# Writing Agent - Human Style ## Links - Product page URL: https://www.agentpmt.com/marketplace/writing-agent-human-style - Product markdown URL: https://www.agentpmt.com/marketplace/writing-agent-human-style?format=agent-md - Product JSON URL: https://www.agentpmt.com/marketplace/writing-agent-human-style?format=agent-json ## Overview - Product ID: 6a0be2087636f77a3fd97d02 - Type: model - Unit type: request - Price: 1000 credits - Categories: Social Media Management, Marketing Automation, AI Copywriting & Text Generation, Blog & Article Writing - Generated at: 2026-06-30T03:40:51.228Z ### Page Description Writing Agent is an AI writing assistant that drafts on-brand social media replies, original social posts, short-form blog posts up to 12,000 characters, and larger blog posts up to 30,000 characters — in your voice, ready to review and publish. Give it a topic, your brand voice, and any notes you want it to use, and get back polished, human-sounding copy that respects your requested character limit. Generate up to ten tailored replies in a single request, spin up original posts from a topic, turn an outline and a few notes into a clean Markdown short blog draft, or create a larger long-form Markdown article. Because it writes only from the facts you provide — never inventing claims, stats, or links — every draft stays accurate and on-message. ### Agent Description Draft on-brand text and Markdown copy from a compact request plus one optional JSON `context` object. Use `draft_social_responses` for one reply per source post (1–10 posts, up to 500 characters each), `draft_social_post` for one original social post (up to 5,000 characters), `draft_short_blog_post` for a Markdown blog draft up to 12,000 characters, and `draft_large_blog_post` for a larger Markdown blog draft up to 30,000 characters. For blog actions, provide `topic` and `max_characters`. Put all writing guidance and source material — voice, goal, audience, outline, examples, brand context, source material, constraints, and instructions — inside the single `context` object rather than as separate fields. Output is returned inline as text or Markdown; requested character limits are enforced, with truncation warnings if a draft is trimmed to fit. The agent writes only from the facts you supply and will not invent claims, statistics, URLs, or offers. This tool drafts copy only — it does not publish, browse the web, or accept files, images, audio, or video. ## Details ### Details Writing Agent is an AI writing assistant that drafts on-brand social media replies, original social posts, short-form blog posts up to 12,000 characters, and larger blog posts up to 30,000 characters — in your voice, ready to review and publish. Give it a topic, your brand voice, and any notes you want it to use, and get back polished, human-sounding copy that respects your requested character limit. Generate up to ten tailored replies in a single request, spin up original posts from a topic, turn an outline and a few notes into a clean Markdown short blog draft, or create a larger long-form Markdown article. Because it writes only from the facts you provide — never inventing claims, stats, or links — every draft stays accurate and on-message. ### Actions - `draft_social_responses` (20 credits): Generate one short brand-appropriate social media response for each supplied post, up to ten posts per request. - `draft_social_post` (10 credits): Generate one original social media post from a topic, character limit, and optional JSON context. - `draft_short_blog_post` (30 credits): Generate one short-form blog post in Markdown from a topic, character limit, and optional JSON context. Provide max_characters from 100 to 12,000. - `draft_large_blog_post` (50 credits): Generate one larger blog post in Markdown from a topic, character limit, and optional JSON context. Provide max_characters from 100 to 30,000. ### Use Cases Draft up to 10 on-brand social media replies in a single request, Write original social posts from a topic and a few notes, Turn an outline and source material into a short Markdown blog post up to 12,000 characters, Draft larger long-form Markdown blog posts up to 30,000 characters, Keep every draft within an exact character limit, Maintain a consistent brand voice across your whole team, Turn campaign briefs and brand notes into ready-to-review copy, Reply to customer and community posts in your tone at scale, Produce accurate drafts that stick to the facts you provide, Speed up content review workflows with publish-ready text, Scale social and blog content creation without losing your voice ### Workflows Using This Tool #### X (Twitter) Thought Leadership Engine: Human-Voice AI Posts from Industry News with Approval and Auto-Publish Stay visible on X (Twitter) every week without staring at a blank compose box. Give this AI social media workflow your beats and your positioning, and it scans the last week of industry news, picks the strongest non-overlapping angles, and writes opinionated, fact-backed posts in a natural human voice that sounds like you, not a press release. Every post is screened by an automated writing quality check that strips robotic, overused AI phrasing, and posts that benefit from a visual get a custom 16:9 image. All drafts queue in a Google Sheet and come to you for batch approval, and the workflow checks back for your decision at 5 and 10 minutes. Approve and it publishes to X, attaching images and links correctly, then marks each row with the live post link so you keep a complete content log. Miss the window and nothing posts: every draft stays safely queued in the sheet, ready to approve and publish on a later run. Ideal for founders, executives, consultants, developer advocates, and marketers who want Twitter automation with editorial control: AI-generated social media posts, social SEO, personal branding, content marketing, and a consistent thought leadership presence built on real facts and a human voice. - Page URL: https://www.agentpmt.com/agent-workflow-skills/x-thought-leadership-engine-turn-industry-news-into-human-voice-posts-with-approval-and-auto-publish - Markdown URL: https://www.agentpmt.com/agent-workflow-skills/x-thought-leadership-engine-turn-industry-news-into-human-voice-posts-with-approval-and-auto-publish?format=agent-md - Published: 2026-06-10T20:59:52.887Z #### Pipedrive AI Email Writer: Personalized Human-Voice Nurture and Follow-Up Drafts for Any CRM Segment Turn any Pipedrive segment into a set of genuinely personal sales emails, written one contact at a time and waiting in your Gmail drafts for your final say. Point this AI email writing workflow at a pipeline stage, an owner, a label, or stalled deals with no recent activity, and it pulls each contact's deal history and notes from Pipedrive, finds the strongest personal hook for every relationship, and writes each email in a natural human voice around your goal: re-engaging a quiet deal, a renewal check-in, post-sale nurture, an upsell conversation, or a simple hello. Every email passes an automated writing quality check that catches robotic, overused AI phrasing and rewrites it before you ever see it. Nothing is sent automatically. Each message lands as a Gmail draft for you to review and send personally, while the workflow logs a note and a follow-up activity on every deal in Pipedrive, records the campaign in a Google Sheets log, and emails you a summary of what is ready. Built for account executives, customer success teams, founders doing their own outreach, sales follow-up and renewal plays, and anyone who wants CRM email automation that produces one-to-one messages that read like they wrote them. - Page URL: https://www.agentpmt.com/agent-workflow-skills/pipedrive-nurture-email-writer-personalized-human-voice-outreach-drafts-for-any-crm-segment - Markdown URL: https://www.agentpmt.com/agent-workflow-skills/pipedrive-nurture-email-writer-personalized-human-voice-outreach-drafts-for-any-crm-segment?format=agent-md - Published: 2026-06-10T20:59:48.301Z #### Human-Voice AI Blog Writer: Research, Write, and Illustrate SEO Articles from Your Content Calendar Turn a topic or a content-calendar spreadsheet into a publish-ready, fact-checked blog article written in a natural human voice. This AI blog writing workflow picks the next due topic from your Google Sheet (or takes one directly), researches it across live news and authoritative web sources, builds a sourced fact sheet and SEO outline, then drafts the full long-form article with a human-style writing agent that writes only from verified facts. Every draft runs through an automated writing quality check that catches robotic, banned AI phrases and rewrites them until the copy passes. A custom hero image is generated to match the story, the finished article is assembled into a formatted Google Doc with a sources section, the run is logged back to your content calendar, and the doc link lands in your inbox. Ideal for content marketing teams, SEO agencies, founders, newsletters, and solo bloggers who want an AI blog post generator and content automation pipeline that delivers consistent, on-brand, long-form SEO content without the research grind or the telltale AI voice. - Page URL: https://www.agentpmt.com/agent-workflow-skills/human-voice-blog-factory-research-write-illustrate-and-deliver-seo-articles-from-your-content-calendar - Markdown URL: https://www.agentpmt.com/agent-workflow-skills/human-voice-blog-factory-research-write-illustrate-and-deliver-seo-articles-from-your-content-calendar?format=agent-md - Published: 2026-06-10T20:59:39.285Z ### Related Content #### Creative Content Automation, Human-Voice Copy on AgentPMT - Type: article - Page URL: https://www.agentpmt.com/articles/creative-content-automation-human-voice-copy-on-agentpmt - Markdown URL: https://www.agentpmt.com/articles/creative-content-automation-human-voice-copy-on-agentpmt?format=agent-md Writing Agent - Human Style is a new AgentPMT agent tool that drafts human-sounding social replies, original posts, and Markdown blog articles strictly from the facts you supply, never inventing claims or links. It plugs straight into live automations like the X posting engine, the Human-Voice AI Blog Writer, and the Pipedrive AI Email Writer. ## Integration Details ### DynamicMCP - Setup page URL: https://www.agentpmt.com/dynamic-mcp - Claude setup guide: https://www.agentpmt.com/dynamic-mcp#platform=claude - ChatGPT setup guide: https://www.agentpmt.com/dynamic-mcp#platform=chatgpt - Cursor setup guide: https://www.agentpmt.com/dynamic-mcp#platform=cursor - Windsurf setup guide: https://www.agentpmt.com/dynamic-mcp#platform=windsurf Use the local router for command-based MCP clients. It forwards requests to `https://api.agentpmt.com/mcp` and does not execute tools locally. ```bash npm install -g @agentpmt/mcp-router agentpmt-setup ``` ### REST API The live page renders cURL, Python, JavaScript, and Node.js examples. Logged-in users see those examples prefilled with their own API and budget credentials. - Purchase endpoint: https://api.agentpmt.com/products/purchase - Authorization format: `Bearer ` ```bash curl -X POST "https://api.agentpmt.com/products/purchase" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer eW91ci1hcGkta2V5LWhlcmU6eW91ci1idWRnZXQta2V5LWhlcmU=" \ -d '{ "product_id": "6a0be2087636f77a3fd97d02", "parameters": { "action": "draft_social_responses", "posts": [], "max_characters_per_response": 1 } }' ``` ### Autonomous Agents Autonomous agents can access this tool through AgentAddress credit balances or direct x402 payments. Use the Autonomous Agent API reference for endpoint shapes after choosing the access pattern below. - Autonomous Agent API reference URL: https://www.agentpmt.com/docs/api-reference/autonomous-agents - Autonomous Agent API reference markdown URL: https://www.agentpmt.com/docs/api-reference/autonomous-agents?format=agent-md - Credit-Based Access Using AgentAddress: https://www.agentpmt.com/docs/autonomous-agents/credit-based-tool-usage-with-agentaddress - AgentAddress is preferred for persistent file access, stored platform state, and maximum tool use ability across repeated calls. - Direct x402 is for independent one-off tool calls that do not require shared files or stored platform state. - Direct x402 public payments: USDC on Base, Arbitrum, Optimism, Polygon, and Avalanche. - X402 Payment Instructions: https://www.agentpmt.com/docs/autonomous-agents/x402-payments-for-tool-usage #### Product Skill Package This product has a published Agent Skill package for product-specific operating instructions. - Skill slug: writing-agent-human-style - Version: 1.0.0 - Download SKILL.md: https://raw.githubusercontent.com/AgentPMT/agent-skills/main/skills/writing-agent-human-style/SKILL.md - Package source: https://github.com/AgentPMT/agent-skills/tree/main/skills/writing-agent-human-style - OpenClaw listing: https://clawhub.ai/agentpmt/writing-agent-human-style - OpenClaw install: `openclaw skills install writing-agent-human-style` - skills.sh install: `npx skills add AgentPMT/agent-skills --skill writing-agent-human-style` - Last published: 2026-06-09T21:37:37.120Z ### Schema #### Parameters - Schema type: actions ```json { "actions": { "draft_social_responses": { "description": "Generate one short brand-appropriate social media response for each supplied post, up to ten posts per request.", "properties": { "posts": { "type": "array", "description": "Social posts to respond to. Required. Provide 1 to 10 posts; one response is generated for each post.", "required": true, "items": { "type": "object", "properties": { "post_id": { "type": "string", "description": "Optional caller-provided post identifier, echoed back in response metadata.", "required": false, "maxLength": 120 }, "content": { "type": "string", "description": "Source post content to respond to. Required.", "required": true, "minLength": 1, "maxLength": 5000 } } }, "minItems": 1, "maxItems": 10 }, "max_characters_per_response": { "type": "integer", "description": "Maximum characters for each generated response. Required. Must be 1 to 500.", "required": true, "minimum": 1, "maximum": 500 }, "context": { "type": "object", "description": "Optional JSON object with shared writing guidance and source context. Suggested keys: voice, goal, audience, instructions, source_material, brand_context, examples, constraints. Must serialize to no more than 40,000 characters; combined topic/posts/context input is limited to 85,000 characters before final prompt budget enforcement.", "required": false } }, "price_per_unit": 20 }, "draft_social_post": { "description": "Generate one original social media post from a topic, character limit, and optional JSON context.", "properties": { "topic": { "type": "string", "description": "Topic to write about. Required.", "required": true }, "max_characters": { "type": "integer", "description": "Maximum characters for the generated social post. Required. Must be 1 to 5,000.", "required": true, "minimum": 1, "maximum": 5000 }, "context": { "type": "object", "description": "Optional JSON object with writing guidance and source context. Suggested keys: voice, goal, audience, instructions, source_material, brand_context, examples, constraints, desired_structure. Must serialize to no more than 40,000 characters; combined topic/posts/context input is limited to 85,000 characters before final prompt budget enforcement.", "required": false } }, "price_per_unit": 10 }, "draft_short_blog_post": { "description": "Generate one short-form blog post in Markdown from a topic, character limit, and optional JSON context. Provide max_characters from 100 to 12,000.", "properties": { "topic": { "type": "string", "description": "Topic to write about. Required.", "required": true }, "max_characters": { "type": "integer", "description": "Maximum characters for returned Markdown. Required. Must be 100 to 12,000.", "required": true, "minimum": 100, "maximum": 12000 }, "context": { "type": "object", "description": "Optional JSON object with outline, writing guidance, and source context. Suggested keys: outline, voice, goal, audience, instructions, source_material, brand_context, examples, constraints, desired_structure. Must serialize to no more than 40,000 characters; combined topic/posts/context input is limited to 85,000 characters before final prompt budget enforcement.", "required": false } }, "price_per_unit": 30 }, "draft_large_blog_post": { "description": "Generate one larger blog post in Markdown from a topic, character limit, and optional JSON context. Provide max_characters from 100 to 30,000.", "properties": { "topic": { "type": "string", "description": "Topic to write about. Required.", "required": true }, "max_characters": { "type": "integer", "description": "Maximum characters for returned Markdown. Required. Must be 100 to 30,000.", "required": true, "minimum": 100, "maximum": 30000 }, "context": { "type": "object", "description": "Optional JSON object with outline, writing guidance, and source context. Suggested keys: outline, voice, goal, audience, instructions, source_material, brand_context, examples, constraints, desired_structure. Must serialize to no more than 40,000 characters; combined topic/posts/context input is limited to 85,000 characters before final prompt budget enforcement.", "required": false } }, "price_per_unit": 50 } } } ``` ### Usage Instructions # Writing Agent Generate polished, on-brand text and Markdown drafts — social media replies, original social posts, short-form blog posts, and larger blog posts. Send a compact request plus one optional `context` object, and the tool returns ready-to-review copy that respects your requested character limit. ## Actions ### draft_social_responses Generate one short reply for each social post you supply. Required: - `posts`: 1 to 10 posts, each with `content`; optional `post_id` for your own mapping - `max_characters_per_response`: 1 to 500 characters per reply Optional: - `context`: JSON object with shared writing guidance ### draft_social_post Generate one original social media post. Required: - `topic` - `max_characters`: 1 to 5,000 characters Optional: - `context`: JSON object with writing guidance and source material ### draft_short_blog_post Generate one short-form blog post in Markdown. Required: - `topic` - `max_characters`: 100 to 12,000 characters Optional: - `context`: JSON object with outline, writing guidance, and source material ### draft_large_blog_post Generate one larger blog post in Markdown. Required: - `topic` - `max_characters`: 100 to 30,000 characters Optional: - `context`: JSON object with outline, writing guidance, and source material ## Context Field Put all writing guidance and source material in the single `context` object instead of separate fields. `context` must be a JSON object that serializes to no more than 40,000 characters, and the combined `topic`, `posts` content, and `context` are limited to 85,000 characters per request. Keep it concise and include only material the draft should actually use. Useful context fields: - `voice`: tone, style, and brand voice guidance - `goal`: what the draft should accomplish - `audience`: who the content is for - `instructions`: specific writing instructions - `outline`: requested structure for blog posts or longer drafts - `source_material`: facts, product details, campaign notes, or excerpts to use - `brand_context`: positioning, vocabulary, claims to use or avoid - `examples`: example outputs or style references - `constraints`: words, claims, formats, or topics to avoid - `desired_structure`: requested sections, bullets, or formatting ## Output The tool returns finished writing inline as text or Markdown in `content`. Social response calls also return a `responses` array with one item per input post. If a draft exceeds the requested character limit, the tool trims it to fit and includes `OUTPUT_TRUNCATED_TO_CHARACTER_LIMIT` in `warnings`. The agent writes only from the facts and material you provide — it will not invent claims, statistics, URLs, or offers — so every draft stays accurate and on-message. ## Notes This tool drafts copy only. It does not publish content, browse the web, retrieve URLs, or accept files, images, audio, or video. ### Additional Product Content ## On-brand writing, in your voice Writing Agent drafts polished social media replies, original social posts, short-form blog posts, and larger long-form blog articles that sound like you — not like a robot. Give it a topic, your brand voice, and any notes you want it to use, and get back ready-to-review copy that respects your exact character limits every time. ## What you can create 1. **Social media replies** — generate up to 10 tailored, on-brand replies in a single request, each within your character limit. 2. **Original social posts** — turn a topic and a few notes into a ready-to-publish post. 3. **Short-form blog posts** — go from an outline and source material to a clean Markdown article up to 12,000 characters. 4. **Larger blog posts** — draft long-form Markdown articles up to 30,000 characters for deeper customer education, announcements, guides, and thought leadership. ## Write in your voice Share your tone, audience, goal, key points, examples, and anything to avoid, and every draft comes back on-brand and on-message. Reuse the same guidance across requests so your whole team sounds consistent. ## Accurate by design Writing Agent only writes from the facts and material you provide. It won't invent statistics, quotes, links, or claims — so drafts stay truthful and easy to approve, with a human always in the loop for the final say. ## Who it's for Social media managers, marketing and content teams, founders, agencies, and creators who want consistent, human-sounding copy at scale — from short replies to longer Markdown blog drafts — without the blank-page slog. ### Frequently Asked Questions #### How do I connect this tool to an external agent? - Page URL: https://www.agentpmt.com/faq - Markdown URL: https://www.agentpmt.com/faq?format=agent-md You can install the local MCP server by opening a terminal and running: ``` npm install -g @agentpmt/mcp-router agentpmt-setup ``` This will connect you to local agents like Claude Code, Windsurf, Grok Build, Cursor, etc. Alternatively you can connect to the hosted version with this config block, no installation required: ``` { "mcpServers": { "agentpmt": { "type": "streamable-http", "url": "https://api.agentpmt.com/mcp", "headers": { "Authorization": "Bearer ", "x-instance-metadata": "{\"client\":\"generic-mcp\",\"platform\":\"remote\"}" } } } } ``` [View MCP Connection Instructions](/docs/mcp-reference/connection) for more details. #### How does an external agent use this tool? - Page URL: https://www.agentpmt.com/faq - Markdown URL: https://www.agentpmt.com/faq?format=agent-md After the external agent is connected to an Agent Group that can use this tool, paste this prompt into the agent: > Use the AgentPMT-Tool-Search-and-Execution tool. First call action 'get\_instructions' so you know how to use the tool search interface. Then call action 'get\_schema' with tool\_id 6a0be2087636f77a3fd97d02 ("Writing Agent - Human Style"). After reading the schema and any returned instructions, tell me what this tool can do, we are going to be using it The agent should fetch the tool schema first, collect the required parameters for your request, and then call the tool through AgentPMT. ### Dependencies This product has no public dependency products.