gridzen-developer-kit 0.7.0__tar.gz → 0.7.1__tar.gz

{gridzen_developer_kit-0.7.0 → gridzen_developer_kit-0.7.1}/MANIFEST.in

@@ -13,3 +13,6 @@ include docs/verification-evaluation.md
 
 include docs/atomic-tools.md
 recursive-include examples/atomic_tools *.json *.py *.md
+
+include llms-install.md docs/activation.md docs/mexico-identity-account.md docs/multilingual-ui.md
+recursive-include examples *.md *.json *.py *.ts

{gridzen_developer_kit-0.7.0/src/gridzen_developer_kit.egg-info → gridzen_developer_kit-0.7.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gridzen-developer-kit
-Version: 0.7.0
+Version: 0.7.1
 Summary: Single-task MCP profiles and Skills, offline utilities, research and explicit verification sandbox
 Author-email: Gridzen <open@gridzen.ai>
 License-Expression: MIT
@@ -28,7 +28,7 @@ Requires-Dist: fastapi==0.142.4; extra == "test"
 Requires-Dist: uvicorn==0.54.0; extra == "test"
 Dynamic: license-file
 
-# Gridzen Developer Kit 0.7.0
+# Gridzen Developer Kit 0.7.1
 
 The hosted developer interface supports Vietnamese alongside English, Spanish and Simplified Chinese: https://gridzen.ai/developers/?lang=vi . UI language does not enable live checks or country coverage. See [UI language maintenance](docs/multilingual-ui.md).
 
@@ -49,9 +49,9 @@ python3 -m venv .venv
 
 Open [GridZen instant trial](https://gridzen.ai/console/start?lang=en) to run synthetic signup-phone and identity-onboarding responses without an account, API key or approval. Success, rejection and unavailable scenarios make no upstream calls and verify no real person. Agents can use the separate [key-free trial MCP](https://gridzen.ai/console/downloads/quickstart_mcp.py), installed with `mcp==2.3.0` and `httpx==0.28.1` in a virtual environment.
 
-For persistent test records and supplier sandbox callbacks, connect a verified merchant sandbox account. Production access is capability-specific: eligible routes may offer bounded real trials, while others remain unavailable. Read the authenticated capability conditions; published prices do not enable paid purchases. This documentation update does not change PyPI or the official MCP Registry version.
+For persistent test records and supplier sandbox callbacks, connect a verified merchant sandbox account. Production access is capability-specific: eligible routes may offer bounded real trials, while others remain unavailable. Read the authenticated capability conditions; published prices do not enable paid purchases. Package releases and the hosted MCP Registry entry have independent versions; installing this package grants no merchant permissions.
 
-Fourteen Skills: the original six research/workflow Skills plus eight single-task profiles. Three new tools run offline; five merchant profiles call the existing authenticated GridZen API only with separate authorization, current availability and funding. The anonymous remote MCP retains five research/synthetic tools and never performs live verification. Research covers 198 countries/territories as a dated 2026-10-07 snapshot, not live service coverage.
+Fourteen Skills: the original six research/workflow Skills plus eight single-task profiles. Three new tools run offline; five merchant profiles call the existing authenticated GridZen API only with separate authorization, current availability and permitted use. The anonymous remote MCP retains five research/synthetic tools and never performs live verification. Research covers 198 countries/territories as a dated 2026-10-07 snapshot, not live service coverage.
 
 [中文指南](README.zh-CN.md) · [Guía en español](README.es.md)
 
@@ -64,9 +64,9 @@ Fourteen Skills: the original six research/workflow Skills plus eight single-tas
 | Missing or delayed callback | [Guide](https://gridzen.ai/console/learn/callback-recovery?lang=en) | [Recovery fixture](examples/verification_delivery/) |
 | Verification to business permission | [Guide](https://gridzen.ai/console/learn/business-permission-boundary?lang=en) | [Self-hosted n8n fixture](examples/n8n/) |
 
-[Chinese and Spanish article files](distribution/market-expansion-2026-10-13/articles/) · [Demo video](distribution/market-expansion-2026-10-13/media/identity-three-outcomes.mp4) · [Smithery listing](https://smithery.ai/servers/support-35ug/gridzen-verification).
+[Chinese and Spanish article files](https://github.com/immurray/gridzen-developer-kit/tree/main/distribution/market-expansion-2026-10-13/articles/) · [Demo video](https://github.com/immurray/gridzen-developer-kit/blob/main/distribution/market-expansion-2026-10-13/media/identity-three-outcomes.mp4).
 
-Public examples are synthetic. Approved prices and per-product availability are published at https://gridzen.ai/pricing/; live payments remain disabled. [Request an approved pilot](https://gridzen.ai/console/pilot), without sending identity documents or credentials to public MCP tools.
+Public examples are synthetic. Approved prices and per-product availability are published at https://gridzen.ai/pricing/; paid activation remains unavailable. [Request an approved pilot](https://gridzen.ai/console/pilot), without sending identity documents or credentials to public MCP tools.
 
 [Per-check plan and activation requirements](https://gridzen.ai/console/quote?lang=en) · [JSON](https://gridzen.ai/console/api/commercial/options)
 
@@ -81,9 +81,9 @@ python3 -m venv .venv
 . .venv/bin/activate
 python -m pip install './gridzen-developer-kit[mcp]'
 gridzen coverage --country ID --capability bank_account_match
-gridzen plan --country ID --event payout
+gridzen plan --country ID --event onboarding
 gridzen simulate --country ID --capability bank_account_match --scenario timeout
-python gridzen-developer-kit/examples/payout.py
+python gridzen-developer-kit/examples/customer_tasks.py
 ```
 
 Python 3.11+. CLI and MCP use the bundled offline catalog and fixtures; the Python HTTP client/example calls the public sandbox. Dependencies are downloaded only during installation. API reference: https://gridzen.ai/developers/api/openapi.json .
@@ -107,7 +107,7 @@ Copy the individual directories from `skills/` into your compatible agent's proj
 ```python
 from gridzen_developer.client import Gridzen
 client = Gridzen()
-plan = client.plan('ID', 'payout')
+plan = client.plan('ID', 'onboarding')
 result = client.simulate('ID', 'bank_account_match', 'not_found')
 assert result['status'] == 'inconclusive'
 assert result['verified'] is False
@@ -115,7 +115,7 @@ assert result['verified'] is False
 
 Only documented country/event/capability/scenario fields are accepted. Never send identity numbers, bank accounts, documents or credentials to the sandbox. Simulation IDs encode fixtures and are not unique transaction identifiers. A synthetic match cannot authorize real users or payments. Research evidence is distinct from Gridzen availability or commercial permission.
 
-## Repository checkout: local service and checks
+## Repository source: local service and checks
 
 ```sh
 python -m pip install '.[test,server]'
@@ -126,7 +126,7 @@ uvicorn gridzen_developer.server:app --host 127.0.0.1 --port 8030
 
 Production uses an independent container at localhost:8030 proxied only under `/developers/`. See deploy/compose.yml and deploy/developers.conf. Removing that proxy file and stopping this container rolls back the preview; the existing API and Agent Company stacks are separate.
 
-## Repository checkout: build distributions
+## Repository source: build distributions
 
 `python scripts/build_downloads.py` creates allowlisted developer-kit and Skills ZIPs; it excludes tests, deployment files, private credentials and itself from recursive download packaging. `python scripts/build_catalog.py <repo>/docs/research/identity-verification/2026-10-07` refreshes the public research projection. Main repository report files remain the provenance source.
 
@@ -143,11 +143,11 @@ npx skills add immurray/gridzen-developer-kit
 Install the tagged Python/MCP release from GitHub (Python 3.11+ and Git):
 
 ```sh
-python -m pip install "gridzen-developer-kit[mcp] @ git+https://github.com/immurray/gridzen-developer-kit.git@v0.6.0"
+python -m pip install "gridzen-developer-kit[mcp] @ git+https://github.com/immurray/gridzen-developer-kit.git@v0.7.1"
 ```
 
-PyPI 0.6.0 is published and verified. Install with `python -m pip install
-gridzen-developer-kit`. See [the release tracker](distribution/STATUS.md) for
+Install the latest PyPI release with `python -m pip install --upgrade
+gridzen-developer-kit`. See [the release tracker](https://github.com/immurray/gridzen-developer-kit/blob/main/distribution/STATUS.md) for
 publication and installation evidence.
 
 Remote client configuration (conventional JSON; client syntax may vary):
@@ -166,16 +166,17 @@ Original code and Skills: MIT. Research provenance and third-party rights:
 
 ## Marketplace availability
 
-Source and previous release downloads are public. Existing Registry and Skills.sh listings cover the research service; new product profiles are not separate approved listings. Docker catalog submission is awaiting review. See [the publication ledger](distribution/STATUS.md) for exact status and remaining platform steps.
+Source and previous release downloads are public. Existing Registry and Skills.sh listings cover the research service; new product profiles are not separate approved listings. Docker catalog submission is awaiting review. See [the publication ledger](https://github.com/immurray/gridzen-developer-kit/blob/main/distribution/STATUS.md) for exact status and remaining platform steps.
 
 
-## Six bundled Skills (0.6.0)
+## 14 bundled Skills (0.7.1)
 
 `python -m pip install gridzen-developer-kit` installs the CLI, stdio MCP dependencies
-and all six Skill directories. Version 0.6.0 is published on
-[PyPI](https://pypi.org/project/gridzen-developer-kit/0.6.0/); clean installation,
-CLI, stdio MCP and all six bundled Skill directories were verified. No extra MCP
-dependency installation is required.
+and all 14 Skill directories.
+
+The 14 Skills comprise 6 research/workflow Skills and 8 single-task profiles. Of the 8 profiles, 3 run offline and 5 merchant profiles require separate authorization. Five public MCP tools provide research/synthetic operations. No live identity verification. No extra MCP
+dependency installation is required. Check available versions on
+[PyPI](https://pypi.org/project/gridzen-developer-kit/).
 
 ```sh
 gridzen coverage --country MX
@@ -189,12 +190,12 @@ copy a complete directory into your assistant's configured Skills directory to
 activate it. Installing a wheel does not automatically activate a client's Skills.
 
 The existing select/integrate/explain Skills remain available. Added offline
-workflows, version 1.0.0: `mexico-pilot-scoper`, `payout-policy-designer`, and
-`provider-rights-readiness`. Each includes MIT, README, complete response fixtures
+workflows, version 1.0.0, cover evaluation scope, evidence-review policies and
+provider-rights readiness. Each includes MIT, README, complete response fixtures
 and agent acceptance prompts. They make no third-party calls and grant no real
 verification, legal approval or regulatory conclusion.
 
-## Configure your assistant (v0.6.0)
+## Configure your assistant (v0.7.1)
 
 ```sh
 python3 -m venv .venv
@@ -236,7 +237,7 @@ gridzen feedback --task signup_phone --country US --outcome blocked --blocker mi
 gridzen feedback --input task-summary.json --share
 ```
 
-Phone intelligence is not OTP or ownership verification. Identity fixtures are not hosted document/liveness sessions. Payout matching remains a prototype with no real enabled route. Provider intake Skills are for provider operations/BYO, not a universal customer gate.
+Phone intelligence is not OTP or ownership verification. Identity fixtures are not hosted document/liveness sessions. Provider intake Skills are for provider operations/BYO, not a universal customer gate.
 
 Remote APIs count fixed task/capability/country/stage/error categories for 90 days, including technical failures. They store no arguments, identity data, credentials, raw chats or per-user tracking. Local feedback is off by default. After explicit opt-in, CLI and stdio MCP automatically upload category-only events. Reading static Skills remains unobservable. Optional feedback requires explicit consent, contains only fixed categories, and is unverified self-reported evidence. A SHA-256 hash of its random receipt ID is retained 30 days for 30-day retry deduplication; the ID itself is not stored. Counters are capped at 10,000 requests/day and 500 summaries/day per database; missing history or offline usage is unknown. Requests are not unique customers.
 
@@ -259,7 +260,7 @@ Local queued events expire after 30 days and are removed on the next enqueue/flu
 
 ## Separate owner-approved customer pilot
 
-The published 0.6.0 kit and its five public tools remain research/synthetic tools. A separate hosted pilot accepts customer applications for basic signup-phone validity and hosted personal identity onboarding: [apply](https://gridzen.ai/console/pilot?lang=en), [integration guide](https://gridzen.ai/console/pilot-guide?lang=en), [public scope](https://gridzen.ai/guides/customer-pilot/).
+The package and its five public tools retain their research/synthetic boundaries. A separate hosted pilot accepts customer applications for basic signup-phone validity and hosted personal identity onboarding: [apply](https://gridzen.ai/console/pilot?lang=en), [integration guide](https://gridzen.ai/console/pilot-guide?lang=en), [public scope](https://gridzen.ai/guides/customer-pilot/).
 
 Submitting an application never activates production. The owner must approve supplier rights, downstream agreements, capabilities, request limits and expiry; only confirmed free allowances are used. The production pilot has its own downloaded MCP client and merchant API key. Do not send documents, faces or provider keys to the public research MCP. Basic phone validity does not provide OTP or ownership.
 
@@ -292,10 +293,25 @@ not prove all agents have executed or recommended the skills.
 
 ## Existing Mexico SPEI payment evidence
 
-In the updated GitHub checkout or developer ZIP (the existing PyPI release does not yet include this task), use `gridzen plan --country MX --event payout --task mx_cep_existing_payment --stage production` to discover the separate authenticated CEP trial. Public tools remain research/synthetic only. [Live capability conditions](https://gridzen.ai/console/api/payment-evidence/mx/cep/capabilities) require a merchant key; do not send transaction details or keys to public tools. [Runnable offline example](examples/cep_reconciliation/) makes no network calls. CEP preserves original XML, independent signature and exact expected-transaction binding; historical names do not establish current identity or account control. No transfer is created; paid checkout remains disabled.
+In the installed package or developer source ZIP, use `gridzen tools --product mx-cep` to discover the separate authenticated CEP workflow. Public tools remain research/synthetic only. [Live capability conditions](https://gridzen.ai/console/api/payment-evidence/mx/cep/capabilities) require a merchant key; do not send transaction details or keys to public tools. [Runnable offline example](examples/cep_reconciliation/) makes no network calls. CEP preserves original XML, independent signature and exact expected-transaction binding; historical names do not establish current identity or account control. This workflow verifies existing SPEI evidence; it does not initiate a transfer.
 
 ## Mexico identity and beneficiary-name comparison
 
 [Task, pricing boundaries and zero-cost integration examples](docs/mexico-identity-account.md) cover first account binding, account changes and exception review. The 14 MXN quote does not enable production calls; read the authenticated capability response. Public MCP and Skills remain research/synthetic only.
 
 [Run the identity/account result example offline, without signup](examples/mx_identity_account/).
+
+## Documents included with pip installation
+
+The wheel and source distribution include the same 14 canonical Skill directories
+and public integration guides as the website source download. English, Chinese and
+Spanish READMEs, task guides, ten-client instructions, examples and client templates
+are installed under `share/gridzen-developer-kit/` in your Python environment.
+
+```sh
+python -c "import sysconfig; from pathlib import Path; print(Path(sysconfig.get_path('data')) / 'share/gridzen-developer-kit/README.md')"
+```
+
+Open that README or `docs/harness/README.md` locally. Research snapshots and old
+offline identifiers remain compatible; they do not grant live verification or
+business authorization. CEP/SPEI guides describe evidence for existing transactions.

{gridzen_developer_kit-0.7.0 → gridzen_developer_kit-0.7.1}/README.es.md

@@ -1,4 +1,4 @@
-# Kit de desarrollo Gridzen 0.6.0
+# Kit de desarrollo Gridzen 0.7.1
 
 [Integración directa o GridZen: evalúe su tarea](docs/verification-evaluation.md#español) · [Preparación y costes](https://gridzen.ai/console/learn?lang=es&source=developer_kit#decision-fit)
 
@@ -11,7 +11,7 @@
 - [Recuperar callbacks retrasados](https://gridzen.ai/console/learn/callback-recovery?lang=es)
 - [Permisos después de verificar](https://gridzen.ai/console/learn/business-permission-boundary?lang=es)
 
-[SQLite](examples/verification_delivery/) · [n8n](examples/n8n/) · [Smithery](https://smithery.ai/servers/support-35ug/gridzen-verification)
+[SQLite](examples/verification_delivery/) · [n8n](examples/n8n/)
 
 Los ejemplos son sintéticos. Se prepara el precio por verificación; pagos reales deshabilitados.
 
@@ -20,9 +20,9 @@ Los ejemplos son sintéticos. Se prepara el precio por verificación; pagos real
 
 Abra la [prueba inmediata de GridZen](https://gridzen.ai/console/start?lang=es) para simular comprobaciones telefónicas e incorporación de identidad sin cuenta, clave ni aprobación. Los escenarios de éxito, rechazo e indisponibilidad no llaman a proveedores reales ni verifican personas. Los agentes pueden usar el [MCP de prueba sin clave](https://gridzen.ai/console/downloads/quickstart_mcp.py) con `mcp==2.3.0` y `httpx==0.28.1` en un entorno virtual.
 
-Conecte una cuenta sandbox con correo verificado para guardar registros y recibir callbacks. La producción sigue siendo un piloto gratuito controlado; autoservicio de producción y pagos no están habilitados. Esta actualización documental no cambia PyPI ni la versión del registro oficial MCP.
+Conecte una cuenta sandbox con correo verificado para guardar registros y recibir callbacks. El acceso real depende de cada producto: algunas rutas permiten pruebas limitadas y otras siguen sin estar disponibles. Consulta capacidades y permisos autenticados; un precio publicado no habilita compras. El paquete y el MCP Registry remoto tienen versiones independientes; instalar no concede permisos de comerciante.
 
-Investigación sobre 198 países y territorios, planificación de integraciones, cinco resultados simulados, CLI/SDK HTTP de Python, MCP local y seis Skills. No hay canales de proveedores reales activos. Ningún resultado simulado verifica a una persona real.
+Investigación sobre 198 países y territorios, planificación de integraciones, cinco resultados simulados, CLI/SDK HTTP de Python, MCP local y 14 Skills. El MCP público de investigación y simulación no llama a proveedores reales; los perfiles de comerciante requieren autorización separada. Ningún resultado simulado verifica a una persona real.
 
 Prueba y guía: https://gridzen.ai/developers/ . El selector permite cambiar entre español, inglés y chino, y recuerda la elección. La investigación es del 2026-10-07; las fuentes y sus restricciones se conservan en el idioma original.
 
@@ -34,9 +34,9 @@ Descarga y descomprime gridzen-developer-kit.zip. Ejecuta lo siguiente desde el
 python3 -m venv .venv
 . .venv/bin/activate
 python -m pip install './gridzen-developer-kit[mcp]'
-gridzen plan --country ID --event payout
+gridzen plan --country ID --event onboarding
 gridzen simulate --country ID --capability bank_account_match --scenario timeout
-python gridzen-developer-kit/examples/payout.py
+python gridzen-developer-kit/examples/customer_tasks.py
 ```
 
 En Windows, activa con `.venv\Scripts\activate`. La CLI y MCP local funcionan sin conexión tras instalar las dependencias; el SDK HTTP y el ejemplo de Python llaman al entorno público de pruebas.
@@ -49,9 +49,9 @@ Añade un servidor stdio local a un cliente compatible y sustituye command por l
 {"mcpServers":{"gridzen":{"command":"/absolute/path/to/.venv/bin/gridzen-mcp","args":[]}}}
 ```
 
-Prueba: «Planifica una verificación de pagos para Indonesia y simula una espera agotada del proveedor». Las cinco herramientas consultan cobertura, planifican, generan simulaciones, recuperan pruebas y explican resultados. La configuración depende del cliente; no hay endpoint MCP remoto de producción.
+Prueba: «Planifica una verificación de incorporación para Indonesia y simula una espera agotada del proveedor». Las cinco herramientas consultan cobertura, planifican, generan simulaciones, recuperan pruebas y explican resultados. La configuración depende del cliente; no hay endpoint MCP remoto de producción.
 
-Copia cada carpeta de `skills/` al directorio de habilidades del agente, conservando `SKILL.md` y sus referencias. Los seis Skills cubren selección, integración de pruebas, explicación de resultados, preparación de permisos, políticas de pagos y planificación de pilotos en México. Los identificadores permanecen en inglés; el agente puede explicar los resultados en español.
+Copia cada carpeta de `skills/` al directorio de habilidades del agente, conservando `SKILL.md` y sus referencias. Los 6 Skills de investigación/flujos cubren selección, integración de pruebas, explicación de resultados, preparación de permisos, políticas de revisión de evidencia y planificación de pilotos en México. Los identificadores permanecen en inglés; el agente puede explicar los resultados en español.
 
 ## Interpretación
 
@@ -79,16 +79,17 @@ Código original bajo MIT; consulte NOTICE.md para los derechos de terceros.
 
 ## Publicación en directorios
 
-El código, las descargas, la entrada oficial de MCP Registry y tres páginas de Skills.sh están publicados. La propuesta del catálogo de Docker está pendiente de revisión. Consulta [el registro de publicación](distribution/STATUS.md).
+El código, las descargas, la entrada oficial de MCP Registry y tres páginas de Skills.sh están publicados. La propuesta del catálogo de Docker está pendiente de revisión. Consulta [el registro de publicación](https://github.com/immurray/gridzen-developer-kit/blob/main/distribution/STATUS.md).
 
 
-## Six bundled Skills (0.6.0)
+## 14 bundled Skills (0.7.1)
 
 `python -m pip install gridzen-developer-kit` installs the CLI, stdio MCP dependencies
-and all six Skill directories. Version 0.6.0 is published on
-[PyPI](https://pypi.org/project/gridzen-developer-kit/0.6.0/); clean installation,
-CLI, stdio MCP and all six bundled Skill directories were verified. No extra MCP
-dependency installation is required.
+and all 14 Skill directories.
+
+The 14 Skills comprise 6 research/workflow Skills and 8 single-task profiles. Of the 8 profiles, 3 run offline and 5 merchant profiles require separate authorization. Five public MCP tools provide research/synthetic operations. No live identity verification. No extra MCP
+dependency installation is required. Check available versions on
+[PyPI](https://pypi.org/project/gridzen-developer-kit/).
 
 ```sh
 gridzen coverage --country MX
@@ -102,8 +103,8 @@ copy a complete directory into your assistant's configured Skills directory to
 activate it. Installing a wheel does not automatically activate a client's Skills.
 
 The existing select/integrate/explain Skills remain available. Added offline
-workflows, version 1.0.0: `mexico-pilot-scoper`, `payout-policy-designer`, and
-`provider-rights-readiness`. Each includes MIT, README, complete response fixtures
+workflows, version 1.0.0, cover evaluation scope, evidence-review policies and
+provider-rights readiness. Each includes MIT, README, complete response fixtures
 and agent acceptance prompts. They make no third-party calls and grant no real
 verification, legal approval or regulatory conclusion.
 
@@ -134,7 +135,7 @@ gridzen feedback --task signup_phone --country US --outcome blocked --blocker mi
 gridzen feedback --input task-summary.json --share
 ```
 
-Phone intelligence is not OTP or ownership verification. Identity fixtures are not hosted document/liveness sessions. Payout matching remains a prototype with no real enabled route. Provider intake Skills are for provider operations/BYO, not a universal customer gate.
+Phone intelligence is not OTP or ownership verification. Identity fixtures are not hosted document/liveness sessions. Provider intake Skills are for provider operations/BYO, not a universal customer gate.
 
 Remote APIs count fixed task/capability/country/stage/error categories for 90 days, including technical failures. They store no arguments, identity data, credentials, raw chats or per-user tracking. Local feedback is off by default. After explicit opt-in, CLI and stdio MCP automatically upload category-only events. Reading static Skills remains unobservable. Optional feedback requires explicit consent, contains only fixed categories, and is unverified self-reported evidence. A SHA-256 hash of its random receipt ID is retained 30 days for 30-day retry deduplication; the ID itself is not stored. Counters are capped at 10,000 requests/day and 500 summaries/day per database; missing history or offline usage is unknown. Requests are not unique customers.
 
@@ -159,7 +160,7 @@ Local queued events expire after 30 days and are removed on the next enqueue/flu
 
 ## Piloto independiente con aprobación del responsable
 
-El kit publicado 0.6.0 y sus cinco herramientas públicas siguen siendo de investigación y simulación. Puede solicitar un piloto independiente de validez básica del teléfono e incorporación de identidad: [solicitud](https://gridzen.ai/console/pilot?lang=es), [guía](https://gridzen.ai/console/pilot-guide?lang=es), [alcance](https://gridzen.ai/es/guides/customer-pilot/).
+El paquete y sus cinco herramientas públicas conservan sus límites de investigación y simulación. Puede solicitar un piloto independiente de validez básica del teléfono e incorporación de identidad: [solicitud](https://gridzen.ai/console/pilot?lang=es), [guía](https://gridzen.ai/console/pilot-guide?lang=es), [alcance](https://gridzen.ai/es/guides/customer-pilot/).
 
 Solicitar no activa producción. El responsable confirma derechos del proveedor, acuerdos, capacidades, límites y vencimiento; solo se usan cupos gratuitos confirmados. El piloto utiliza un cliente MCP separado y una clave comercial. No envíe documentos, caras ni claves del proveedor al MCP público. La validez básica no proporciona OTP ni prueba de titularidad.
 

{gridzen_developer_kit-0.7.0 → gridzen_developer_kit-0.7.1}/README.md

@@ -1,4 +1,4 @@
-# Gridzen Developer Kit 0.7.0
+# Gridzen Developer Kit 0.7.1
 
 The hosted developer interface supports Vietnamese alongside English, Spanish and Simplified Chinese: https://gridzen.ai/developers/?lang=vi . UI language does not enable live checks or country coverage. See [UI language maintenance](docs/multilingual-ui.md).
 
@@ -19,9 +19,9 @@ python3 -m venv .venv
 
 Open [GridZen instant trial](https://gridzen.ai/console/start?lang=en) to run synthetic signup-phone and identity-onboarding responses without an account, API key or approval. Success, rejection and unavailable scenarios make no upstream calls and verify no real person. Agents can use the separate [key-free trial MCP](https://gridzen.ai/console/downloads/quickstart_mcp.py), installed with `mcp==2.3.0` and `httpx==0.28.1` in a virtual environment.
 
-For persistent test records and supplier sandbox callbacks, connect a verified merchant sandbox account. Production access is capability-specific: eligible routes may offer bounded real trials, while others remain unavailable. Read the authenticated capability conditions; published prices do not enable paid purchases. This documentation update does not change PyPI or the official MCP Registry version.
+For persistent test records and supplier sandbox callbacks, connect a verified merchant sandbox account. Production access is capability-specific: eligible routes may offer bounded real trials, while others remain unavailable. Read the authenticated capability conditions; published prices do not enable paid purchases. Package releases and the hosted MCP Registry entry have independent versions; installing this package grants no merchant permissions.
 
-Fourteen Skills: the original six research/workflow Skills plus eight single-task profiles. Three new tools run offline; five merchant profiles call the existing authenticated GridZen API only with separate authorization, current availability and funding. The anonymous remote MCP retains five research/synthetic tools and never performs live verification. Research covers 198 countries/territories as a dated 2026-10-07 snapshot, not live service coverage.
+Fourteen Skills: the original six research/workflow Skills plus eight single-task profiles. Three new tools run offline; five merchant profiles call the existing authenticated GridZen API only with separate authorization, current availability and permitted use. The anonymous remote MCP retains five research/synthetic tools and never performs live verification. Research covers 198 countries/territories as a dated 2026-10-07 snapshot, not live service coverage.
 
 [中文指南](README.zh-CN.md) · [Guía en español](README.es.md)
 
@@ -34,9 +34,9 @@ Fourteen Skills: the original six research/workflow Skills plus eight single-tas
 | Missing or delayed callback | [Guide](https://gridzen.ai/console/learn/callback-recovery?lang=en) | [Recovery fixture](examples/verification_delivery/) |
 | Verification to business permission | [Guide](https://gridzen.ai/console/learn/business-permission-boundary?lang=en) | [Self-hosted n8n fixture](examples/n8n/) |
 
-[Chinese and Spanish article files](distribution/market-expansion-2026-10-13/articles/) · [Demo video](distribution/market-expansion-2026-10-13/media/identity-three-outcomes.mp4) · [Smithery listing](https://smithery.ai/servers/support-35ug/gridzen-verification).
+[Chinese and Spanish article files](https://github.com/immurray/gridzen-developer-kit/tree/main/distribution/market-expansion-2026-10-13/articles/) · [Demo video](https://github.com/immurray/gridzen-developer-kit/blob/main/distribution/market-expansion-2026-10-13/media/identity-three-outcomes.mp4).
 
-Public examples are synthetic. Approved prices and per-product availability are published at https://gridzen.ai/pricing/; live payments remain disabled. [Request an approved pilot](https://gridzen.ai/console/pilot), without sending identity documents or credentials to public MCP tools.
+Public examples are synthetic. Approved prices and per-product availability are published at https://gridzen.ai/pricing/; paid activation remains unavailable. [Request an approved pilot](https://gridzen.ai/console/pilot), without sending identity documents or credentials to public MCP tools.
 
 [Per-check plan and activation requirements](https://gridzen.ai/console/quote?lang=en) · [JSON](https://gridzen.ai/console/api/commercial/options)
 
@@ -51,9 +51,9 @@ python3 -m venv .venv
 . .venv/bin/activate
 python -m pip install './gridzen-developer-kit[mcp]'
 gridzen coverage --country ID --capability bank_account_match
-gridzen plan --country ID --event payout
+gridzen plan --country ID --event onboarding
 gridzen simulate --country ID --capability bank_account_match --scenario timeout
-python gridzen-developer-kit/examples/payout.py
+python gridzen-developer-kit/examples/customer_tasks.py
 ```
 
 Python 3.11+. CLI and MCP use the bundled offline catalog and fixtures; the Python HTTP client/example calls the public sandbox. Dependencies are downloaded only during installation. API reference: https://gridzen.ai/developers/api/openapi.json .
@@ -77,7 +77,7 @@ Copy the individual directories from `skills/` into your compatible agent's proj
 ```python
 from gridzen_developer.client import Gridzen
 client = Gridzen()
-plan = client.plan('ID', 'payout')
+plan = client.plan('ID', 'onboarding')
 result = client.simulate('ID', 'bank_account_match', 'not_found')
 assert result['status'] == 'inconclusive'
 assert result['verified'] is False
@@ -85,7 +85,7 @@ assert result['verified'] is False
 
 Only documented country/event/capability/scenario fields are accepted. Never send identity numbers, bank accounts, documents or credentials to the sandbox. Simulation IDs encode fixtures and are not unique transaction identifiers. A synthetic match cannot authorize real users or payments. Research evidence is distinct from Gridzen availability or commercial permission.
 
-## Repository checkout: local service and checks
+## Repository source: local service and checks
 
 ```sh
 python -m pip install '.[test,server]'
@@ -96,7 +96,7 @@ uvicorn gridzen_developer.server:app --host 127.0.0.1 --port 8030
 
 Production uses an independent container at localhost:8030 proxied only under `/developers/`. See deploy/compose.yml and deploy/developers.conf. Removing that proxy file and stopping this container rolls back the preview; the existing API and Agent Company stacks are separate.
 
-## Repository checkout: build distributions
+## Repository source: build distributions
 
 `python scripts/build_downloads.py` creates allowlisted developer-kit and Skills ZIPs; it excludes tests, deployment files, private credentials and itself from recursive download packaging. `python scripts/build_catalog.py <repo>/docs/research/identity-verification/2026-10-07` refreshes the public research projection. Main repository report files remain the provenance source.
 
@@ -113,11 +113,11 @@ npx skills add immurray/gridzen-developer-kit
 Install the tagged Python/MCP release from GitHub (Python 3.11+ and Git):
 
 ```sh
-python -m pip install "gridzen-developer-kit[mcp] @ git+https://github.com/immurray/gridzen-developer-kit.git@v0.6.0"
+python -m pip install "gridzen-developer-kit[mcp] @ git+https://github.com/immurray/gridzen-developer-kit.git@v0.7.1"
 ```
 
-PyPI 0.6.0 is published and verified. Install with `python -m pip install
-gridzen-developer-kit`. See [the release tracker](distribution/STATUS.md) for
+Install the latest PyPI release with `python -m pip install --upgrade
+gridzen-developer-kit`. See [the release tracker](https://github.com/immurray/gridzen-developer-kit/blob/main/distribution/STATUS.md) for
 publication and installation evidence.
 
 Remote client configuration (conventional JSON; client syntax may vary):
@@ -136,16 +136,17 @@ Original code and Skills: MIT. Research provenance and third-party rights:
 
 ## Marketplace availability
 
-Source and previous release downloads are public. Existing Registry and Skills.sh listings cover the research service; new product profiles are not separate approved listings. Docker catalog submission is awaiting review. See [the publication ledger](distribution/STATUS.md) for exact status and remaining platform steps.
+Source and previous release downloads are public. Existing Registry and Skills.sh listings cover the research service; new product profiles are not separate approved listings. Docker catalog submission is awaiting review. See [the publication ledger](https://github.com/immurray/gridzen-developer-kit/blob/main/distribution/STATUS.md) for exact status and remaining platform steps.
 
 
-## Six bundled Skills (0.6.0)
+## 14 bundled Skills (0.7.1)
 
 `python -m pip install gridzen-developer-kit` installs the CLI, stdio MCP dependencies
-and all six Skill directories. Version 0.6.0 is published on
-[PyPI](https://pypi.org/project/gridzen-developer-kit/0.6.0/); clean installation,
-CLI, stdio MCP and all six bundled Skill directories were verified. No extra MCP
-dependency installation is required.
+and all 14 Skill directories.
+
+The 14 Skills comprise 6 research/workflow Skills and 8 single-task profiles. Of the 8 profiles, 3 run offline and 5 merchant profiles require separate authorization. Five public MCP tools provide research/synthetic operations. No live identity verification. No extra MCP
+dependency installation is required. Check available versions on
+[PyPI](https://pypi.org/project/gridzen-developer-kit/).
 
 ```sh
 gridzen coverage --country MX
@@ -159,12 +160,12 @@ copy a complete directory into your assistant's configured Skills directory to
 activate it. Installing a wheel does not automatically activate a client's Skills.
 
 The existing select/integrate/explain Skills remain available. Added offline
-workflows, version 1.0.0: `mexico-pilot-scoper`, `payout-policy-designer`, and
-`provider-rights-readiness`. Each includes MIT, README, complete response fixtures
+workflows, version 1.0.0, cover evaluation scope, evidence-review policies and
+provider-rights readiness. Each includes MIT, README, complete response fixtures
 and agent acceptance prompts. They make no third-party calls and grant no real
 verification, legal approval or regulatory conclusion.
 
-## Configure your assistant (v0.6.0)
+## Configure your assistant (v0.7.1)
 
 ```sh
 python3 -m venv .venv
@@ -206,7 +207,7 @@ gridzen feedback --task signup_phone --country US --outcome blocked --blocker mi
 gridzen feedback --input task-summary.json --share
 ```
 
-Phone intelligence is not OTP or ownership verification. Identity fixtures are not hosted document/liveness sessions. Payout matching remains a prototype with no real enabled route. Provider intake Skills are for provider operations/BYO, not a universal customer gate.
+Phone intelligence is not OTP or ownership verification. Identity fixtures are not hosted document/liveness sessions. Provider intake Skills are for provider operations/BYO, not a universal customer gate.
 
 Remote APIs count fixed task/capability/country/stage/error categories for 90 days, including technical failures. They store no arguments, identity data, credentials, raw chats or per-user tracking. Local feedback is off by default. After explicit opt-in, CLI and stdio MCP automatically upload category-only events. Reading static Skills remains unobservable. Optional feedback requires explicit consent, contains only fixed categories, and is unverified self-reported evidence. A SHA-256 hash of its random receipt ID is retained 30 days for 30-day retry deduplication; the ID itself is not stored. Counters are capped at 10,000 requests/day and 500 summaries/day per database; missing history or offline usage is unknown. Requests are not unique customers.
 
@@ -229,7 +230,7 @@ Local queued events expire after 30 days and are removed on the next enqueue/flu
 
 ## Separate owner-approved customer pilot
 
-The published 0.6.0 kit and its five public tools remain research/synthetic tools. A separate hosted pilot accepts customer applications for basic signup-phone validity and hosted personal identity onboarding: [apply](https://gridzen.ai/console/pilot?lang=en), [integration guide](https://gridzen.ai/console/pilot-guide?lang=en), [public scope](https://gridzen.ai/guides/customer-pilot/).
+The package and its five public tools retain their research/synthetic boundaries. A separate hosted pilot accepts customer applications for basic signup-phone validity and hosted personal identity onboarding: [apply](https://gridzen.ai/console/pilot?lang=en), [integration guide](https://gridzen.ai/console/pilot-guide?lang=en), [public scope](https://gridzen.ai/guides/customer-pilot/).
 
 Submitting an application never activates production. The owner must approve supplier rights, downstream agreements, capabilities, request limits and expiry; only confirmed free allowances are used. The production pilot has its own downloaded MCP client and merchant API key. Do not send documents, faces or provider keys to the public research MCP. Basic phone validity does not provide OTP or ownership.
 
@@ -262,10 +263,25 @@ not prove all agents have executed or recommended the skills.
 
 ## Existing Mexico SPEI payment evidence
 
-In the updated GitHub checkout or developer ZIP (the existing PyPI release does not yet include this task), use `gridzen plan --country MX --event payout --task mx_cep_existing_payment --stage production` to discover the separate authenticated CEP trial. Public tools remain research/synthetic only. [Live capability conditions](https://gridzen.ai/console/api/payment-evidence/mx/cep/capabilities) require a merchant key; do not send transaction details or keys to public tools. [Runnable offline example](examples/cep_reconciliation/) makes no network calls. CEP preserves original XML, independent signature and exact expected-transaction binding; historical names do not establish current identity or account control. No transfer is created; paid checkout remains disabled.
+In the installed package or developer source ZIP, use `gridzen tools --product mx-cep` to discover the separate authenticated CEP workflow. Public tools remain research/synthetic only. [Live capability conditions](https://gridzen.ai/console/api/payment-evidence/mx/cep/capabilities) require a merchant key; do not send transaction details or keys to public tools. [Runnable offline example](examples/cep_reconciliation/) makes no network calls. CEP preserves original XML, independent signature and exact expected-transaction binding; historical names do not establish current identity or account control. This workflow verifies existing SPEI evidence; it does not initiate a transfer.
 
 ## Mexico identity and beneficiary-name comparison
 
 [Task, pricing boundaries and zero-cost integration examples](docs/mexico-identity-account.md) cover first account binding, account changes and exception review. The 14 MXN quote does not enable production calls; read the authenticated capability response. Public MCP and Skills remain research/synthetic only.
 
 [Run the identity/account result example offline, without signup](examples/mx_identity_account/).
+
+## Documents included with pip installation
+
+The wheel and source distribution include the same 14 canonical Skill directories
+and public integration guides as the website source download. English, Chinese and
+Spanish READMEs, task guides, ten-client instructions, examples and client templates
+are installed under `share/gridzen-developer-kit/` in your Python environment.
+
+```sh
+python -c "import sysconfig; from pathlib import Path; print(Path(sysconfig.get_path('data')) / 'share/gridzen-developer-kit/README.md')"
+```
+
+Open that README or `docs/harness/README.md` locally. Research snapshots and old
+offline identifiers remain compatible; they do not grant live verification or
+business authorization. CEP/SPEI guides describe evidence for existing transactions.

{gridzen_developer_kit-0.7.0 → gridzen_developer_kit-0.7.1}/README.zh-CN.md

@@ -1,4 +1,4 @@
-# Gridzen 开发者工具包 0.6.0
+# Gridzen 开发者工具包 0.7.1
 
 [直连还是使用 GridZen：按任务评估](docs/verification-evaluation.md#中文) · [正式上线与费用检查](https://gridzen.ai/console/learn?lang=zh&source=developer_kit#decision-fit)
 
@@ -11,7 +11,7 @@
 - [延迟回调恢复](https://gridzen.ai/console/learn/callback-recovery?lang=zh)
 - [核验后业务权限](https://gridzen.ai/console/learn/business-permission-boundary?lang=zh)
 
-[SQLite](examples/verification_delivery/) · [n8n](examples/n8n/) · [Smithery](https://smithery.ai/servers/support-35ug/gridzen-verification)
+[SQLite](examples/verification_delivery/) · [n8n](examples/n8n/)
 
 公开示例是模拟。按次核验报价正在准备，生产收费尚未启用。
 
@@ -20,9 +20,9 @@
 
 打开[立即试用](https://gridzen.ai/console/start?lang=zh)，无需账号、密钥或审批即可运行注册号码与身份入驻的模拟响应。可测试成功、未通过和暂不可用；不调用真实上游，不核验真人。Agent 可下载独立的[免密钥试用 MCP](https://gridzen.ai/console/downloads/quickstart_mcp.py)，在虚拟环境安装 `mcp==2.3.0`、`httpx==0.28.1` 后启动。
 
-需要保存测试记录、接收供应商沙盒回传时，再连接已验证邮箱的商户沙盒账号。真实核验仍为独立受控免费试点；自助生产和收费尚未开放。本次只更新接入说明，不更改 PyPI 或官方 MCP Registry 版本。
+需要保存测试记录、接收供应商沙盒回传时，再连接已验证邮箱的商户沙盒账号。真实能力按产品区分，部分路线可提供有界试用，其他路线可能仍不可用。以已登录工作台的当前能力和权限为准；公开价格不代表已开放购买。安装包与远程 MCP Registry 分别版本化，安装不授予商户权限。
 
-工具包提供 198 个国家/地区的核验研究、接入方案、五种模拟结果、Python CLI/HTTP SDK、本地 MCP 和六个 Skills。当前没有启用真实供应商通道，模拟结果不代表真实人员通过核验。
+工具包提供 198 个国家/地区的核验研究、接入方案、五种模拟结果、Python CLI/HTTP SDK、本地 MCP 和 14 个 Skills。匿名研究／沙盒 MCP 不调用真实供应商；商户配置需要单独授权，模拟结果不代表真实人员通过核验。
 
 在线试用与中文指南：https://gridzen.ai/developers/ 。页面右上角可切换中文、英文和西班牙文，并记住选择。研究快照日期为 2026-10-07，来源和原始接入限制保持原文。
 
@@ -34,9 +34,9 @@
 python3 -m venv .venv
 . .venv/bin/activate
 python -m pip install './gridzen-developer-kit[mcp]'
-gridzen plan --country ID --event payout
+gridzen plan --country ID --event onboarding
 gridzen simulate --country ID --capability bank_account_match --scenario timeout
-python gridzen-developer-kit/examples/payout.py
+python gridzen-developer-kit/examples/customer_tasks.py
 ```
 
 Windows 下使用 `.venv\Scripts\activate` 激活虚拟环境。CLI 和本地 MCP 安装后可离线使用；Python HTTP SDK 与示例调用公开沙盒。
@@ -49,9 +49,9 @@ Windows 下使用 `.venv\Scripts\activate` 激活虚拟环境。CLI 和本地 MC
 {"mcpServers":{"gridzen":{"command":"/absolute/path/to/.venv/bin/gridzen-mcp","args":[]}}}
 ```
 
-可输入：“为印度尼西亚制定付款核验接入方案，然后测试供应商超时。”五个工具分别查询覆盖、规划、生成模拟结果、读取结果和解释原因。客户端配置格式可能不同；当前没有远程生产 MCP 地址。
+可输入：“为印度尼西亚制定身份入驻核验接入方案，然后测试供应商超时。”五个工具分别查询覆盖、规划、生成模拟结果、读取结果和解释原因。客户端配置格式可能不同；当前没有远程生产 MCP 地址。
 
-将 `skills/` 中各个文件夹复制到 Agent 支持的技能目录，保留 `SKILL.md` 和引用文件。六个 Skill 覆盖方案选择、沙盒接入、结果解释、供应商权限准备、提现政策和墨西哥试点规划。代码标识和技能名称保持英文，Agent 可以用中文讲解。
+将 `skills/` 中各个文件夹复制到 Agent 支持的技能目录，保留 `SKILL.md` 和引用文件。6 个研究/工作流 Skills 覆盖方案选择、沙盒接入、结果解释、供应商权限准备、证据复核策略和墨西哥试点规划。代码标识和技能名称保持英文，Agent 可以用中文讲解。
 
 ## 理解测试结果
 
@@ -72,22 +72,23 @@ Windows 下使用 `.venv\Scripts\activate` 激活虚拟环境。CLI 和本地 MC
 工具参数发送到 Gridzen；本地 stdio 安装后仍可离线运行。
 
 Skills 安装：`npx skills add immurray/gridzen-developer-kit`。
-源码：https://github.com/immurray/gridzen-developer-kit 。PyPI 尚未发布，
-当前请使用 GitHub 发布包或官网下载包。公开源码使用 MIT 许可证；第三方资料
+源码：https://github.com/immurray/gridzen-developer-kit 。可从 PyPI 安装，
+或使用 GitHub 发布包和官网下载包；已核实发行状态见发布台账。公开源码使用 MIT 许可证；第三方资料
 权利及研究边界见 NOTICE.md。
 
 ## 市场发布状态
 
-源码、版本下载、官方 MCP Registry 和三个 Skills.sh 技能页已公开；Docker 目录投稿待审核。各渠道真实状态及剩余步骤见[发布台账](distribution/STATUS.md)。
+源码、版本下载、官方 MCP Registry 和三个 Skills.sh 技能页已公开；Docker 目录投稿待审核。各渠道真实状态及剩余步骤见[发布台账](https://github.com/immurray/gridzen-developer-kit/blob/main/distribution/STATUS.md)。
 
 
-## Six bundled Skills (0.6.0)
+## 14 bundled Skills (0.7.1)
 
 `python -m pip install gridzen-developer-kit` installs the CLI, stdio MCP dependencies
-and all six Skill directories. Version 0.6.0 is published on
-[PyPI](https://pypi.org/project/gridzen-developer-kit/0.6.0/); clean installation,
-CLI, stdio MCP and all six bundled Skill directories were verified. No extra MCP
-dependency installation is required.
+and all 14 Skill directories.
+
+The 14 Skills comprise 6 research/workflow Skills and 8 single-task profiles. Of the 8 profiles, 3 run offline and 5 merchant profiles require separate authorization. Five public MCP tools provide research/synthetic operations. No live identity verification. No extra MCP
+dependency installation is required. Check available versions on
+[PyPI](https://pypi.org/project/gridzen-developer-kit/).
 
 ```sh
 gridzen coverage --country MX
@@ -101,8 +102,8 @@ copy a complete directory into your assistant's configured Skills directory to
 activate it. Installing a wheel does not automatically activate a client's Skills.
 
 The existing select/integrate/explain Skills remain available. Added offline
-workflows, version 1.0.0: `mexico-pilot-scoper`, `payout-policy-designer`, and
-`provider-rights-readiness`. Each includes MIT, README, complete response fixtures
+workflows, version 1.0.0, cover evaluation scope, evidence-review policies and
+provider-rights readiness. Each includes MIT, README, complete response fixtures
 and agent acceptance prompts. They make no third-party calls and grant no real
 verification, legal approval or regulatory conclusion.
 
@@ -133,7 +134,7 @@ gridzen feedback --task signup_phone --country US --outcome blocked --blocker mi
 gridzen feedback --input task-summary.json --share
 ```
 
-Phone intelligence is not OTP or ownership verification. Identity fixtures are not hosted document/liveness sessions. Payout matching remains a prototype with no real enabled route. Provider intake Skills are for provider operations/BYO, not a universal customer gate.
+Phone intelligence is not OTP or ownership verification. Identity fixtures are not hosted document/liveness sessions. Provider intake Skills are for provider operations/BYO, not a universal customer gate.
 
 Remote APIs count fixed task/capability/country/stage/error categories for 90 days, including technical failures. They store no arguments, identity data, credentials, raw chats or per-user tracking. Local feedback is off by default. After explicit opt-in, CLI and stdio MCP automatically upload category-only events. Reading static Skills remains unobservable. Optional feedback requires explicit consent, contains only fixed categories, and is unverified self-reported evidence. A SHA-256 hash of its random receipt ID is retained 30 days for 30-day retry deduplication; the ID itself is not stored. Counters are capped at 10,000 requests/day and 500 summaries/day per database; missing history or offline usage is unknown. Requests are not unique customers.
 
@@ -158,7 +159,7 @@ Local queued events expire after 30 days and are removed on the next enqueue/flu
 
 ## 独立的客户生产试点
 
-已发行的 0.6.0 工具包与公开五个工具仍提供研究和模拟，不自动启用真人核验。客户可以申请独立试点：[申请入口](https://gridzen.ai/console/pilot?lang=zh)、[接入指南](https://gridzen.ai/console/pilot-guide?lang=zh)、[公开范围](https://gridzen.ai/zh/guides/customer-pilot/)。
+工具包与公开五个工具仍提供研究和模拟，不自动启用真人核验。客户可以申请独立试点：[申请入口](https://gridzen.ai/console/pilot?lang=zh)、[接入指南](https://gridzen.ai/console/pilot-guide?lang=zh)、[公开范围](https://gridzen.ai/zh/guides/customer-pilot/)。
 
 申请不会自动开通。负责人核对供应商权限、下游协议、能力、次数和有效期后批准，仅用确认的免费额度。生产试点使用独立下载的 MCP 客户端和商户 Key；不向研究 MCP 提交证件、人脸或供应商密钥。号码基础有效性不提供 OTP 或号码归属证明。
 

{gridzen_developer_kit-0.7.0/src/gridzen_developer/web → gridzen_developer_kit-0.7.1/clients}/compatibility.json

@@ -41,7 +41,7 @@
     {
       "client": "claude-desktop",
       "config_path": "gridzen-clients/claude-desktop/claude_desktop_config.json",
-      "skill_path": "Six individual skill ZIPs; upload in Customize → Skills",
+      "skill_path": "14 individual skill ZIPs; upload in Customize → Skills",
       "template": "clients/claude-desktop.json",
       "manual_import": true,
       "config_tests": "passed",