A guided seven-stage process for writing a long-form blog post, either from scratch or from an existing outline. It can use a project voice profile or inline tone guidance.

Use it to plan and write blog posts or articles, continue from a prepared outline, and shape the result to match a defined voice.

It breaks a large writing task into decisions about the idea, audience, purpose, context, and writing style before drafting.

write-post — Skill for Claude Code by ondrej-svec

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add ondrej-svec/heart-of-gold-toolkit --skill write-post

Clone the repo

git clone --depth 1 https://github.com/ondrej-svec/heart-of-gold-toolkit

Made for: Claude Code.

Or install guide, the plugin that ships this one along with the rest of its 7 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/write-post/github.svg)](https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/write-post)

Your own site

<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/write-post"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/write-post/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/write-post"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/write-post.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 712 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00041	$0.00712
Opus 5	$0.00020	$0.00356
Sonnet 5	$0.00008	$0.00142
Haiku 4.5	$0.00004	$0.00071

Measured 12d ago against content hash 832a51e9ed3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

write-post scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/guide/skills/write-post/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/guide:write-post — Blog Post Writing

Write a long-form blog post from scratch or from a pipeline-generated outline.

A 7-phase guided writing process that helps you write an authentic blog post in your voice.

Getting Started

This skill can start two ways:

From a pipeline outline — If a blog outline exists in content/drafts/ with needs_write_post: true in its frontmatter, offer to pick up from that outline and start from that context.
From scratch — If no outline exists or the user wants to start fresh, begin with the context phase. This preserves the current behavior of the original /write-post skill.

Voice Profile

Read the voice profile from config.yaml at voice.reference path. If the voice profile file is missing or unavailable, fall back to inline voice hints from the voice.tone config field. The skill should still work without a voice reference — use the tone keywords as style anchors.

The 7 Phases

Phase 1: Context

Gather context for the post:

What's the core idea or experience?
Who is the audience?
What should the reader feel or do after reading?
Read any existing blog outline (from pipeline or user-provided)

Phase 2: Scaffold

Create the post structure:

Build an outline following the emotional arc (hook → scene → mess → moment → reflection → soft landing)
Map each section to specific experiences, signals, or insights
Identify the emotional thread that ties everything together

Phase 3: Dictate

Write the first draft:

Encourage the user to speak/write freely — capture raw voice
Don't edit for polish yet — get the ideas down
Preserve authentic phrasing and emotional moments

Phase 4: Shape

Shape the raw draft into a structured post:

Apply the scaffold structure
Ensure smooth transitions between sections
Check that the emotional arc flows naturally
Maintain the user's authentic voice throughout

Phase 5: Iterate

Refine the draft:

Read aloud — does it sound like the user?
Check for jargon, corporate-speak, or generic language
Tighten sentences (target under 25 words each)
Ensure first-person voice is consistent
Get user feedback and incorporate changes

Read the full file on GitHub · 89 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago First seen · 89 lines · 41 tokens per session scan A 832a51e9ed3f

Subscribe to this mod's changes

write-post is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 22d ago), licensed MIT. It adds 41 tokens to every session and 712 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens