website-build-skill 0.1.0 → 0.1.2

package/adapters/claude-desktop.md

@@ -1,11 +1,10 @@
 # Claude Desktop
 
-Status: UNVERIFIED. Account controls, skill upload availability and exact menu labels need a live check.
+Check the upload controls and menu labels in your account.
 Available manual route: attach the five bundles and paste the [shared instructions](chatgpt-project.md#instruction-block).
-Planned, unavailable: download a release `website-build-skill.zip`; no release asset exists yet.
-A future skill ZIP contains one complete `website-build-skill/` directory, including its manifest and relative resources.
+For skill ZIP upload, prepare an archive with one complete `website-build-skill/` directory, including its manifest and relative resources.
 Where an account exposes skill upload, upload that complete ZIP and confirm the actual loaded files.
-A terminal-host copy does not prove ordinary desktop chat loaded anything.
+Verify loading in the desktop chat where you will use the method.
 Reference target: [Use skills](https://support.claude.com/en/articles/12512180-use-skills-in-claude).
 
 
@@ -21,13 +20,14 @@ Supply private brief/brand files separately in the user's own project.
 For provenance only, supply the [inactive archive](../skills/website-build-skill/archive/graphics-design-original.md) separately if needed; never execute it.
 
 
-## Common limits and smoke check
+## Check that it loaded
+
+Native loading on this host is awaiting a real-client trial; the check below confirms it on yours. Current status: [compatibility](../docs/COMPATIBILITY.md).
 
-Status: UNVERIFIED. Instructions and candidate paths do not establish native support.
 Give the host a synthetic brief and ask it to identify the entrypoint and complete asset list.
 Record client version, date, exact path, tool availability and the observed invocation.
 Start Researcher, verify saved library read-back, then confirm Coordinator waits for its gate.
 For TEAM, record seven separate routes and families; an inherited family leaves independent review BLOCKED.
 Never grant a Reviewer write access just to persist findings. Return text for Coordinator to capture.
-No search blocks current research; no files requires saved-and-reattached bodies; no images blocks visual mockups.
+When a tool is absent, keep current research BLOCKED until opened sources return; save and reattach named file bodies before the save gate; return inspected images before the visual gate.
 Read the [method](../docs/METHOD.md), [compatibility](../docs/COMPATIBILITY.md) and [installer contract](../docs/INSTALLER.md).

package/adapters/codex.md

@@ -1,21 +1,22 @@
 # Codex
 
 - Manual SOLO: copy the full canonical folder to a new `.agents/skills/website-build-skill/` in the chosen project.
-- Candidate invocation, UNVERIFIED: ask the host to load `website-build-skill`; confirm the exact file it opens.
-- Installs the files, activation still UNVERIFIED: `npx github:aunysillyme/website-build-skill --team --target codex --dir . --scope project --yes`.
+- Load the skill: ask the host to load `website-build-skill`; confirm the exact file it opens.
+- Install the files: `npx website-build-skill --team --target codex --dir . --scope project --yes`.
 - Planned native definitions: `.codex/agents/website-<role>.toml` with name, description and full canonical developer_instructions. Round-trip quotes and backslashes.
 - Fallback: separate sessions using [the full team bundle](../docs/bundles/team.md). Do not overwrite `.codex/config.toml` or infer independence from two model names.
 - Shared core: Hermes may use the same candidate path; preserve identical content and retain the core until every owner releases it.
 - Sources to verify: [skills](https://learn.chatgpt.com/docs/build-skills), [custom agents](https://learn.chatgpt.com/docs/agent-configuration/subagents).
 
 
-## Common limits and smoke check
+## Check that it loaded
+
+Native loading on this host is awaiting a real-client trial; the check below confirms it on yours. Current status: [compatibility](../docs/COMPATIBILITY.md).
 
-Status: UNVERIFIED. Instructions and candidate paths do not establish native support.
 Give the host a synthetic brief and ask it to identify the entrypoint and complete asset list.
 Record client version, date, exact path, tool availability and the observed invocation.
 Start Researcher, verify saved library read-back, then confirm Coordinator waits for its gate.
 For TEAM, record seven separate routes and families; an inherited family leaves independent review BLOCKED.
 Never grant a Reviewer write access just to persist findings. Return text for Coordinator to capture.
-No search blocks current research; no files requires saved-and-reattached bodies; no images blocks visual mockups.
+When a tool is absent, keep current research BLOCKED until opened sources return; save and reattach named file bodies before the save gate; return inspected images before the visual gate.
 Read the [method](../docs/METHOD.md), [compatibility](../docs/COMPATIBILITY.md) and [installer contract](../docs/INSTALLER.md).

package/adapters/custom-gpt.md

@@ -1,8 +1,8 @@
 # Custom GPT
 
-Status: UNVERIFIED for this package. In an eligible account, put the block below in Instructions and the bundles in Knowledge.
+In an eligible account, put the block below in Instructions and the bundles in Knowledge.
 Enable only available, authorized research/file tools. Use Preview to exercise a synthetic brief through research and mockups.
-Do not promise memory across chats. Save and reattach a state packet.
+Save and reattach a state packet in each new chat.
 
 ## Instruction block
 
@@ -21,7 +21,7 @@ Choose the smallest stack that meets the approved requirements.
 Load playbooks.md only for the topic being implemented or checked.
 Keep one primary action and truthful content consistent across every route.
 Never describe a proposed file, test, memory write, or deployment as completed.
-When you cannot search, write, test, or remember, state that limit and produce a handoff.
+For each tool the next stage needs, use it or return the exact handoff for a capable runner.
 Follow the human's recorded install choice; this upload selects SOLO.
 A later switch to TEAM uses the chosen host's setup and verified separate workers.
 Read all seven complete role bodies in team.md on either path. Before each job, complete
@@ -30,7 +30,7 @@ Name the previous framing you are clearing when changing solo jobs.
 An independent pre-release reviewer must use a different model family from the builder.
 Keep project data in this project; do not upload it to public examples or repositories.
 Do not publish beyond the user's recorded authorization.
-Finish each stage with artifacts, completed checks, remaining limits, and the next owner.
+Finish each stage with artifacts, completed checks, next steps, and the next owner.
 ```
 
 ## Upload these files from one revision
@@ -45,13 +45,14 @@ Supply private brief/brand files separately in the user's own project.
 For provenance only, supply the [inactive archive](../skills/website-build-skill/archive/graphics-design-original.md) separately if needed; never execute it.
 
 
-## Common limits and smoke check
+## Check that it loaded
+
+Native loading on this host is awaiting a real-client trial; the check below confirms it on yours. Current status: [compatibility](../docs/COMPATIBILITY.md).
 
-Status: UNVERIFIED. Instructions and candidate paths do not establish native support.
 Give the host a synthetic brief and ask it to identify the entrypoint and complete asset list.
 Record client version, date, exact path, tool availability and the observed invocation.
 Start Researcher, verify saved library read-back, then confirm Coordinator waits for its gate.
 For TEAM, record seven separate routes and families; an inherited family leaves independent review BLOCKED.
 Never grant a Reviewer write access just to persist findings. Return text for Coordinator to capture.
-No search blocks current research; no files requires saved-and-reattached bodies; no images blocks visual mockups.
+When a tool is absent, keep current research BLOCKED until opened sources return; save and reattach named file bodies before the save gate; return inspected images before the visual gate.
 Read the [method](../docs/METHOD.md), [compatibility](../docs/COMPATIBILITY.md) and [installer contract](../docs/INSTALLER.md).

package/adapters/grok.md

@@ -1,15 +1,16 @@
 # Grok
 
-Status: UNVERIFIED. No Bot importer or automatic team creator is supplied.
+Set up Bots through the account controls using the complete roles and manual relay below.
+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: attach all five [bundles](../docs/bundles/team.md), then paste the setup request below.
-- Native skill candidate: `.grok/skills/website-build-skill/`; discovery and invocation require a clean-client check.
+- 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).
 - 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). These are verification targets, not package test evidence.
+- 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.
 
 ```text
-Give me the team (option 2). Use the attached team.md and create Website Researcher first, then Website Coordinator, Website Designer, Website Graphics, Website Builder, Website Optimizer, and Website Reviewer with their complete role bodies. Use only controls actually available in this account. Return seven setup acknowledgements with routes, model families and tool limits. If Bot creation is unavailable, show the manual fallback. Give my request to Researcher first; every other worker waits for the saved-library gate. An inherited model does not establish independent review.
+Give me the team (option 2). Use the attached team.md and create Website Researcher first, then Website Coordinator, Website Designer, Website Graphics, Website Builder, Website Optimizer, and Website Reviewer with their complete role bodies. Use only controls actually available in this account. Return seven setup acknowledgements with routes, model families and tool limits. If Bot creation is unavailable, show the manual fallback. 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.
 ```
 
 ## Manual fallback
@@ -19,9 +20,9 @@ Give me the team (option 2). Use the attached team.md and create Website Researc
 - 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. A missing **New**, instruction field, or group control is an UNVERIFIED setup limit, not permission to invent 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. Shared group membership alone does not prove file access.
-- 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.` Setup acknowledgements do not pass work gates.
+- 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.
+- 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.
 
 **Create these seven Bots in this exact order**
 
@@ -33,11 +34,11 @@ Give me the team (option 2). Use the attached team.md and create Website Researc
 6. **Website Optimizer.** Click **New**, name it `Website Optimizer`, paste `roles/optimizer.md` in full, and save. Check source retrieval, validators and rendered-page access. It works with and after Builder on its bounded discovery assignment.
 7. **Website Reviewer.** Click **New**, name it `Website Reviewer`, paste `roles/reviewer.md` in full, and save. Use read-only permissions where the host supports them; otherwise use a read-only artifact packet and returned text. Record the actual model family. If the host cannot supply a family different from Builder's, keep this Bot INTERNAL and relay the final packet to an actual different-family reviewer. The release gate stays BLOCKED until that review happens.
 
-**Connect the group without inventing orchestration**
+**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 group routing or automated handoff is unavailable, use separate Bot chats and relay each handoff and its attachments manually. This still uses distinct workers; labels inside one chat do not create a team. Ordinary single-chat work uses SOLO.
-- If group messages are text-only, attach mockups and assets directly to the receiving Bot. A text path to an image is not visual access.
+- If group routing or automated handoff is unavailable, use separate Bot chats and relay each handoff and its attachments manually. 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.
 
 ```text
@@ -73,7 +74,7 @@ If routing fails, return the complete addressed packet for me to relay manually.
 
 **Trigger the first work handoff**
 
-Send this to **Website Researcher**, not the group or Coordinator:
+Send this directly to **Website Researcher**:
 
 ```text
 Begin user-request-to-researcher. You are the first working agent.
@@ -88,13 +89,13 @@ If you cannot search, say so, provide query-plan.md and unresolved-claims.md, an
 leave the research gate BLOCKED. If you cannot save files, return named file bodies
 for me to save and reattach; wait for read-back before passing the disk gate.
 Pass only when the saved library covers every touched domain and every claim we
-will act on has an opened source URL, a publication/update date or explicit unknown, and an access date on or after the ASK DATE. A proposal is not a completed save.
+will act on has an opened source URL, a publication/update date or explicit unknown, and an access date on or after the ASK DATE. Read back the actual saved files before confirming persistence.
 Then send research-to-coordinator to <actual Coordinator route> using all handoff
 fields and readable artifacts. No other role starts before this research gate.
 ```
 
 - First receipt: Researcher supplies `site-work/handoffs/researcher/research-<revision>.yaml` and its library. If automatic delivery fails, copy the whole receipt and attach the library to Coordinator yourself.
 - First acceptance: Coordinator opens the files, checks coverage and source dates, and writes PASS or BLOCKED in `site-work/status.md`. Only PASS releases downstream scope handoffs.
-- First design: Designer and Graphics read their named library files, return learning/top-up receipts, and apply their domain checklists. They do not start from a research summary pasted without its evidence.
-- Persistence: no Bot is assumed to remember a group chat. Preserve the files and receipts, and reattach the current revision in each new session. A durable-memory proposal remains pending until an actual supported save is read back.
+- First design: Designer and Graphics read their named library files, return learning/top-up receipts, and apply their domain checklists. They open the evidence behind the research summary before starting.
+- Persistence: preserve the files and receipts, and reattach the current revision in each new session. Carry state in the saved files, since a Bot may not remember a group chat. A durable-memory proposal remains pending until an actual supported save is read back.
 - Completion: report seven saved definitions, seven setup acknowledgements, actual routes and families, research-gate status, and all remaining capability limits separately. Never call the whole team ready from definition creation alone.

package/adapters/hermes.md

@@ -1,12 +1,12 @@
 # Hermes
 
-Status: UNVERIFIED. Native loading, project trust, team packaging and shared discovery need live trials.
+Check project trust and the installed client's loading controls before starting.
 Manual SOLO: copy the complete canonical folder into a new `.agents/skills/website-build-skill/` in the chosen project.
-A file-reading fallback can load its SKILL.md directly; that does not prove native discovery.
-Candidate preload, UNVERIFIED: `hermes -s website-build-skill` after discovery is confirmed.
-Candidate trust operation, UNVERIFIED: `hermes skills trust`; this changes trust state and requires the user's authorization.
+For explicit loading, ask the session to read its SKILL.md directly.
+After confirming the installed CLI supports it, try preload: `hermes -s website-build-skill` after discovery is confirmed.
+After checking the installed CLI help, use its trust operation: `hermes skills trust`; this changes trust state and requires the user's authorization.
 Do not create version-control state or alter global settings during a copy.
-Installs the files, activation still UNVERIFIED: `npx github:aunysillyme/website-build-skill --team --target hermes --dir . --scope project --yes --bundle-dir ./team-aliases`.
+Install the files: `npx website-build-skill --team --target hermes --dir . --scope project --yes --bundle-dir ./team-aliases`.
 
 ## Two planned branches
 
@@ -15,12 +15,12 @@ Installs the files, activation still UNVERIFIED: `npx github:aunysillyme/website
 | A: declarative roles | Current schema, exact path, native discovery and permissions | Seven full canonical bodies in verified native files |
 | B: separate sessions | Real session routes and artifact read-back | Core plus `.website-build-skill/team/hermes/setup.md`, seven session packets and an explicit alias destination |
 
-No branch is selected as verified here. The installer must fail closed on an unknown native schema.
+Select a native branch only after collecting its required evidence. The installer must fail closed on an unknown native schema.
 Session packets include each full role, tools, family, ownership, accessible library revision and handoff contract.
-An alias only loads instructions; it never proves seven workers exist.
+An alias loads instructions. Verify each worker through its actual session route.
 Manual fallback: use separate chats and [the team relay](grok.md#manual-fallback).
-A worktree or child session does not establish access to another session's uncommitted files.
-Inherited child tools do not isolate Reviewer; use a read-only packet and returned findings when needed.
+Check that each worker can read the assigned revision, including any uncommitted files it needs.
+Check Reviewer permissions on inherited tools; use a read-only packet and returned findings when needed.
 
 ## Shared core and receipt
 
@@ -37,13 +37,14 @@ Probe image, browser, execution and independent-family access separately.
 Source targets: [skills](https://hermes-agent.nousresearch.com/docs/user-guide/features/skills), [delegation](https://hermes-agent.nousresearch.com/docs/user-guide/features/delegation), [CLI](https://hermes-agent.nousresearch.com/docs/user-guide/cli).
 
 
-## Common limits and smoke check
+## Check that it loaded
+
+Native loading on this host is awaiting a real-client trial; the check below confirms it on yours. Current status: [compatibility](../docs/COMPATIBILITY.md).
 
-Status: UNVERIFIED. Instructions and candidate paths do not establish native support.
 Give the host a synthetic brief and ask it to identify the entrypoint and complete asset list.
 Record client version, date, exact path, tool availability and the observed invocation.
 Start Researcher, verify saved library read-back, then confirm Coordinator waits for its gate.
 For TEAM, record seven separate routes and families; an inherited family leaves independent review BLOCKED.
 Never grant a Reviewer write access just to persist findings. Return text for Coordinator to capture.
-No search blocks current research; no files requires saved-and-reattached bodies; no images blocks visual mockups.
+When a tool is absent, keep current research BLOCKED until opened sources return; save and reattach named file bodies before the save gate; return inspected images before the visual gate.
 Read the [method](../docs/METHOD.md), [compatibility](../docs/COMPATIBILITY.md) and [installer contract](../docs/INSTALLER.md).

package/adapters/zero-install.md

@@ -4,7 +4,7 @@ Paste this self-contained starter into an AI chat. It needs no repository retrie
 It establishes the first task; attach the full bundles for the complete method.
 
 ```text
-Use option 1: Teach my AI. Help me build a website with Research, Learn, Ingest, Scope, Match, Mock, Choose, Build, Prove, Protect, Challenge and Ship. First act as Researcher: establish the request date from host evidence, then research the site's design, accessibility, performance, security, stack and search needs using current opened sources. Save a library with source URLs, publication dates or unknown, access dates, disagreements and checklists. If you lack search, say research is BLOCKED and return a query plan. If you lack files, return named bodies for me to save and reattach before passing the save gate. Only then confirm my brief, extract my brand or request profile/banner screenshots, and show three visual mockups. Wait for my named selection before site code. Choose the smallest fitting stack. Keep evidence and handoffs between roles. Protect means security headers and the ship security checklist; Challenge means a different model family reviews a fixed candidate read-only, and I authorize release. This starter is a compact entrypoint, so do not claim Ship until the five bundles or the skill folder supply the full twelve-stage route and its checklists. Start with the site request I provide next; ask only for missing inputs that change the work.
+Use option 1: Teach my AI. Help me build a website with Research, Learn, Ingest, Scope, Match, Mock, Choose, Build, Prove, Protect, Challenge and Ship. First act as Researcher: establish the request date from host evidence, then research the site's design, accessibility, performance, security, stack and search needs using current opened sources. Save a library with source URLs, publication dates or unknown, access dates, disagreements and checklists. When search is unavailable, report research as BLOCKED and return a query plan. If you lack files, return named bodies for me to save and reattach before passing the save gate. Only then confirm my brief, extract my brand or request profile/banner screenshots, and show three visual mockups. Wait for my named selection before site code. Choose the smallest fitting stack. Keep evidence and handoffs between roles. Protect means security headers and the ship security checklist; Challenge means a different model family reviews a fixed candidate read-only, and I authorize release. This starter is a compact entrypoint, so claim Ship only after the five bundles or the skill folder supply the full twelve-stage route and its checklists. Start with the site request I provide next; ask only for missing inputs that change the work.
 ```
 
 ## Full method
@@ -12,6 +12,7 @@ Use option 1: Teach my AI. Help me build a website with Research, Learn, Ingest,
 Paste or attach [method](../docs/bundles/method.md), [prompts](../docs/bundles/prompts.md), [playbooks](../docs/bundles/playbooks.md), [checklists](../docs/bundles/checklists.md) and [team](../docs/bundles/team.md).
 They exist locally and in the public repository: browse [the bundle folder](https://github.com/aunysillyme/website-build-skill/tree/main/docs/bundles), download [the main archive](https://github.com/aunysillyme/website-build-skill/archive/refs/heads/main.zip), or open a raw file such as
 `https://raw.githubusercontent.com/aunysillyme/website-build-skill/main/docs/bundles/method.md`.
-Retrieval serves the files; a host bootstrapping itself from a URL is UNVERIFIED.
+Ask the host to identify the files it actually loaded; see [compatibility](../docs/COMPATIBILITY.md) for the required evidence.
+Native loading on this host is awaiting a real-client trial; asking the host to confirm what it read is the check that establishes it on yours. Current status: [compatibility](../docs/COMPATIBILITY.md).
 Never substitute a similar repository when retrieval fails. Pin one revision and verify manifest hashes before combining files.
-Without retrieval, supply the text itself. A URL alone is not loaded knowledge.
+When retrieval is unavailable, supply the text itself and ask the host to confirm what it read.

package/docs/COMPATIBILITY.md

@@ -1,34 +1,42 @@
 # Compatibility
 
-Status vocabulary: DOCUMENTED requires opened official evidence; TESTED requires a recorded actual trial.
-This repository currently makes no TESTED host claim. All package integrations below are UNVERIFIED.
-Candidate interfaces come from the design specification; consult the linked official source before a live trial.
-
-| Host | Manual payload | What to verify | Source |
-| --- | --- | --- | --- |
-| Claude Code | Complete skill or root plugin | Discovery, invocation, assets and worker isolation | [skills](https://code.claude.com/docs/en/skills) |
-| Codex | Complete skill, explicit router | Shared destination, role configuration, real family | [skills](https://learn.chatgpt.com/docs/build-skills) |
-| Hermes | Complete skill, separate sessions | Trust, alias semantics, routes, inherited permissions | [skills](https://hermes-agent.nousresearch.com/docs/user-guide/features/skills) |
-| Antigravity | Explicit core pointer | Schema, paths, quoted off, routing, denied writes | [subagents](https://antigravity.google/docs/subagents) |
-| Grok Bot | Five bundles, manual roles | Actual account controls, routes, image relay | [Bots](https://docs.x.ai/grok-bot/bots) |
-| Claude Desktop | Five bundles; future skill ZIP | Account upload controls and loaded resources | [skills](https://support.claude.com/en/articles/12512180-use-skills-in-claude) |
-| ChatGPT Project/custom GPT | Instructions plus five bundles | File access, tool availability, state reattachment | [Projects](https://help.openai.com/en/articles/10169521-projects-in-chatgpt) |
-| Generic file-reading agent | Explicit core pointer | Router read-back and preserved instructions | [adapter](../adapters/agents-md.md) |
-
-## Evidence required per row
-
-Record exact client/runtime version, actual trial date, operating system, artifact revision,
-installed file list and hashes, invocation, observed outputs, negative cases and limitations.
-Retain a sanitized receipt in this repository before promoting the claim.
-Documentation alone cannot establish native loading, enforcement or automatic worker creation.
+## Tested hosts
+
+No host below has a completed real-client trial yet. Each 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
+documented to tested when its receipt records the client/runtime version, trial date,
+operating system, package revision, installed paths and hashes, invocation, observed
+output, failure cases and remaining checks, kept sanitized in this repository.
 Hosted repository checks have a [revision-bound baseline receipt](evidence/audit-baseline.json).
-Those Linux CI checks do not establish client activation. Windows/client trials, registry
-delivery, ZIP upload and raw-URL bootstrap remain UNVERIFIED.
-The maintainer runtime is Node 22.22.3. The package declares Node 18 or newer, and the check
-matrix runs 18, 20, 22.22.3 and 24; no other runtime is claimed.
 
-## Degradation
+## Hosts with a documented setup
+
+These guides describe file-copy, upload and manual-session routes. Their official documentation
+links are verification targets for a client trial. A documented setup becomes a tested-host entry
+when its receipt demonstrates loading, file access, tool permissions and the selected workflow.
+
+| Host | Setup guide | What to verify | Official reference |
+|---|---|---|---|
+| Claude Code | [Skill or plugin](../adapters/claude-code.md) | Discovery, invocation, assets and worker isolation | [Skills](https://code.claude.com/docs/en/skills) |
+| 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) |
+| 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) |
+
+## Evidence to collect
+
+- **Documentation:** save the opened official source, version, access date and setup facts it supports.
+- **Native loading:** record the actual entrypoint and every resource the client can read.
+- **TEAM:** record separate routes, setup acknowledgements, model families and permission probes.
+- **Delivery:** record fresh package installs for each operating system being claimed, including Linux and Windows.
+- **Uploads and URLs:** verify account ZIP controls and raw-URL retrieval in the actual client.
+- **Runtime:** the package declares Node 18 or newer; [the check workflow](https://github.com/aunysillyme/website-build-skill/blob/main/.github/workflows/check.yml) defines its runtime matrix.
+
+## Working with the tools you have
 
-The [canonical missing-capability table](../skills/website-build-skill/playbooks/research-and-memory.md#missing-capability-table)
-is included in method and team bundles. It keeps research, visual mockups, measurements,
-independent review and release blocked when their required tools or evidence are missing.
+The [canonical tool table](../skills/website-build-skill/playbooks/research-and-memory.md#working-with-the-tools-you-have)
+supplies the next step for research, saved files, visual mockups, measurements, independent review and release.
+Each stage resumes when its required tool output or evidence is available.

package/docs/EVALUATION.md

@@ -52,6 +52,9 @@ A change to the ledger itself requires code-owner review. No content checker can
 The gate scans every public file, including hidden community metadata, fixtures and generated bundles.
 It rejects personal paths, private identifiers, personal names and email addresses without echoing their values.
 Production exceptions are exact license authorship and repository URL namespaces.
+The related public repository allowlist contains exactly `agent-personalizer` and
+`model-orchestrator`, for GitHub URLs, raw file URLs and npm GitHub shorthand.
+The privacy regression rejects a third repository, longer names and adjacent private text.
 The supported public product name and exact CODEOWNERS handle are narrow, resolved
 exceptions implemented by privacyIssues. Path-shaped uses remain rejected. These
 exceptions do not permit personal identifiers elsewhere.

package/docs/INSTALLER.md

@@ -1,35 +1,39 @@
 # Installer contract
 
-Status: the installer is implemented; native worker generation is not.
-`npx github:aunysillyme/website-build-skill` copies the canonical files, verifies them by read-back and writes a
-receipt of exactly what it wrote. It never creates a running agent, and host activation stays
-UNVERIFIED until a real client trial. The manual copy route below still works and needs no Node.
+`npx website-build-skill` copies the canonical files, verifies them by read-back and writes a
+receipt of exactly what it wrote. Open the chosen host and ask it to read the installed entrypoint.
+See [compatibility](COMPATIBILITY.md) for host setup evidence and loading checks.
+For TEAM, use the complete role bundles with separate sessions and manual handoffs.
 
-## Manual copy available now
+## Manual copy
 
 Copy the complete `skills/website-build-skill/` directory into a new, empty destination:
 
-| Target | Project destination | Activation status |
+| Target | Project destination | Loading step |
 | --- | --- | --- |
-| Claude Code | `.claude/skills/website-build-skill/` | UNVERIFIED; read back the entrypoint and assets |
-| Codex | `.agents/skills/website-build-skill/` | UNVERIFIED; inspect discovery and invocation |
-| Hermes | `.agents/skills/website-build-skill/` | UNVERIFIED; trust and shared discovery need a trial |
-| Antigravity | `.website-build-skill/` | Explicit file-reading route; native definitions planned |
-| Generic agent | `.website-build-skill/` | Ask it to read the entrypoint; preserve existing routers |
-| Grok file-capable host | `.grok/skills/website-build-skill/` | UNVERIFIED; otherwise paste bundles |
+| Claude Code | `.claude/skills/website-build-skill/` | Read back the entrypoint and assets |
+| Codex | `.agents/skills/website-build-skill/` | Inspect discovery and invocation |
+| Hermes | `.agents/skills/website-build-skill/` | Check trust and shared discovery |
+| Antigravity | `.website-build-skill/` | Ask the session to read the entrypoint |
+| Generic agent | `.website-build-skill/` | Read the entrypoint and preserve existing routers |
+| Grok file-capable host | `.grok/skills/website-build-skill/` | Read back the entrypoint, or paste the bundles |
 
 Do not merge into a conflicting directory. Compare and preserve existing files first.
 Copy a router pointer into existing project instructions only with authorization; do not replace them.
-A copied file is prepared content. Discovery and activation require a separate read-back.
+Confirm the host can read the copied entrypoint and assets before beginning.
 For chat-only hosts, attach the five bundles and use the [Project instructions](../adapters/chatgpt-project.md).
 
 ## Command interface
 
-Before the package is on npm, the same entry point runs from the repository with
-`npx github:aunysillyme/website-build-skill <flags>`, verified to print its version.
+Install from npm:
 
-Installs the files, activation still UNVERIFIED: `npx github:aunysillyme/website-build-skill --solo --target codex --dir . --scope project --yes`.
-Installs the files, activation still UNVERIFIED: `npx github:aunysillyme/website-build-skill --team --target antigravity --dir . --scope project --yes`.
+```bash
+npx website-build-skill --solo --target codex --dir . --scope project --yes
+npx website-build-skill --team --target antigravity --dir . --scope project --yes
+```
+
+For unreleased changes, use `npx github:aunysillyme/website-build-skill` with the same flags.
+Append `#<reviewed-commit-sha>` to the repository reference for a reproducible install.
 
 - Choice: mutually exclusive `--solo` / `--team`; no arguments asks the canonical human question first.
 - Target: `claude-code`, `codex`, `hermes`, `antigravity`, `grok`, `agents`, `chatgpt`, `portable`.
@@ -61,13 +65,10 @@ Hermes branch A requires verified declarative role support. Branch B uses separa
 Both branches keep Researcher first, seven acknowledgements, a blocked downstream gate and a different-family Reviewer.
 See [Antigravity](../adapters/antigravity.md), [Hermes](../adapters/hermes.md) and [team ownership](../adapters/team.yaml).
 
