Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Technical Publishing

ASecurity

Prepare and publish technical articles: canonical site and channel copy.

10 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentsbashgitdocumentation

Works with

cli

Security Analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned 10/7/2026

$npx -y skills add fmind/dot --skill technical-publishing --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Technical Publishing?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Technical Publishing
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fmind-technical-publishing/badge)](https://www.skillsdirectory.com/skills/fmind-technical-publishing)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: technical-publishing
description: "Prepare and publish technical articles: canonical site and channel copy."
license: MIT
metadata:
  kind: task
  author: Médéric HURIER (Fmind)
  source: github.com/fmind/dot/tree/main/skills/technical-publishing
  created: "2026-08-30"
  updated: "2026-10-07"
---

# Publish Technical Articles

Publish technical articles from package sources through review, canonical web publication, and channel copy. Third-party documentation sites and static websites use project-local documentation tooling, while software releases use [release](../git-delivery/references/release/GUIDE.md). Run the project-owned CLI from the publishing checkout:

```bash
mise run pub -- init article <slug>                       # scaffold directories and draft
mise run pub -- check <package> --publish-ready            # offline readiness gate
mise run pub -- publish <package> --site <site-directory> --dry-run # preview publication
```

## Workflow

1. **Read the project contract first**: inspect its `AGENTS.md`, current CLI help, and local publishing skill for the requested deliverable. The [package overview](references/packages.md) is orientation, not a replacement for the current schema or publication policy.
1. **Prepare deliverables in the package**: prepare and review the article and channel deliverables inside the package before publication; `draft.txt` contains raw notes that agents never edit; see [Package layout](references/packages.md).
1. **Respect voice and boundaries**: adhere to the editorial voice in [Voice and identity](references/voice.md); agree the register before drafting; never invent anecdotes, clients, or metrics; cut hype, decorative lists, and empty corporate summaries.
1. **Follow the diagram conventions**: explanatory diagrams follow [fmind-visuals](../fmind-visuals/SKILL.md) and [d2](../diagrams-as-code/references/d2.md) using the light-surface theme; store `.d2` sources beside rendered PNGs.
1. **Record demos with VHS**: use the shared [VHS workflow](../fmind-visuals/references/recording.md), retain the tape and synthetic inputs beside the export, and provide a transcript or static alternative; recording does not publish the asset.
1. **Fact-check**: verify claims and links with [fact-check](../fact-check/SKILL.md) before review and after late edits.
1. **Publish only when authorized**: for the package, follow the project's publishing skill before omitting `--dry-run`: the command exports, opens and merges a site PR, verifies the live article, records publication, and retires the temporary `article.md`. Prepare corrections through the site's explicit erratum or edition workflow; ownership does not authorize rewriting published text.
1. **Prepare channel copy for hand-posting**: use the session's channel selection, otherwise the project's defaults (in Pub: articles need only `seo.txt`; announcements and episodes default to LinkedIn and X). Prepare selected adaptations in `posts/`; Medium is retired, so create no Medium copy. Channels are posted by hand, never automated or scheduled. Write the copy with the project's post workflow and checker when present; this skill keeps the package, channel selection, and publication log.

## Documentation

- [Package layout](references/packages.md) · [Voice and identity](references/voice.md)
- Companion skills: [fact-check](../fact-check/SKILL.md) (claims and links), [fmind-visuals](../fmind-visuals/SKILL.md) (diagram theme and brand), [d2](../diagrams-as-code/references/d2.md) (diagram source), and [release](../git-delivery/references/release/GUIDE.md) (software releases).

Attribution

fmindfmind
View sourceSee grades on GitHubMore from fmind →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →