[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79R9P9KFH6D1CCEPAYKKWYA":3,"skill-same:01M79R9P9KFH6D1CCEPAYKKWYA":72},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M79R9P9KFH6D1CCEPAYKKWYA","wp-abilities-verify",null,"Verify a WordPress plugin's Abilities API registrations: enumerate abilities, check that callback behavior matches each annotation's claim (the adversarial readonly-but-writes detection), validate permissions and schemas, and validate audit documents produced by wp-abilities-audit.","gambitph\u002FAhentic","gambitph","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F3227089?v=4","01M6C1ZD8129MTRC23K53VJ45E","Gambit Technologies","01M79R7A85NS2N9JAK7AC0NE1X",0,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Fgambitph\u002FAhentic\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fwp-abilities-verify\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: wp-abilities-verify\ndescription: \"Verify a WordPress plugin's Abilities API registrations: enumerate abilities, check that callback behavior matches each annotation's claim (the adversarial readonly-but-writes detection), validate permissions and schemas, and validate audit documents produced by wp-abilities-audit.\"\ncompatibility: \"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.\"\n---\n\n# WP Abilities Verify\n\nVerify a WordPress plugin's Abilities API registrations. The\ncenterpiece is the **adversarial annotation correctness check**: a\n`readonly: true` ability that actually writes (via `$wpdb->update`,\n`update_option`, a non-GET delegate, etc.) is a security and UX\ndisaster because agents plan actions on the basis of the annotations\nthey introspect. This skill catches those lies by reading the callback\nbody and comparing what it does against what the annotation claims.\n\nThe skill also validates audit docs produced by `wp-abilities-audit`,\nchecks permission gates and schema hygiene, and optionally executes\neach ability against a live environment.\n\n## When to use\n\n- After abilities have been registered in a plugin but before a PR\n  lands.\n- As a health-check on an already-shipped plugin (catch regressions\n  where a refactor turned a readonly ability into a writing one).\n- To validate an audit document before handing it to an implementer.\n\n## Two modes\n\n- **Static mode** — runs from the plugin checkout. No env. Enumerates\n  via source inspection, runs the adversarial correctness check, runs\n  schema and permission lints, and validates audit docs.\n- **Runtime mode** — requires a running env. Does everything static\n  does PLUS: `wp_get_abilities()` for authoritative enumeration,\n  executes each ability with curated inputs, confirms permission\n  roundtrip against real users, and runs a twin-invocation heuristic\n  on `idempotent: true` abilities to flag candidates for review\n  (return-value equality is a signal, not a verdict — core defines\n  idempotent as \"no additional effect on the environment\").\n\nBoth modes produce the same structured report format.\n\nA static-mode PASS means \"no obvious-shape violations,\" not \"verified\nwrite-free.\" For high-stakes plugins, run runtime mode before landing\n— it catches bootstrap-order, permission-roundtrip, and idempotency\nissues that static can't. See `references\u002Fannotation-correctness.md`\nfor the static blind spots.\n\n## Inputs required\n\n1. **Plugin checkout path** — working tree to verify.\n2. **Mode** — `static` or `runtime`. Default to static if unspecified.\n3. **(Runtime only) Env-up command** — read the plugin's `AGENTS.md`.\n   Common patterns: `npm run wp-env start`, `npx wp-env start`, or a\n   composer-based bring-up. Plugin families with their own dev tooling\n   will document their own command. Do NOT assume `npm run wp-env`\n   works.\n4. **(Optional) Audit doc path** — enables cross-checks between the\n   audit and the registered abilities, and validates the audit itself.\n5. **Report output path** — explicit path, typically the user's vault.\n\n## Prerequisites\n\n- `wp-project-triage` has been run on the plugin.\n- The plugin has at least one registered ability in source. Zero hits\n  on `wp_register_ability(` → return a clear \"no abilities registered\"\n  report, not an empty PASS.\n\n## Procedure\n\n### 1. (If audit provided) Validate the audit doc\n\nRead `references\u002Faudit-schema-validation.md`. Validate the audit\nagainst the canonical schema owned by `wp-abilities-audit`. Surface\nmissing required fields, multiple `reference_ability: true`, and\n`backing: null` entries that aren't paired with a `surfaced_gaps`\nentry. `backing: null` alone is WARN (intentional gap output), not\nFAIL.\n\n### 2. Enumerate abilities statically\n\nRead `references\u002Fstatic-enumeration.md`. Find each\n`wp_register_ability(` call, extract the name, the annotation block,\nand the execute-callback location. Use a multi-line tool (`rg\n--multiline --pcre2`) — the canonical formatting splits the call\nacross lines. Record each ability's source-file + line + annotations +\ncallback byte range.\n\n### 3. (Runtime only) Enumerate via REST + wp-cli\n\nRead `references\u002Fruntime-harness.md`. Bring the env up using the\ncommand from `AGENTS.md`, then enumerate via `wp_get_abilities()` over\nwp-cli and cross-check against the static inventory. Source-only →\nFAIL (registration not firing). Runtime-only → WARN (dynamic\nregistration path).\n\n### 4. Annotation correctness (the adversarial core)\n\nRead `references\u002Fannotation-correctness.md`. Read each callback body\nand verify it matches the annotation claim:\n\n- `readonly: true` → callback must not write to the database, the\n  options table, post \u002F user \u002F term \u002F comment data, the filesystem,\n  cron, or via non-GET HTTP \u002F REST delegates.\n- `destructive: false` → callback must not delete, refund, void,\n  cancel, or trash.\n- `idempotent: true` → repeated calls with the same input have no\n  additional effect on the environment (per the `idempotent`\n  annotation's docblock in `class-wp-ability.php`). Static catches\n  counter writes and per-call cron schedules; runtime adds a\n  twin-invocation heuristic for visible state changes.\n\nThe reference lists common write patterns as a starting set, not a\nchecklist — plugin vocabularies vary, and the agent extends with verbs\nspecific to the plugin under verification.\n\nFalse positives get suppressed via an inline `\u002F\u002F verify-ignore:\n\u003Cannotation> -- \u003Creason>` comment.\n\n### 5. Permission roundtrip\n\nRead `references\u002Fpermission-roundtrip.md`. Static: classify each\n`permission_callback` against the six shapes (preferred Shape A\n`current_user_can(...)`; FAIL on Shape B-bad `WP_REST_Request`\npatterns or Shape E literal `true`). Runtime: anon and subscriber\ndenied; admin allowed (unless deliberately public). When an audit was\nprovided, cross-check the registered cap against the audit's declared\ngate.\n\n### 6. Schema lints\n\nRead `references\u002Fschema-lints.md`. Six small principles applied to\neach ability's `input_schema`: object schemas declare\n`additionalProperties`; required fields have descriptions; enums\nnon-empty; no `$ref`; defaults are statically constant (including\n`(object) array()`); reference abilities have no required inputs.\n\nCross-reference `..\u002Fwp-abilities-api\u002Freferences\u002Finput-schema-gotchas.md`\nfor the four runtime gotchas (defaults not injected on the\nproperty-level path, pagination key drift, `empty()` on string IDs,\ndirect vs indirect invocation strictness).\n\n### 7. Error-code vocabulary\n\nCross-reference `..\u002Fwp-abilities-api\u002Freferences\u002Ferror-code-vocabulary.md`.\nInspect each callback's `WP_Error` returns; non-vocabulary codes →\nWARN.\n\n## Verification\n\nThe run produces a structured markdown report at the user-specified\npath:\n\n```\n---\nLast updated: \u003CYYYY-MM-DD HH:MM>\n---\n\n# \u003CPlugin> Abilities Verification — \u003CStatic|Runtime> Mode\n\n## Status: \u003CPASS|WARN|FAIL>\n\n## Audit doc validation (if provided)\n\n## Static inventory\n\n## Annotation correctness\n| Ability | Claim | Result | Evidence |\n|---|---|---|---|\n\n## Permission gates\n\n## Schema lints\n\n## Error-code vocabulary\n```\n\nEvery ability is OK, WARN, or FAIL. A single FAIL → top-line FAIL;\nWARNs without FAILs → WARN; otherwise PASS.\n\n## Failure modes \u002F debugging\n\n- **Env not reachable (runtime)** — env-up failed or Docker isn't\n  running. Re-run `wp-project-triage`, then fix the env. Don't fall\n  back silently to static without noting it in the report.\n- **No abilities in source** — return a clear \"nothing to verify\"\n  report.\n- **Audit schema mismatch** — point at\n  `references\u002Faudit-schema-validation.md`; don't auto-fix the audit.\n- **False positive on readonly-writes** — see the `\u002F\u002F verify-ignore`\n  mechanism in `references\u002Fannotation-correctness.md`. Document why\n  each suppression is legitimate.\n- **Runtime enumeration smaller than static** — registration hook\n  isn't firing. Check init hook timing, activation state, autoloader\n  order.\n\n## Escalation\n\n- Recurring legitimate pattern that trips the adversarial check across\n  multiple plugins → propose adding it to the suppression guidance in\n  `annotation-correctness.md`. Don't broaden the candidate-pattern\n  list speculatively.\n- Audit-schema validator rejects a legitimate audit → the canonical\n  schema in `..\u002Fwp-abilities-audit\u002Freferences\u002Faudit-schema.md` has\n  evolved. Update `references\u002Faudit-schema-validation.md` to match.\n\n## Out of scope\n\nToken-budget measurement is a separate verification axis — an\nannotation-clean, schema-clean, runtime-passing ability set can still\nbe unshippable if its `tools\u002Flist` form burns through an agent's\ncontext budget. That axis is tracked separately. Do not aggregate\nmanual or external measurement into this skill's PASS \u002F FAIL verdict.\n","# WP Abilities Verify\n\nVerify a WordPress plugin's Abilities API registrations. The\ncenterpiece is the **adversarial annotation correctness check**: a\n`readonly: true` ability that actually writes (via `$wpdb->update`,\n`update_option`, a non-GET delegate, etc.) is a security and UX\ndisaster because agents plan actions on the basis of the annotations\nthey introspect. This skill catches those lies by reading the callback\nbody and comparing what it does against what the annotation claims.\n\nThe skill also validates audit docs produced by `wp-abilities-audit`,\nchecks permission gates and schema hygiene, and optionally executes\neach ability against a live environment.\n\n## When to use\n\n- After abilities have been registered in a plugin but before a PR\n  lands.\n- As a health-check on an already-shipped plugin (catch regressions\n  where a refactor turned a readonly ability into a writing one).\n- To validate an audit document before handing it to an implementer.\n\n## Two modes\n\n- **Static mode** — runs from the plugin checkout. No env. Enumerates\n  via source inspection, runs the adversarial correctness check, runs\n  schema and permission lints, and validates audit docs.\n- **Runtime mode** — requires a running env. Does everything static\n  does PLUS: `wp_get_abilities()` for authoritative enumeration,\n  executes each ability with curated inputs, confirms permission\n  roundtrip against real users, and runs a twin-invocation heuristic\n  on `idempotent: true` abilities to flag candidates for review\n  (return-value equality is a signal, not a verdict — core defines\n  idempotent as \"no additional effect on the environment\").\n\nBoth modes produce the same structured report format.\n\nA static-mode PASS means \"no obvious-shape violations,\" not \"verified\nwrite-free.\" For high-stakes plugins, run runtime mode before landing\n— it catches bootstrap-order, permission-roundtrip, and idempotency\nissues that static can't. See `references\u002Fannotation-correctness.md`\nfor the static blind spots.\n\n## Inputs required\n\n1. **Plugin checkout path** — working tree to verify.\n2. **Mode** — `static` or `runtime`. Default to static if unspecified.\n3. **(Runtime only) Env-up command** — read the plugin's `AGENTS.md`.\n   Common patterns: `npm run wp-env start`, `npx wp-env start`, or a\n   composer-based bring-up. Plugin families with their own dev tooling\n   will document their own command. Do NOT assume `npm run wp-env`\n   works.\n4. **(Optional) Audit doc path** — enables cross-checks between the\n   audit and the registered abilities, and validates the audit itself.\n5. **Report output path** — explicit path, typically the user's vault.\n\n## Prerequisites\n\n- `wp-project-triage` has been run on the plugin.\n- The plugin has at least one registered ability in source. Zero hits\n  on `wp_register_ability(` → return a clear \"no abilities registered\"\n  report, not an empty PASS.\n\n## Procedure\n\n### 1. (If audit provided) Validate the audit doc\n\nRead `references\u002Faudit-schema-validation.md`. Validate the audit\nagainst the canonical schema owned by `wp-abilities-audit`. Surface\nmissing required fields, multiple `reference_ability: true`, and\n`backing: null` entries that aren't paired with a `surfaced_gaps`\nentry. `backing: null` alone is WARN (intentional gap output), not\nFAIL.\n\n### 2. Enumerate abilities statically\n\nRead `references\u002Fstatic-enumeration.md`. Find each\n`wp_register_ability(` call, extract the name, the annotation block,\nand the execute-callback location. Use a multi-line tool (`rg\n--multiline --pcre2`) — the canonical formatting splits the call\nacross lines. Record each ability's source-file + line + annotations +\ncallback byte range.\n\n### 3. (Runtime only) Enumerate via REST + wp-cli\n\nRead `references\u002Fruntime-harness.md`. Bring the env up using the\ncommand from `AGENTS.md`, then enumerate via `wp_get_abilities()` over\nwp-cli and cross-check against the static inventory. Source-only →\nFAIL (registration not firing). Runtime-only → WARN (dynamic\nregistration path).\n\n### 4. Annotation correctness (the adversarial core)\n\nRead `references\u002Fannotation-correctness.md`. Read each callback body\nand verify it matches the annotation claim:\n\n- `readonly: true` → callback must not write to the database, the\n  options table, post \u002F user \u002F term \u002F comment data, the filesystem,\n  cron, or via non-GET HTTP \u002F REST delegates.\n- `destructive: false` → callback must not delete, refund, void,\n  cancel, or trash.\n- `idempotent: true` → repeated calls with the same input have no\n  additional effect on the environment (per the `idempotent`\n  annotation's docblock in `class-wp-ability.php`). Static catches\n  counter writes and per-call cron schedules; runtime adds a\n  twin-invocation heuristic for visible state changes.\n\nThe reference lists common write patterns as a starting set, not a\nchecklist — plugin vocabularies vary, and the agent extends with verbs\nspecific to the plugin under verification.\n\nFalse positives get suppressed via an inline `\u002F\u002F verify-ignore:\n\u003Cannotation> -- \u003Creason>` comment.\n\n### 5. Permission roundtrip\n\nRead `references\u002Fpermission-roundtrip.md`. Static: classify each\n`permission_callback` against the six shapes (preferred Shape A\n`current_user_can(...)`; FAIL on Shape B-bad `WP_REST_Request`\npatterns or Shape E literal `true`). Runtime: anon and subscriber\ndenied; admin allowed (unless deliberately public). When an audit was\nprovided, cross-check the registered cap against the audit's declared\ngate.\n\n### 6. Schema lints\n\nRead `references\u002Fschema-lints.md`. Six small principles applied to\neach ability's `input_schema`: object schemas declare\n`additionalProperties`; required fields have descriptions; enums\nnon-empty; no `$ref`; defaults are statically constant (including\n`(object) array()`); reference abilities have no required inputs.\n\nCross-reference `..\u002Fwp-abilities-api\u002Freferences\u002Finput-schema-gotchas.md`\nfor the four runtime gotchas (defaults not injected on the\nproperty-level path, pagination key drift, `empty()` on string IDs,\ndirect vs indirect invocation strictness).\n\n### 7. Error-code vocabulary\n\nCross-reference `..\u002Fwp-abilities-api\u002Freferences\u002Ferror-code-vocabulary.md`.\nInspect each callback's `WP_Error` returns; non-vocabulary codes →\nWARN.\n\n## Verification\n\nThe run produces a structured markdown report at the user-specified\npath:\n\n```\n---\nLast updated: \u003CYYYY-MM-DD HH:MM>\n---\n\n# \u003CPlugin> Abilities Verification — \u003CStatic|Runtime> Mode\n\n## Status: \u003CPASS|WARN|FAIL>\n\n## Audit doc validation (if provided)\n\n## Static inventory\n\n## Annotation correctness\n| Ability | Claim | Result | Evidence |\n|---|---|---|---|\n\n## Permission gates\n\n## Schema lints\n\n## Error-code vocabulary\n```\n\nEvery ability is OK, WARN, or FAIL. A single FAIL → top-line FAIL;\nWARNs without FAILs → WARN; otherwise PASS.\n\n## Failure modes \u002F debugging\n\n- **Env not reachable (runtime)** — env-up failed or Docker isn't\n  running. Re-run `wp-project-triage`, then fix the env. Don't fall\n  back silently to static without noting it in the report.\n- **No abilities in source** — return a clear \"nothing to verify\"\n  report.\n- **Audit schema mismatch** — point at\n  `references\u002Faudit-schema-validation.md`; don't auto-fix the audit.\n- **False positive on readonly-writes** — see the `\u002F\u002F verify-ignore`\n  mechanism in `references\u002Fannotation-correctness.md`. Document why\n  each suppression is legitimate.\n- **Runtime enumeration smaller than static** — registration hook\n  isn't firing. Check init hook timing, activation state, autoloader\n  order.\n\n## Escalation\n\n- Recurring legitimate pattern that trips the adversarial check across\n  multiple plugins → propose adding it to the suppression guidance in\n  `annotation-correctness.md`. Don't broaden the candidate-pattern\n  list speculatively.\n- Audit-schema validator rejects a legitimate audit → the canonical\n  schema in `..\u002Fwp-abilities-audit\u002Freferences\u002Faudit-schema.md` has\n  evolved. Update `references\u002Faudit-schema-validation.md` to match.\n\n## Out of scope\n\nToken-budget measurement is a separate verification axis — an\nannotation-clean, schema-clean, runtime-passing ability set can still\nbe unshippable if its `tools\u002Flist` form burns through an agent's\ncontext budget. That axis is tracked separately. Do not aggregate\nmanual or external measurement into this skill's PASS \u002F FAIL verdict.\n",{"name":5,"description":7,"compatibility":24},"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.","main","c4de8c3c2dcdca2892337cdc47c05dcb1cea8562",".cursor\u002Fskills\u002Fwp-abilities-verify","https:\u002F\u002Fgithub.com\u002Fgambitph\u002FAhentic","https:\u002F\u002Fgithub.com\u002Fgambitph","https:\u002F\u002Fwpstackable.com","2026-08-15 14:40:10",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add gambitph\u002FAhentic --skill wp-abilities-verify",{"tool":38,"command":39},"bunx","bunx skills add gambitph\u002FAhentic --skill wp-abilities-verify",{"tool":41,"command":42},"pnpm","pnpm dlx skills add gambitph\u002FAhentic --skill wp-abilities-verify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgambitph\u002FAhentic\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fwp-abilities-verify\u002FSKILL.md",true,[46,52,56,60,64,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fannotation-correctness.md","REFERENCE","参考文档",8217,"https:\u002F\u002Fgithub.com\u002Fgambitph\u002FAhentic\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fwp-abilities-verify\u002Freferences\u002Fannotation-correctness.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Faudit-schema-validation.md",5243,"https:\u002F\u002Fgithub.com\u002Fgambitph\u002FAhentic\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fwp-abilities-verify\u002Freferences\u002Faudit-schema-validation.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fpermission-roundtrip.md",7611,"https:\u002F\u002Fgithub.com\u002Fgambitph\u002FAhentic\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fwp-abilities-verify\u002Freferences\u002Fpermission-roundtrip.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fruntime-harness.md",16825,"https:\u002F\u002Fgithub.com\u002Fgambitph\u002FAhentic\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fwp-abilities-verify\u002Freferences\u002Fruntime-harness.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fschema-lints.md",4772,"https:\u002F\u002Fgithub.com\u002Fgambitph\u002FAhentic\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fwp-abilities-verify\u002Freferences\u002Fschema-lints.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fstatic-enumeration.md",4487,"https:\u002F\u002Fgithub.com\u002Fgambitph\u002FAhentic\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fwp-abilities-verify\u002Freferences\u002Fstatic-enumeration.md",[73,80,87,94,101,108],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M79RB5GMQX62XBSR4XMJ3758","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fgambitph\u002FAhentic\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M79RB0ET331AVRW6W4JAW30C","wp-rest-api","Use when building, extending, or debugging WordPress REST API endpoints\u002Froutes: register_rest_route, WP_REST_Controller\u002Fcontroller classes, schema\u002Fargument validation, permission_callback\u002Fauthentication, response shaping, register_rest_field\u002Fregister_meta, or exposing CPTs\u002Ftaxonomies via show_in_rest.","https:\u002F\u002Fgithub.com\u002Fgambitph\u002FAhentic\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fwp-rest-api\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M79RAX0CGSMDWJ7F5DATG4WF","wp-project-triage","Use when you need a deterministic inspection of a WordPress repository (plugin\u002Ftheme\u002Fblock theme\u002FWP core\u002FGutenberg\u002Ffull site) including tooling\u002Ftests\u002Fversion hints, and a structured JSON report to guide workflows and guardrails.","https:\u002F\u002Fgithub.com\u002Fgambitph\u002FAhentic\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fwp-project-triage\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M79RAQ5Q24QC2W4M3XDM2195","wp-plugin-directory-guidelines","Use when reviewing WordPress plugins for GPL compliance, checking license headers or compatibility, evaluating upsell\u002Ffreemium\u002Ftrialware patterns, validating plugin naming or trademark rules, checking plugin slugs, understanding why a plugin was rejected from WordPress.org, or answering any question about the 18 WordPress.org Plugin Directory guidelines — even if the user doesn't mention 'guidelines' explicitly.","https:\u002F\u002Fgithub.com\u002Fgambitph\u002FAhentic\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fwp-plugin-directory-guidelines\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M79RAJ56J66CKG54B0SBK8PX","wp-plugin-development","Use when developing WordPress plugins: architecture and hooks, activation\u002Fdeactivation\u002Funinstall, admin UI and Settings API, data storage, cron\u002Ftasks, security (nonces\u002Fcapabilities\u002Fsanitization\u002Fescaping), and release packaging.","https:\u002F\u002Fgithub.com\u002Fgambitph\u002FAhentic\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fwp-plugin-development\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M79RACN5F4BJYC0QX4MBFV0P","wp-performance","Use when investigating or improving WordPress performance (backend-only agent): profiling and measurement (WP-CLI profile\u002Fdoctor, Server-Timing, Query Monitor via REST headers), database\u002Fquery optimization, autoloaded options, object caching, cron, HTTP API calls, and safe verification.","https:\u002F\u002Fgithub.com\u002Fgambitph\u002FAhentic\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fwp-performance\u002FSKILL.md",[],[]]