about Add Prompt