website-build-skill 0.1.5 → 0.1.7

package/.claude-plugin/plugin.json

@@ -1,10 +1,33 @@
 {
   "name": "website-build-skill",
-  "version": "0.1.5",
-  "description": "A skill pack that teaches your AI current website-building expertise: research, design, code, accessibility, performance, search and security.",
+  "version": "0.1.7",
+  "description": "A skill pack that turns your AI into an expert website builder: current research, design, code, accessibility, speed, SEO and security, alone or as a team.",
   "author": {
     "name": "website-build-skill contributors"
   },
   "repository": "https://github.com/aunysillyme/website-build-skill",
-  "license": "MIT"
+  "license": "MIT",
+  "homepage": "https://github.com/aunysillyme/website-build-skill",
+  "keywords": [
+    "agent-skills",
+    "ai-skills",
+    "llm-skills",
+    "claude-skills",
+    "skill-pack",
+    "web-design",
+    "web-development",
+    "claude-code",
+    "codex",
+    "chatgpt",
+    "grok",
+    "antigravity",
+    "multi-agent",
+    "accessibility",
+    "web-performance",
+    "seo",
+    "aeo",
+    "design-systems",
+    "brand-design",
+    "research-workflow"
+  ]
 }

package/CHANGELOG.md

@@ -6,6 +6,24 @@ Version policy: [Semantic Versioning 2.0.0](https://semver.org/spec/v2.0.0.html)
 
 ## [Unreleased]
 
+## [0.1.7] - 2026-09-25
+
+### Changed
+
+- Grok Bot has its own setup in the Grok adapter, written from xAI's Grok Bot documentation (read 2026-09-25) and the operator's own use: install the package into `/workspace`, save it as a private skill, and run TEAM as a six-Bot group with Reviewer outside Grok Bot, since every Bot runs on Grok. Grok Bot stays a documented setup with no trial receipt ([#15](https://github.com/aunysillyme/website-build-skill/issues/15)).
+- The shared manual fallback no longer names an instruction field or a seven-Bot group; it points to where each host keeps standing instructions and respects the host's group limit.
+- One description everywhere: `package.json`, the GitHub About box, npm and `.claude-plugin/plugin.json` now carry the same line, which matches the README lead and names the solo or team choice. The plugin manifest also gains the homepage and keywords.
+
+## [0.1.6] - 2026-09-24
+
+### Added
+
+- Dated native-loading receipt for the Grok Build CLI 1.0.40 (SOLO, macOS, trusted folder, 2026-09-24) in `docs/evidence/`, linked from compatibility and the Grok adapter ([#15](https://github.com/aunysillyme/website-build-skill/issues/15)).
+
+### Changed
+
+- The Grok adapter says to trust the project folder: Grok Build offers project skills only in a trusted folder, found during the trial. Grok Bot (the Bots app) is named separately as still awaiting its trial.
+
 ## [0.1.5] - 2026-09-24
 
 ### Added

package/CLAUDE.md

@@ -13,5 +13,5 @@ node --test test/*.test.mjs
 ```
 
 The installer is real; the native worker generator is not. Do not imply seven workers start.
-Native SOLO loading is tested on Claude Code and Codex (one run each, receipts in docs/evidence/).
+Native SOLO loading is tested on Claude Code, Codex and the Grok Build CLI (one run each, receipts in docs/evidence/).
 Other hosts, TEAM, account tools and independent-review access are UNVERIFIED until a real trial.

package/README.md

@@ -124,7 +124,7 @@ With any of these missing, the AI hands you the exact next step (a query plan, f
 ## Choose your host
 
 Each guide below has a documented setup with its own loading check. Native loading is tested
-on Claude Code and Codex with dated receipts (one run each, limitations listed), and [compatibility](docs/COMPATIBILITY.md) tracks
+on Claude Code, Codex and the Grok Build CLI with dated receipts (one run each, limitations listed), and [compatibility](docs/COMPATIBILITY.md) tracks
 current status host by host.
 
 | Host | Set it up | What you get |

package/REPO_SETTINGS.md

@@ -7,9 +7,9 @@ trusting any row; a checklist is only as current as its last read.
 
 ## Description
 
-- [x] Repository description set to this one line, identical to package.json and npm. Read back 2026-09-23; it matches.
+- [x] Repository description set to this one line, identical to package.json, .claude-plugin/plugin.json and npm. Set 2026-09-25 in 0.1.7.
 
-Skills that make your AI an expert website builder: current research, design, accessibility, performance, SEO, security and code, for any LLM or agent.
+A skill pack that turns your AI into an expert website builder: current research, design, code, accessibility, speed, SEO and security, alone or as a team.
 
 ## Topics
 

package/adapters/grok.md

@@ -7,7 +7,7 @@ See [compatibility](../docs/COMPATIBILITY.md) for setup evidence and host trials
 
 - SOLO: paste the starter in [zero-install](zero-install.md), or give a file-capable session the complete canonical skill.
 - TEAM: install or attach all five [bundles](../docs/bundles/team.md), open the seven sessions yourself, then paste the setup request below in each session.
-- Native skill candidate: `.grok/skills/website-build-skill/`; discovery and invocation require a clean-client check. Native loading on this host is awaiting a real-client trial; the check above confirms it on yours. Current status: [compatibility](../docs/COMPATIBILITY.md).
+- Native skill (Grok Build CLI): install with `--target grok`, which writes `.grok/skills/website-build-skill/`, then trust the project folder (accept the trust prompt, or run `grok --trust` there once). Grok Build offers project skills only in a trusted folder. Native loading was tested on Grok Build CLI 1.0.40 (macOS, SOLO, trusted folder, 2026-09-24; one run, limitations in the [receipt](../docs/evidence/host-trial-grok-build-2026-09-24.json)); `grok inspect --json` lists the skill with source `project` when it is available to you. Grok Bot is a separate app with its own setup, below. Current status: [compatibility](../docs/COMPATIBILITY.md).
 - Independence: workers from one model family leave the independent release gate BLOCKED.
 - Reference: [Bot setup](https://docs.x.ai/grok-bot/bots), [collaboration](https://docs.x.ai/grok-bot/chat-and-collaboration), [skills](https://docs.x.ai/build/features/skills-plugins-marketplaces). Use these references when checking the installed controls.
 
@@ -15,6 +15,32 @@ See [compatibility](../docs/COMPATIBILITY.md) for setup evidence and host trials
 Give me the team (option 2). I open each session myself and carry the handoffs between them, with Researcher first. Use the attached team.md and the complete role body for this session. Return its setup acknowledgement with session reference, model family and tool limits. I collect seven acknowledgements through the manual setup below. Give my request to Researcher first; every other worker waits for the saved-library gate. Use a reviewer from a different model family for independent review.
 ```
 
+## Grok Bot
+
+Grok Bot is the Bots app (desktop, iPhone and Android). It keeps skills in its own private skill library, so `--target grok` does not reach it. This setup follows xAI's [Grok Bot documentation](https://docs.x.ai/grok-bot/overview), read 2026-09-25; no trial receipt exists yet, so treat each step as the documented route and confirm it on your account.
+
+**What the app gives you**
+
+- One private skill library shared by all your Bots. Type `/` in the composer to use a saved skill; if one is missing, open **Marketplace → Your plugins → Manage plugins and skills** and look under **Private skills**.
+- One shared cloud computer for all your Bots, with a browser, a command line and a `/workspace` folder every Bot can read. Keep `site-work/` there.
+- Bots with their own conversation and memory. A Bot's standing rules live in its profile **description**.
+- Group chats of two to six Bots, `@` mentions, and direct Bot-to-Bot handoffs. Handoffs posted to a group are text only, so a Bot sends an image directly to the Bot that must inspect it.
+- Up to six attachments per message, 25 MB per document.
+- Every Bot runs on Grok: there is no model picker (reported by the operator, 2026-09-25). A reviewer from a different model family therefore sits outside Grok Bot.
+
+**SOLO**
+
+1. Choose **New** (`Cmd/Ctrl+N`), then **Create new Bot**, and use **Edit Profile** to name it `Website Builder`.
+2. Ask it to install the package into `/workspace` and learn it as a skill: `Run npx website-build-skill@latest --solo --target portable --dir /workspace/website-build-skill --yes, read /workspace/website-build-skill/.website-build-skill/SKILL.md, and save it as a private skill called website-build-skill that reads the files beside it.` The Bot learns the skill and keeps it across conversations (reported by the operator, 2026-09-25).
+3. Type `/` and confirm `website-build-skill` is listed. If it is missing, attach the five [bundles](../docs/bundles/team.md) to your first message and ask the Bot to keep them in `/workspace/website-build-skill/`.
+4. Start the build with `/website-build-skill` and your site request.
+
+**TEAM**
+
+- Create six Bots in the order below (Researcher, Coordinator, Designer, Graphics, Builder, Optimizer). Save each role body from the [team bundle](../docs/bundles/team.md) to `/workspace/site-work/roles/<role>.md` and write in each description: `You are Website <Role>. Before every task, read /workspace/site-work/roles/<role>.md and follow it.`
+- Put those six in one group, Researcher first. A Bot keeps its memory, skills and context when it joins a group (reported by the operator, 2026-09-25). Six is the group limit, and it fits: the seventh role, Reviewer, needs a different model family, so it runs outside Grok Bot and you relay the final packet to it.
+- Follow the steps below for setup acknowledgements, the research gate and the handoff contract. Since every Bot reads `/workspace`, pass file paths in handoffs rather than reattaching files.
+
 ## Manual fallback
 
 TEAM: one command installs the seven workers' files; you open each session yourself and carry the handoffs between them. Researcher goes first. This manual relay is the TEAM workflow.
@@ -24,7 +50,7 @@ TEAM: one command installs the seven workers' files; you open each session yours
 - Get the complete `docs/bundles/team.md`, `method.md`, `prompts.md`, `playbooks.md`, and `checklists.md` from the same release. The team bundle contains the seven complete role bodies and this guide; the prompts bundle contains active prompts.
 - Get `skills/website-build-skill/archive/graphics-design-original.md` separately for Researcher's provenance reading. Keep its inactive header and do not execute its historical save instructions.
 - Choose the private project workspace where `site-work/` will live. Keep its research and brand files out of the public skill repository and deployment output.
-- Open your host's Bots area. Use **New** to create one Bot at a time; set its name and paste the entire named role body into its instruction field, then save. These are semantic field instructions; exact field labels in your account must be checked. If **New**, the instruction field or group controls are absent, use separate chats and relay the complete role packets manually rather than inventing an API.
+- Open your host's Bots or agents area and create one worker at a time. Give each the entire named role body wherever your host keeps standing instructions (in Grok Bot, a role file in `/workspace` that the description points to, as in [Grok Bot](grok.md#grok-bot)), then save. If your host has no such place, use separate chats and relay the complete role packets manually rather than inventing an API.
 - Give each Bot the method, prompt, playbook and checklist bundles as files or pasted text through controls your account actually provides. If a filename inside an instruction is inaccessible, attach or paste that file's contents with its label before work starts. Confirm file access separately for each Bot.
 - Request only a setup acknowledgement: name, received role, route, actual model family if known, tools, and inaccessible files. For all Bots except Researcher add: `Wait for the research gate; do not begin your role yet.` Pass each work gate using its own required evidence.
 
@@ -40,7 +66,7 @@ TEAM: one command installs the seven workers' files; you open each session yours
 
 **Connect the group and verify its routes**
 
-- If your account exposes group creation, create `Website Design` and add the seven saved Bots in the same order, Researcher first. Record the actual route for each. Verify one bounded setup message reaches the intended recipient using the host's documented addressing controls.
+- If your host offers group chats, create `Website Design` and add the saved workers in the same order, Researcher first, up to the host's group limit (six in Grok Bot, where Reviewer runs outside the group). Record the actual route for each. Verify one bounded setup message reaches the intended recipient using the host's documented addressing controls.
 - Use separate Bot chats and relay each handoff and its attachments manually, including when the account offers a group view. Keep distinct workers on separate routes; separate workers need separate routes, and labels inside one chat stay one worker. Ordinary single-chat work uses SOLO.
 - If group messages are text-only, attach mockups and assets directly to the receiving Bot. Image review needs the Bot to open the image itself; a text path alone gives it only the path, so confirm the receiving Bot can inspect the image directly.
 - Give Coordinator this complete contract after replacing each angle-bracket route with the real saved Bot/chat reference. Unresolved placeholders keep setup incomplete.

package/docs/COMPATIBILITY.md

@@ -2,7 +2,7 @@
 
 ## Tested hosts
 
-Two hosts have a dated native-loading receipt. Each covers SOLO skill discovery and loading
+Three hosts have a dated native-loading receipt. Each covers SOLO skill discovery and loading
 on the exact version below, from one run under the operator's existing client configuration
 (each receipt lists its limitations); the full SOLO build route, TEAM and deployment stay
 documented until a trial records them.
@@ -11,6 +11,7 @@ documented until a trial records them.
 |---|---|---|---|---|
 | Claude Code | 2.1.281, macOS 26.6.2 arm64 | SOLO, native loading tested | 2026-09-24 | [receipt](evidence/host-trial-claude-code-2026-09-24.json) |
 | Codex CLI | 0.154.0, macOS 26.6.2 arm64 | SOLO, native loading tested | 2026-09-24 | [receipt](evidence/host-trial-codex-2026-09-24.json) |
+| Grok Build CLI | 1.0.40, macOS 26.6.2 arm64 | SOLO, native loading tested in a trusted folder | 2026-09-24 | [receipt](evidence/host-trial-grok-build-2026-09-24.json) |
 
 Every other host has a documented setup and
 a check you run, in its own adapter guide, to confirm it loaded on yours. A host moves from
@@ -31,7 +32,7 @@ when its receipt demonstrates loading, file access, tool permissions and the sel
 | Codex | [Skill and explicit router](../adapters/codex.md) | Shared destination, role configuration and actual model family | [Skills](https://learn.chatgpt.com/docs/build-skills) |
 | Hermes | [Skill and separate sessions](../adapters/hermes.md) | Trust, alias semantics, routes and inherited permissions | [Skills](https://hermes-agent.nousresearch.com/docs/user-guide/features/skills) |
 | Antigravity | [Explicit core pointer](../adapters/antigravity.md) | Schema, paths, quoted off, routing and denied writes | [Subagents](https://antigravity.google/docs/subagents) |
-| Grok Bot | [Bundles and manual roles](../adapters/grok.md) | Account controls, routes and image relay | [Bots](https://docs.x.ai/grok-bot/bots) |
+| Grok Bot | [Private skill and six-Bot group](../adapters/grok.md#grok-bot), from the xAI docs read 2026-09-25 | `/` lists the saved skill, role files in `/workspace`, group routes; Reviewer outside Grok Bot | [Bots](https://docs.x.ai/grok-bot/bots) |
 | Claude Desktop | [Bundle attachments](../adapters/claude-desktop.md) | Account upload controls and loaded resources | [Skills](https://support.claude.com/en/articles/12512180-use-skills-in-claude) |
 | ChatGPT Project/custom GPT | [Instructions and bundles](../adapters/chatgpt-project.md) | File access, tool availability and state reattachment | [Projects](https://help.openai.com/en/articles/10169521-projects-in-chatgpt) |
 | Generic file-reading agent | [Explicit core pointer](../adapters/agents-md.md) | Router read-back and preserved instructions | [Adapter](../adapters/agents-md.md) |

package/docs/bundles/team.md

@@ -1688,7 +1688,7 @@ TEAM: one command installs the seven workers' files; you open each session yours
 - Get the complete `docs/bundles/team.md`, `method.md`, `prompts.md`, `playbooks.md`, and `checklists.md` from the same release. The team bundle contains the seven complete role bodies and this guide; the prompts bundle contains active prompts.
 - Get `skills/website-build-skill/archive/graphics-design-original.md` separately for Researcher's provenance reading. Keep its inactive header and do not execute its historical save instructions.
 - Choose the private project workspace where `site-work/` will live. Keep its research and brand files out of the public skill repository and deployment output.
-- Open your host's Bots area. Use **New** to create one Bot at a time; set its name and paste the entire named role body into its instruction field, then save. These are semantic field instructions; exact field labels in your account must be checked. If **New**, the instruction field or group controls are absent, use separate chats and relay the complete role packets manually rather than inventing an API.
+- Open your host's Bots or agents area and create one worker at a time. Give each the entire named role body wherever your host keeps standing instructions (in Grok Bot, a role file in `/workspace` that the description points to, as in [Grok Bot](../../adapters/grok.md#grok-bot)), then save. If your host has no such place, use separate chats and relay the complete role packets manually rather than inventing an API.
 - Give each Bot the method, prompt, playbook and checklist bundles as files or pasted text through controls your account actually provides. If a filename inside an instruction is inaccessible, attach or paste that file's contents with its label before work starts. Confirm file access separately for each Bot.
 - Request only a setup acknowledgement: name, received role, route, actual model family if known, tools, and inaccessible files. For all Bots except Researcher add: `Wait for the research gate; do not begin your role yet.` Pass each work gate using its own required evidence.
 
@@ -1704,7 +1704,7 @@ TEAM: one command installs the seven workers' files; you open each session yours
 
 **Connect the group and verify its routes**
 
-- If your account exposes group creation, create `Website Design` and add the seven saved Bots in the same order, Researcher first. Record the actual route for each. Verify one bounded setup message reaches the intended recipient using the host's documented addressing controls.
+- If your host offers group chats, create `Website Design` and add the saved workers in the same order, Researcher first, up to the host's group limit (six in Grok Bot, where Reviewer runs outside the group). Record the actual route for each. Verify one bounded setup message reaches the intended recipient using the host's documented addressing controls.
 - Use separate Bot chats and relay each handoff and its attachments manually, including when the account offers a group view. Keep distinct workers on separate routes; separate workers need separate routes, and labels inside one chat stay one worker. Ordinary single-chat work uses SOLO.
 - If group messages are text-only, attach mockups and assets directly to the receiving Bot. Image review needs the Bot to open the image itself; a text path alone gives it only the path, so confirm the receiving Bot can inspect the image directly.
 - Give Coordinator this complete contract after replacing each angle-bracket route with the real saved Bot/chat reference. Unresolved placeholders keep setup incomplete.

package/docs/evidence/content-review.json

@@ -10,24 +10,28 @@
       "disposition": "instructions-and-qualified-status-only"
     },
     "CHANGELOG.md": {
-      "sha256": "4e1c9fd46f9f759efa2f1bb8d782d7110985a485194b4214716cae9d94a5a5c5",
+      "sha256": "a037c93c45108844f00bdaab50be0634272a6919aab5394a6955df758c413c99",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "0.1.2: the installer prompt block became a two-row choice table and one save-location sentence; reviewed by Claude against install-choice.txt and SKILL.md, same facts. Reviewed the added 0.1.1 framing note against the presentation copy changes; publication is a separate release action. Implementation-agent editorial review; independent review remains pending. Reviewed the copied-install checker ladder fix against the canonical instructions and regression test. Live host retrial remains pending release. Reviewed for the ROUND 1 audit: added Fixed/Added/Changed lines for the restored positive-and-accurate adapter, SKILL.md, designer.md, grok.md and validate.mjs fixes. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.3: reviewed the #13 description check and #14 Hermes path documentation entries against the implementation and regression tests; publication remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. Reviewed the #15 Fixed line for the symlinked-parent receipt path against src/install.mjs and installer tests 7e-7g, and the #15 Added line against the two receipts. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. 0.1.5 release heading moved the Unreleased lines under [0.1.5] - 2026-09-24 unchanged."
+      "review": "0.1.2: the installer prompt block became a two-row choice table and one save-location sentence; reviewed by Claude against install-choice.txt and SKILL.md, same facts. Reviewed the added 0.1.1 framing note against the presentation copy changes; publication is a separate release action. Implementation-agent editorial review; independent review remains pending. Reviewed the copied-install checker ladder fix against the canonical instructions and regression test. Live host retrial remains pending release. Reviewed for the ROUND 1 audit: added Fixed/Added/Changed lines for the restored positive-and-accurate adapter, SKILL.md, designer.md, grok.md and validate.mjs fixes. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.3: reviewed the #13 description check and #14 Hermes path documentation entries against the implementation and regression tests; publication remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. Reviewed the #15 Fixed line for the symlinked-parent receipt path against src/install.mjs and installer tests 7e-7g, and the #15 Added line against the two receipts. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. 0.1.5 release heading moved the Unreleased lines under [0.1.5] - 2026-09-24 unchanged. 0.1.6 (#15): Grok Build CLI 1.0.40 SOLO native-loading receipt added; wording promoted only for that client, in a trusted folder, one run; Grok Bot (Bots app) stays awaiting its trial. Claude (orchestrator, ran the trial) editorial review, independent review remains pending. 0.1.7: Grok Bot setup and one-description entries reviewed against the diff. Claude editorial review."
     },
     "CLAUDE.md": {
-      "sha256": "983dd28a6ba815adef9201351d7845f6cf5567e0be92be975ee74d98b4ee346a",
+      "sha256": "4bc19853ddcdea0b2b751f82fba1d7c2451d2ae42f173dba1da2f6035df6e464",
       "disposition": "status-claims-bound-to-receipts",
       "claims": [
         {
-          "text": "Native SOLO loading is tested on Claude Code and Codex",
+          "text": "Native SOLO loading is tested on Claude Code, Codex and the Grok Build CLI",
           "evidence": "docs/evidence/host-trial-claude-code-2026-09-24.json"
         },
+        {
+          "text": "Codex and the Grok Build CLI",
+          "evidence": "docs/evidence/host-trial-grok-build-2026-09-24.json"
+        },
         {
           "text": "(one run each, receipts in docs/evidence/)",
           "evidence": "docs/evidence/host-trial-codex-2026-09-24.json"
         }
       ],
-      "review": "0.1.5 (#15): status line narrowed to the two SOLO loading receipts; other hosts, TEAM, account tools and independent review stay UNVERIFIED. Claude editorial review."
+      "review": "0.1.5 (#15): status line narrowed to the two SOLO loading receipts; other hosts, TEAM, account tools and independent review stay UNVERIFIED. Claude editorial review. 0.1.6 (#15): Grok Build CLI 1.0.40 SOLO native-loading receipt added; wording promoted only for that client, in a trusted folder, one run; Grok Bot (Bots app) stays awaiting its trial. Claude (orchestrator, ran the trial) editorial review, independent review remains pending."
     },
     "CODE_OF_CONDUCT.md": {
       "sha256": "9b32964f09663dbcf16e5ce39b4522928ba4c74d13c49f3fe6a9fb131b8ddd31",
@@ -43,17 +47,21 @@
       "disposition": "instructions-and-qualified-status-only"
     },
     "README.md": {
-      "sha256": "362773785e80e089e8311429cc045243747e0943bdad9601e54f882314ca6777",
+      "sha256": "15e40dd0a81edb667484500a1f2c86e747fae08a70d39410805cc52091b0ae7e",
       "disposition": "status-claims-bound-to-receipts",
-      "review": "0.1.2: the installer prompt block became a two-row choice table and one save-location sentence; reviewed by Claude against install-choice.txt and SKILL.md, same facts. Reviewed the requested skill-pack framing and each learning-table sentence against its linked canonical instructions; preserved the twelve stages, starter, setup card and sibling links. Demo URL awaits the separately recorded artifact. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. ROUND 1 (2026-09-24): added the receipts' one-run and operator-configuration limitations to the promoted wording, per the code-reviewer finding.",
+      "review": "0.1.2: the installer prompt block became a two-row choice table and one save-location sentence; reviewed by Claude against install-choice.txt and SKILL.md, same facts. Reviewed the requested skill-pack framing and each learning-table sentence against its linked canonical instructions; preserved the twelve stages, starter, setup card and sibling links. Demo URL awaits the separately recorded artifact. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. ROUND 1 (2026-09-24): added the receipts' one-run and operator-configuration limitations to the promoted wording, per the code-reviewer finding. 0.1.6 (#15): Grok Build CLI 1.0.40 SOLO native-loading receipt added; wording promoted only for that client, in a trusted folder, one run; Grok Bot (Bots app) stays awaiting its trial. Claude (orchestrator, ran the trial) editorial review, independent review remains pending.",
       "claims": [
         {
           "text": "Native loading is tested",
           "evidence": "docs/evidence/host-trial-claude-code-2026-09-24.json"
         },
         {
-          "text": "on Claude Code and Codex with dated receipts",
+          "text": "on Claude Code, Codex and the Grok Build CLI with dated receipts",
           "evidence": "docs/evidence/host-trial-codex-2026-09-24.json"
+        },
+        {
+          "text": "and the Grok Build CLI with dated receipts",
+          "evidence": "docs/evidence/host-trial-grok-build-2026-09-24.json"
         }
       ]
     },
@@ -63,9 +71,9 @@
       "review": "0.1.3: reviewed the same-commit description update and explicit GitHub command against the task specification; no live repository setting was changed in this offline implementation pass. Implementation-agent editorial review; independent review remains pending. The command uses the exact repository URL to preserve the existing privacy allowance for public repository references."
     },
     "REPO_SETTINGS.md": {
-      "sha256": "f0a405e61c2361c9b746a867279dc2ca28a983a14899d14b249286c486e989de",
+      "sha256": "4460fa8f5379df2991fc11eb55ba7ae6319ca66acc5a2f8702b3b64b6847d967",
       "disposition": "instructions-and-qualified-status-only",
-      "review": "Topic list changed to match the skill-pack framing and package.json keywords (20 topics). Reviewed by Claude against the check TOPICS rule. 0.1.3: matched the Description text to package.json and added the requested 2026-09-23 read-back row from the maintainer task bundle; GitHub and npm were not independently queried in this offline implementation pass. Implementation-agent editorial review; independent review remains pending."
+      "review": "Topic list changed to match the skill-pack framing and package.json keywords (20 topics). Reviewed by Claude against the check TOPICS rule. 0.1.3: matched the Description text to package.json and added the requested 2026-09-23 read-back row from the maintainer task bundle; GitHub and npm were not independently queried in this offline implementation pass. Implementation-agent editorial review; independent review remains pending. 0.1.7: description line replaced with the unified 155-character string also set in package.json and plugin.json. Claude editorial review."
     },
     "SECURITY.md": {
       "sha256": "9e0a9064cd020c23ae82f4c734ceab24bb9e4297073227a49ecc41414e33f8b7",
@@ -119,9 +127,15 @@
       "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
     },
     "adapters/grok.md": {
-      "sha256": "66e869b434ec1857b3abcda064f2e4162e41bdd5f9765496095caafeadd4bdaa",
-      "disposition": "instructions-and-qualified-status-only",
-      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
+      "sha256": "722ec03c83e8edc7cff0d2b9a6f3fc46f2e5c971a483f8a93fc799e7dae9414c",
+      "disposition": "status-claims-bound-to-receipts",
+      "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. 0.1.6 (#15): Grok Build CLI 1.0.40 SOLO native-loading receipt added; wording promoted only for that client, in a trusted folder, one run; Grok Bot (Bots app) stays awaiting its trial. Claude (orchestrator, ran the trial) editorial review, independent review remains pending. 0.1.7: reviewed the new Grok Bot section against docs.x.ai/grok-bot pages read 2026-09-25 (bots, chat-and-collaboration, files-and-results, computer-and-apps, skills-routines-and-automations, faq) and two operator reports (no model picker; a Bot learns an installed skill and keeps memory, skills and context in a group). Portable install command and SKILL.md path confirmed by a local dry install. Grok Bot stays a documented setup with no receipt. The manual-fallback edits are host-neutral because the fallback is copied into team.md. Claude editorial review.",
+      "claims": [
+        {
+          "text": "Native loading was tested on Grok Build CLI 1.0.40 (macOS, SOLO, trusted folder, 2026-09-24;",
+          "evidence": "docs/evidence/host-trial-grok-build-2026-09-24.json"
+        }
+      ]
     },
     "adapters/hermes.md": {
       "sha256": "bfb7624ce627d7a59328a16a663ed71aa96dbe24ede160bc349f13dd08cd1578",
@@ -134,7 +148,7 @@
       "review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending."
     },
     "docs/COMPATIBILITY.md": {
-      "sha256": "3b7fa6f4e1c0576beb6ec6cc6af7365318affc41fe162066936f9332d998eaf8",
+      "sha256": "4f51a66171eb84590e7e919e2ffd23010e475fec9b48ce6b52ad73b918df15a9",
       "disposition": "status-claims-bound-to-receipts",
       "claims": [
         {
@@ -144,9 +158,13 @@
         {
           "text": "| Codex CLI | 0.154.0, macOS 26.6.2 arm64 | SOLO, native loading tested | 2026-09-24 |",
           "evidence": "docs/evidence/host-trial-codex-2026-09-24.json"
+        },
+        {
+          "text": "| Grok Build CLI | 1.0.40, macOS 26.6.2 arm64 | SOLO, native loading tested in a trusted folder | 2026-09-24 |",
+          "evidence": "docs/evidence/host-trial-grok-build-2026-09-24.json"
         }
       ],
-      "review": "Reviewed documented setup routes and required trial evidence; retained the existing revision-bound hosted-check claim and receipt. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. ROUND 1 (2026-09-24): added the receipts' one-run and operator-configuration limitations to the promoted wording, per the code-reviewer finding."
+      "review": "Reviewed documented setup routes and required trial evidence; retained the existing revision-bound hosted-check claim and receipt. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. ROUND 1 (2026-09-24): added the receipts' one-run and operator-configuration limitations to the promoted wording, per the code-reviewer finding. 0.1.6 (#15): Grok Build CLI 1.0.40 SOLO native-loading receipt added; wording promoted only for that client, in a trusted folder, one run; Grok Bot (Bots app) stays awaiting its trial. Claude (orchestrator, ran the trial) editorial review, independent review remains pending. 0.1.7: Grok Bot row stays under documented setups (no receipt), now pointing at the new Grok Bot section and naming what to verify. Claude editorial review."
     },
     "docs/EVALUATION.md": {
       "sha256": "cb34b13e24b906496d0f05ef20187695bd51defe75b25abb7df8d5ad2935c32d",

package/docs/evidence/host-trial-grok-build-2026-09-24.json

@@ -0,0 +1,74 @@
+{
+  "status": "PASS (native loading only, trusted folder)",
+  "packageCommit": "28d33366f49aa0e25ef0af222c97fbf72be300c9",
+  "packageVersion": "0.1.5 (npm, installed with npx website-build-skill@0.1.5)",
+  "mode": "solo",
+  "scope": "Native skill discovery and loading by the Grok Build CLI in a clean temporary git project with a synthetic brief. No website was built; research, mockup, build, review and handoff boundaries were not exercised. Grok Bot (the Bots app) was not tested.",
+  "negativeTrials": [
+    {
+      "case": "Untrusted project folder",
+      "result": "skill not offered",
+      "observed": "grok inspect --json in the fresh project reported projectTrusted false and listed no website-build-skill; Grok Build skips project skills in untrusted folders at startup (its own docs, user-guide/08-skills.md)."
+    }
+  ],
+  "review": {
+    "candidateSha256": null,
+    "modelFamily": null,
+    "findings": [],
+    "dispositions": []
+  },
+  "trialId": "2026-09-24-grok-build-solo-load",
+  "client": {
+    "host": "Grok Build CLI",
+    "version": "grok 1.0.40 (eb1a2256660d) stable",
+    "os": "macOS 26.6.2 arm64",
+    "modelFamily": "xAI Grok (grok-4.7, recorded as modelId in the trial session transcript under ~/.grok/sessions)"
+  },
+  "invocation": "native project skill: installer wrote .grok/skills/website-build-skill/; the project folder was trusted; grok inspect --json then listed website-build-skill with source type project; headless grok -p asked to list native skills and load website-build-skill through its native skill mechanism",
+  "startedAt": "2026-09-24T07:31:08Z",
+  "finishedAt": "2026-09-24T07:34:01Z",
+  "commands": [
+    "npx --yes website-build-skill@0.1.5 --solo --target grok --dir <trial-project> --output-dir <trial-output> --receipt <trial-output>/install-receipt.json --yes",
+    "grok inspect --json (untrusted: skill absent)",
+    "trust <trial-project> (entry added to ~/.grok/trusted_folders.toml, removed after the trial)",
+    "grok inspect --json (trusted: skill listed, source project)",
+    "grok --output-format json -p '<synthetic loading brief>'"
+  ],
+  "artifacts": [
+    "installed SKILL.md sha256 71cb5b229d68ae1b91a11d4168c6093a88d0c0f7da2dbcab0c933cb6a333c81b",
+    "57 files installed under .grok/skills/website-build-skill/"
+  ],
+  "boundaries": [
+    {
+      "boundary": "Discovery",
+      "result": "PASS",
+      "observed": "Untrusted folder: not offered. Trusted folder: grok inspect lists website-build-skill with source type project and path .grok/skills/website-build-skill/SKILL.md."
+    },
+    {
+      "boundary": "Load",
+      "result": "PASS",
+      "observed": "Reported website-build-skill already in the session's native skills catalog before any file was opened; entrypoint .grok/skills/website-build-skill/SKILL.md; all 57 manifest assets READ (templates/install-choice.txt, tokens.json and handoff.yaml opened through line 3 only); docs/COMPATIBILITY.md not opened (not a manifest asset)."
+    },
+    {
+      "boundary": "First job",
+      "result": "PASS",
+      "observed": "Named Researcher first: ASK DATE from the canonical ladder, site-work/research/library/ on disk, AD01-AD08 then R01-R06 before any other role."
+    }
+  ],
+  "limitations": [
+    "Run through the operator's cli-run wrapper, which adds a task-bundle frame to the prompt.",
+    "Project skills load only in a trusted folder; the trial trusted it by a config entry, the same state the interactive trust prompt or grok --trust saves.",
+    "Grok Build has no separate load-skill tool; loading means reading the SKILL.md path the catalog supplies.",
+    "SOLO loading only: TEAM, research, build and release boundaries are untested. Grok Bot (Bots app) is untested.",
+    "One run under the operator's existing client configuration."
+  ],
+  "transcriptExcerpt": "1. Yes. `website-build-skill` was already in this session's native skills catalog before any file was opened. It was offered with the description \"Current website-building expertise for an AI: research, design, code, accessibility, performance, search and security...\" and the absolute path `.grok/skills/website-build-skill/SKILL.md`. This host has no separate load-skill tool. Loading means reading the `SKILL.md` path the catalog supplies. The filesystem was not searched to discover it.\n\n2. Entrypoint loaded: `.grok/skills/website-build-skill/SKILL.md`. `manifest.json` names 57 assets (`packageVersion` 0.1.5). Each one below was opened and returned content, so each is READ. `manifest.json` itself was opened in two reads because the first stopped at line 1000. `templates/install-choice.txt`, `templates/tokens.json`, and `templates/handoff.yaml` were opened only through line 3, so anything after line 3 in those three files is UNVERIFIED. Checksums in the manifest were not recomputed.\n\n- `SKILL.md` READ\n- `manifest.json` READ\n- `prompts/00-start.md` READ\n- `prompts/01-website-deep-research.md` READ\n- `archive/graphics-design-original.md` READ\n- `prompts/03-extract-brand-kit.md` READ\n- `prompts/04-three-mockups.md` READ\n- `prompts/05-stack-and-build.md` READ\n- `prompts/06-site-audit.md` READ\n- `prompts/07-accessibility-contrast.md` READ\n- `prompts/08-seo-aeo.md` READ\n- `prompts/09-security-headers.md` READ\n- `prompts/10-adversarial-pre-ship.md` READ\n- `prompts/11-ship-and-verify.md` READ\n- `prompts/12-web-design-team.md` READ\n- `prompts/13-coding-research.md` READ\n- `roles/researcher.md` READ\n- `roles/coordinator.md` READ\n- `roles/designer.md` READ\n- `roles/graphics.md` READ\n- `roles/builder.md` READ\n- `roles/optimizer.md` READ\n- `roles/reviewer.md` READ\n- `playbooks/choose-stack.md` READ\n- `playbooks/data-and-templates.md` READ\n- `playbooks/image-pipeline.md` READ\n- `playbooks/self-hosted-fonts.md` READ\n- `playbooks/embed-facades.md` READ\n- `playbooks/security-headers.md` READ\n- `playbooks/structured-data-and-llms.md` READ\n- `playbooks/performance-budgets.md` READ\n- `playbooks/accessibility.md` READ\n- `playbooks/research-and-memory.md` READ\n- `playbooks/deploy-and-operate.md` READ\n- `checklists/research.md` READ\n- `checklists/brand-and-mockups.md` READ\n- `checklists/build.md` READ\n- `checklists/code-quality.md` READ\n- `checklists/accessibility.md` READ\n- `checklists/performance-seo.md` READ\n- `checklists/security.md` READ\n- `checklists/ship.md` READ\n- `references/stacks/static-html.md` READ\n- `references/stacks/scripted-static.md` READ\n- `references/stacks/framework.md` READ\n- `templates/install-choice.txt` READ\n- `templates/brief.md` READ\n- `templates/brand.md` READ\n- `templates/tokens.json` READ\n- `templates/evidence.md` READ\n- `templates/handoff.yaml` READ\n- `templates/audit-brief.md` READ\n- `templates/site-operations.md` READ\n- `templates/status.md` READ\n- `examples/fictional-studio-brief.md` READ\n- `examples/fictional-studio-handoff.md` READ\n- `examples/audit-cases.md` READ\n\nThe entrypoint also names the repository file `docs/COMPATIBILITY.md`. That path is not a manifest asset. It was not opened. Whether it exists in this project is UNVERIFIED. No other entrypoint path failed to open. No website was built, no file was written, and the network was not used.\n\n3. The first job, before any downstream work, is Researcher. The manifest sets `entryRole` to `researcher`. Before intake or research, Researcher establishes ASK DATE from the canonical ladder in `playbooks/research-and-memory.md`, without asking the user and without using model knowledge, and records the rung and raw evidence in `site-work/research/library/scope.md`. Researcher then takes the request through `prompts/00-start.md` and `prompts/01-website-deep-research.md` and writes `site-work/research/library/`. No other role starts until that library exists on disk and its gate passes (AD01 through AD08, then R01 through R06). The install question about solo versus team is for the human at install and is not this first job.\n",
+  "reproduction": "docs/evaluation/host-trial.md steps 1-4 with the loadingBrief recorded in this receipt, after trusting the trial folder",
+  "command": "grok --output-format json -p '<synthetic loading brief>' (after npx --yes website-build-skill@0.1.5 --solo --target grok and trusting the folder)",
+  "environment": "Grok Build CLI 1.0.40 (grok-4.7), macOS 26.6.2 arm64, Node v22.22.3",
+  "date": "2026-09-24",
+  "exitCode": 0,
+  "artifactSha256": "71cb5b229d68ae1b91a11d4168c6093a88d0c0f7da2dbcab0c933cb6a333c81b",
+  "observed": "website-build-skill offered natively in the skills catalog once the folder was trusted; entrypoint .grok/skills/website-build-skill/SKILL.md; all 57 manifest assets read; Researcher named as the first job",
+  "loadingBrief": "## Task bundle\n\n**Context.** This is a host trial for the public npm package website-build-skill (issue #15 in this repository): does Grok Build natively discover and load the skill the installer writes to `.grok/skills/website-build-skill/`? Your current working directory is a clean temporary project where `npx website-build-skill@0.1.5 --solo --target grok` installed the skill. Matching receipts already exist for Claude Code and Codex. This is a synthetic loading trial only: no website is built.\n\n**Purpose.** Record whether the installed skill is offered and loaded natively by this Grok Build session, so the adapter claim can move past UNVERIFIED or stay there with a reason.\n\n**Scope of build.** None. Read-only trial. Deliverable is your text answer only.\n\n**Task class.** read_only\n\n**Granted scope.**\n- The current working directory and its `.grok/skills/website-build-skill/` folder.\n- Anything outside this list is out of scope.\n\n**Capabilities.** Your native skill mechanism; reading files inside the granted scope.\n\n**Vault reading.** none\n\n**The stack.** Not needed for this trial; answer from this session only.\n\n**Denied actions.** Do not write, create, move or delete any file. Do not build a website. Do not search the filesystem outside the current directory. Do not use the network.\n- Anything absent from Capabilities is denied.\n\n**Conventions you do not have.** Plain prose, no em dashes. Report only what you actually observed; say UNVERIFIED rather than guess.\n\n**Match the firmness.** Not applicable: this task interprets nothing the operator said. unrated.\n\n**Context packet.** none\n\n**Frozen invariants.** none\n\n**Resource inventory.** You hold your native skills catalog and file reads in this directory. You lack network access for this task and any tool outside this session.\n\n**Report contract.** Return exactly three numbered answers:\n1. Whether `website-build-skill` appears in the skills you were offered natively in this session, without searching the filesystem for it. Say how it was offered.\n2. Load it through your native skill mechanism. Give the entrypoint path you loaded, then list every asset named in its `manifest.json`, relative to the skill directory, each marked READ or UNREADABLE after actually opening it. Name any other file the entrypoint references that you could not read.\n3. One paragraph: what the skill says the first job is before any downstream work.\nState plainly anything you did not do or could not verify.\n\n**Exit parameters.** Stop after the three answers. Read at most the files the manifest names plus the entrypoint. If you hit a limit, report what you have and name what you did not cover.\n"
+}

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "website-build-skill",
-  "version": "0.1.5",
-  "description": "Skills that make your AI an expert website builder: current research, design, accessibility, performance, SEO, security and code, for any LLM or agent.",
+  "version": "0.1.7",
+  "description": "A skill pack that turns your AI into an expert website builder: current research, design, code, accessibility, speed, SEO and security, alone or as a team.",
   "type": "module",
   "license": "MIT",
   "bin": {

package/skills/website-build-skill/manifest.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "packageVersion": "0.1.5",
+  "packageVersion": "0.1.7",
   "skillName": "website-build-skill",
   "pathBase": "All asset paths resolve from this manifest directory; runtime paths resolve in the authorized user project.",
   "assets": [