CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

wordpress

Use when building, extending, auditing, or modernizing WordPress sites end to end: themes, plugins, WooCommerce, performance, security hardening, or WordPress 7.0 features (AI Client, Abilities API, PHP-only blocks, DataViews). Use as the entry point that routes to the three focused WordPress skills. Do not use for non-WordPress PHP, or front-end work with no WordPress involvement.

64

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

63%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, largely executable WordPress workflow whose 7.0-specific guidance (RTC non-shipping, AI Client, Abilities API, MCP integration) is genuinely valuable. Its weaknesses are token bloat from boilerplate structure trees and generic checklists, and a monolithic layout with no reference files despite reference-grade API content.

Suggestions

Move the WP 7.0 API reference material (AI Client fluent-builder variations, Abilities API registration example, MCP connection JSON configs) into one-level-deep files under references/ and link them from SKILL.md.

Delete or compress content Claude already knows: the standard theme/plugin directory trees, generic caching/CDN/OPcache bullets, and routine security checklist items like 'strong passwords' and 'regular backups'.

Add explicit validation checkpoints with fix-and-retry loops to Phase 8 (e.g. run migrations on staging, verify, then deploy; smoke-test after maintenance mode is lifted) and remove the comment-only wp-config.php code block.

DimensionReasoningScore

Conciseness

The WordPress 7.0-specific material (RTC removal, AI Client, Abilities API, MCP) earns its tokens, but generic boilerplate Claude already knows is inlined: standard theme/plugin directory trees, 'Implement caching (object, page, browser)', 'Minify and combine assets', 'Strong passwords enforced', 'Regular backups configured', and a wp-config.php code block containing only comments. Heavy inline version/date detail (e.g. 'shipped May 20, 2026... April 9 date slipped') further inflates the body.

3 / 5

Actionability

Most guidance is executable and copy-paste ready: full register_post_meta() calls, fluent wp_ai_client_prompt() chains, Abilities API registration on the correct hooks with a complete handler, and concrete MCP server JSON configs. Minor gaps remain, e.g. 'labels' => [...] placeholder, an undefined get_books callback, and the WooCommerce example whose class body is just '// Custom product implementation'.

4 / 5

Workflow Clarity

Eight clearly sequenced phases with numbered actions, per-phase checklists, a Quality Gates section gating phase transitions, and an explicit 'wp plugin check with 0 errors and 0 warnings' verification. Not a 5 because deployment and database migration steps lack explicit validate-fix-retry feedback loops ('Set up database migrations... Deploy to production... Monitor post-deployment' has no checkpoint between migration and deploy).

4 / 5

Progressive Disclosure

The body is a ~560-line monolith with no bundle files (references/, scripts/, assets/ are absent) and no one-level-deep references; substantial reference-grade material (full Abilities API example, AI Client API variations, MCP connection configs) is inlined in SKILL.md. Section headers are well organized and the 'Related skills' pointers exist, but content that should be split into separate files is inline, matching the 'some structure but could be better organized' anchor rather than the 4-5 anchors which require well-signaled file references.

3 / 5

Total

14

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An excellent description: specific capabilities, explicit use-when triggers, routing to sibling skills, and negative boundary guidance all in third-person imperative voice. The only weakness is missing a few natural synonym terms users might say.

DimensionReasoningScore

Specificity

Concrete actions are enumerated comprehensively — 'building, extending, auditing, or modernizing WordPress sites end to end' — across named domains (themes, plugins, WooCommerce, performance, security hardening) plus named 7.0 features (AI Client, Abilities API, PHP-only blocks, DataViews). This matches the 'multiple specific concrete actions; comprehensive coverage' anchor and exceeds the 4 anchor, which allows coverage gaps.

5 / 5

Completeness

Explicitly answers 'when' with a 'Use when...' clause listing concrete triggers, answers 'what' ('entry point that routes to the three focused WordPress skills' plus the enumerated capabilities), and even adds negative scope ('Do not use for non-WordPress PHP, or front-end work with no WordPress involvement'). Clearly matches the top anchor.

5 / 5

Trigger Term Quality

Strong natural keyword coverage: 'WordPress', 'themes', 'plugins', 'WooCommerce', 'performance', 'security hardening', 'WordPress 7.0'. Falls short of the 5 anchor ('comprehensive coverage... including synonyms and file extensions') because common variants are absent, e.g. 'WP', 'store/e-commerce setup', 'migration', or 'headless' — users do say these when they need WordPress help.

4 / 5

Distinctiveness Conflict Risk

Clear WordPress-only niche with an explicit exclusion clause ('Do not use for non-WordPress PHP, or front-end work with no WordPress involvement') and explicit routing relative to the three sibling WordPress skills, so it is unlikely to trigger for the wrong skill. Matches the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (569 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

administrakt0r/pro-skills-repo-administraktor

Path

skills/wordpress-skills/wordpress/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.