wp-full
Skill1 starsChanged 6 months agoMITView on GitHub
Alias / pointer skill — when the user wants "the full rolepod-wplab WP workflow", this lists every individual skill and the phase it belongs to. Zero supporting files. Phase = alias.
In this repository14 other files it gives its agents.
- wp-changesSkill
- wp-connectSkill
- wp-contentSkill
- wp-diagnoseSkill
- wp-edit-designSkill
- wp-edit-pluginSkill
- wp-edit-themeSkill
- wp-execute-phpSkill
- wp-health-checkSkill
- wp-introspectSkill
- wp-migrateSkill
- wp-pair-setupSkill
- wp-recoverySkill
- wp-scaffoldSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 19
If the marker file $GIT_ROOT/.rolepod/parent-active exists, follow the
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Mode selection
If the marker file $GIT_ROOT/.rolepod/parent-active exists, follow the
with-rolepod mode — emit the flat tool inventory under the "When
with-rolepod" section below; do NOT render the flow narrative. Parent's
using-rolepod router decides which wplab skill to invoke based on phase.
Otherwise, follow standalone mode — render the full tour with phase grouping + recommended next skill, under the "When standalone" section.
GIT_ROOT=$(git rev-parse --show-toplevel 2>/dev/null) || GIT_ROOT="$PWD"
if [ -f "$GIT_ROOT/.rolepod/parent-active" ]; then
MODE=with-rolepod
else
MODE=standalone
fiWP Full
Pointer skill. Owns nothing. Has nothing under it. Exists so a single invocation surfaces the entire wp-* skill map.
When with-rolepod
Parent detected. Print the flat tool inventory (no flow narrative):
wplab tools available:
- wp-diagnose (debug evidence)
- wp-health-check (verify evidence)
- wp-changes (review evidence)
- wp-edit-design (build primitive)
- wp-edit-plugin (build primitive)
- wp-edit-theme (build primitive)
- wp-scaffold (build primitive)
- wp-migrate (build + verify pair)
- wp-connect (utility — opens a Target)
- wp-pair-setup (utility — one-click pair via companion)
- wp-introspect (utility — runtime introspection)
- wp-execute-php (utility — guarded PHP eval)
- wp-content (utility — core REST CRUD)
- wp-full (this skill — already loaded)Then stop. Parent owns the phase decision.
When standalone
The 13 skills, by phase:
Define
wp-pair-setup— redeem a companion pair_token, mint App Password, open first Target.wp-connect— open Target on any kind (local / rest / ssh / docker) using vault credentials.
Verify
wp-health-check— sub-5s ping: versions, db_ok, rest_ok, companion_ok, warnings.
Build
wp-content— core REST CRUD: posts, pages, users, options, db SELECT, rest_request.wp-edit-design— Elementor / Divi / Oxygen / Bricks page-builder layouts.wp-edit-theme— theme files, theme.json, global-styles, child themes, theme switch (with snapshot + auto-rollback).wp-edit-plugin— Yoast / RankMath / WPML / WooCommerce / ACF / Forms read+write.wp-scaffold— bootstrap new block / plugin / theme / pattern.
Debug
wp-introspect— read-only runtime snapshot (hooks, transients, options, request_state, hook_state).wp-diagnose— multi-probe sweep + audit + ranked report.
Ship
wp-migrate— dryrun, apply, backup, restore, clone between targets.
Recovery
wp-changes— AI Change Ledger query + toggle + panic-revert + bisect.
Power
wp-execute-php— last-resort PHP eval with 5-layer safety chain.
Reading order
Onboarding a new site → wp-pair-setup → wp-health-check → the build skill matching user intent.
Debugging an existing site → wp-health-check → wp-diagnose → wp-introspect → fix via the right edit skill.
Shipping work between sites → wp-migrate.
No supporting files
This is an alias. Zero templates/, examples/, references/. The 11 individual skills carry the depth.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

