Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Wordpress

ASecurity

Operate connected WordPress sites through the NotFair MCP. Use for WordPress content, posts, pages, media, comments, terms, design, settings, plugins, themes, HTML files, or approved WordPress changes on a NotFair-connected site. Not the local Application-Password CMS setup used by SEO scripts.

3,825 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsapi

Works with

apimcp

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add nowork-studio/notfair-plugin --skill wordpress --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Wordpress?

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

Security grade badge for Wordpress
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/nowork-studio-wordpress-notfair-plugin/badge)](https://www.skillsdirectory.com/skills/nowork-studio-wordpress-notfair-plugin)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: wordpress
description: Operate connected WordPress sites through the NotFair MCP. Use for WordPress content, posts, pages, media, comments, terms, design, settings, plugins, themes, HTML files, or approved WordPress changes on a NotFair-connected site. Not the local Application-Password CMS setup used by SEO scripts.
argument-hint: "<site, content, plugin, or WordPress change>"
---

# WordPress

Follow [`../docs/mcp-connection.md`](../docs/mcp-connection.md). Resolve `~~wordpress` to the live connection. Use its current instructions and capability descriptions to choose tools, and verify the requested site from live data. Do not infer access from Search Console, a local `.env.local` CMS setup, or another connected platform.

This skill is the first-party NotFair WordPress MCP operator (`wordpress_` tools on the universal server). `/notfair:setup-cms` remains the local Application-Password / `.env.local` path for SEO scripts against WordPress, Strapi, Contentful, or Ghost. Do not mix those credentials with this connector.

## Establish the live site

1. Confirm connected sites with a harmless read. Select only a site the connector actually returned.
2. Inspect current capabilities before promising a write. If the connector is missing or unauthorized, direct the user to connect WordPress in the selected NotFair workspace (`/manage-ads-accounts/wordpress`) and stop before claiming live access.
3. Record the site URL, selected site id, current user/role, and whether the session can mutate content, design, settings, or admin surfaces.

Reads commonly include site listing, site details, capability discovery, query, and resource get. Prefer those live descriptions over any skill-level catalog. Prefer a direct update tool over a job for a single edit.

## Read before changing

Pull only the resources needed for the question. For content edits, read the current resource and capture `expectedVersion` from that read. For a new standalone HTML file, the expected-version sentinel is the literal string `absent`.

Lead with the current state, the requested change, and whether the session's role can perform it. Admin role is required for users, settings, design, plugins, themes, core, files, extensions, and jobs. Connector self-modification through plugin management is blocked.

## Execute approved changes safely

Show the exact site, resource, current value, proposed value, risk, and rollback before acting. Obtain approval, apply once, then read back.

The connector exposes content create/update/status/delete, media, terms, comments, design, settings, plugin/theme/core admin, standalone HTML publish/delete, jobs, and change restore. Discover the exact schemas; do not treat that family list as the only allowed surface.

- Create content as draft unless publish is explicitly requested.
- Use `expectedVersion` from a prior read. For new HTML files, use `absent`.
- `requestId` must be stable when retrying the same logical action and must never be reused with changed input.
- Scripts are rejected for standalone HTML publish. Publish HTML only at exact URLs, and only with admin access.
- Prefer get-change plus restore-change over blind retries when the outcome is unknown.
- Confirm success from returned evidence or a fresh read. Report partial failures plainly.

A draft, brief, or generated HTML file is `ready_for_review`. Call a change `published` only after the live connector confirms it.

Attribution

nowork-studionowork-studio
View sourceMore from nowork-studio →
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

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 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', ...

686011 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →