Wp Abilities Verify

What it does

The source separates static inspection from verification in a running WordPress environment. Its central question is whether annotations such as read only or non-destructive accurately describe the callback. It also checks audit documents and permission roundtrips rather than relying on registration metadata alone.

Best for

Maintainers reviewing existing ability registrations or validating a newly implemented ability rollout.

Tradeoffs and requirements

Static mode cannot establish the absence of database or filesystem side effects. Runtime checks need a disposable installation and representative identities. A passing schema lint is narrower than a successful authorization and behavior review.

Targets WordPress 7.0+ plugins (PHP 7.4.0+). Requires a runnable environment (wp-env, docker-based dev stack, or equivalent) for runtime mode; static mode runs entirely from the plugin checkout with no env. Filesystem-based agent with bash + node.

Install from the source

Inspect the pinned source snapshot and its supporting files first. The command selects this skill through the open-source skills CLI. Node.js and agent-specific setup may be required. Installation can download code. Catalog ingestion never executes skill instructions or install scripts.

npx skills add https://github.com/WordPress/agent-skills/tree/eff3785fc28c4380d172094518c66a6a997c95d4/skills/wp-abilities-verify --skill wp-abilities-verify

Review pinned skill folder ↗ · CLI documentation ↗

After source review, use npx skills check and npx skills update to inspect and apply upstream updates. Re-check changed instructions before running them.

Safety & review signals

Static review only. This is not a security audit or a guarantee of safety.

SKILL.md text only; scripts, dependencies and runtime behavior not audited.

• Shell Or Package Install — review the source context.

Allowed tools declaration: Unknown. Runtime permissions and network behavior: Unknown.

Offline package integrity

A temporary folder-copy check, not an agent installation or runtime safety verdict.

7 files copied and checksummed from this exact source snapshot. No package code or installation scripts were executed.

Inventory SHA-256: d51d95351ff668b2ab7164ffa11938562504874eb86adf060e70f665e4e84ae9

AI Craft Pad Skill Score

75/100 · Metadata coverage 80% · Model 1.0

Scores summarize observable discovery signals. Popularity and repository activity apply to the whole repository. Unknown runtime safety earns no certification.

Documentation

100/100

100

Maintenance

100/100

100

License Clarity

0/100

0

Repository Health

85/100

85

Compatibility Evidence

80/100

80

Popularity

61/100

61

Originality

80/100

80

Static Safety

60/100

60

Suggested workflow

Choose the verification mode explicitly, enumerate registrations and trace their callbacks. In runtime mode, capture initial state, exercise representative inputs and permissions, and inspect state changes before evaluating whether the declared annotations are accurate.

How to judge the result

Report evidence separately for annotations, schemas, permission gates and error responses. Include negative authorization cases and callbacks that delegate work. Mark checks unavailable in static mode as untested rather than allowing them to inherit a passing status.