-## What is proven, and what is not
-
-Proven by the test suite and by hand on macOS: traversal and symlink refusal at and below the
-project root, whole-set conflict refusal, idempotent reruns, dry run writing nothing, an
-unwritable output root failing before any skill file, receipt digests matching the bytes on
-disk, uninstall keeping a changed file, router files left untouched with exit 5.
+## Verify the installation
 
-Not proven by anyone: host discovery or activation on any client, a fresh tarball trial on
-Linux or Windows, and the native worker generation described below. Record actual results
-before changing a compatibility row.
+Run the local checks with `npm run check` and `npm test`. The installer tests cover traversal
+and symlink refusal, whole-set conflict refusal, idempotent reruns, dry-run behavior, output-root
+writability, receipt digests, changed-file preservation during uninstall and router integration.
+After installing, compare the receipt with files on disk and follow your adapter's loading check.
+Record client-trial evidence in [compatibility](COMPATIBILITY.md).

package/docs/README.md

@@ -0,0 +1,26 @@
+# Documentation
+
+Start with the guide for the job you want to do:
+
+| Guide | What it gives you |
+|---|---|
+| [Method](METHOD.md) | The stages, role owners and evidence gates |
+| [Installer](INSTALLER.md) | Setup commands, destinations, receipts, exit codes and uninstall |
+| [Compatibility](COMPATIBILITY.md) | Tested hosts, documented setups and evidence requirements |
+| [Tips](TIPS.md) | Brand, design, scope and research practices |
+| [Provenance](PROVENANCE.md) | Sources, attribution and the canonical file map |
+| [Evaluation](EVALUATION.md) | Repository checks and adversarial test cases |
+| [Library check](LIBRARY-CHECK.md) | Validate saved research claims and source receipts |
+| [Bundles](#bundles) | The full method as files to attach or paste into a chat |
+
+## Bundles
+
+Use files from one revision together:
+
+- [Method](bundles/method.md): entrypoint and research contract.
+- [Prompts](bundles/prompts.md): stage instructions.
+- [Playbooks](bundles/playbooks.md): implementation and verification guidance.
+- [Checklists](bundles/checklists.md): stage evidence and release checks.
+- [Team](bundles/team.md): complete roles and manual team setup.
+
+[Quick start](../README.md#quick-start) · [Agent source catalog](../llms.txt).

package/docs/bundles/checklists.md

@@ -4,7 +4,7 @@ Generated from the canonical manifest. Do not edit this file.
 
 Bare skill paths in the included instructions resolve from the canonical skill directory.
 For uploads, locate the named source section in these bundles; request an attachment when absent.
-Project paths resolve only in the authorized website workspace. Native loading is UNVERIFIED.
+Project paths resolve only in the authorized website workspace. See [host setup and evidence](../COMPATIBILITY.md).
 
 ## Contents
 
@@ -40,15 +40,25 @@ Date rule: [ASK DATE, source evidence, and revalidation](../../skills/website-bu
 
 ## Blockers first
 
+AD03, AD04 and AD07 use this checker ladder and the five-rule manual equivalent
+in the receipt section below:
+
+1. `website-build-skill check-library <root>/site-work`, when that command is on PATH.
+2. Otherwise `npx -y website-build-skill@<packageVersion> check-library <root>/site-work`, where `<packageVersion>` is read from the installed `manifest.json`. Never write the literal version into prose, or it goes stale on every bump.
+3. From a repository checkout: `node bin/website-build-skill.mjs check-library <site-work-dir>`.
+4. When no rung can run, meaning no shell, no PATH command and npx fails or has no network: Reviewer records the five-rule manual equivalent. Also record each rung tried, with its command, exit code and output, as the reason.
+
+For every rung that runs, save the command, exit code and output. PASS still needs exit 0 from a mechanical rung, or a recorded manual equivalent for rung 4. Acted-on UNVERIFIED claims still keep research acceptance BLOCKED.
+
 | Check | Reject condition and required passing evidence |
 | --- | --- |
 | AD01: date provenance | Reject missing, invalid, assumed or model-inferred ASK DATE; missing rung; `assumed`, `from memory` or `user-supplied` rung; raw evidence absent or inconsistent with its rung. Require the allowed first successful ladder rung, raw evidence, attempts, precision and any cross-check. Validate the calendar value and derived-floor label; never accept a fabricated date as environment output. |
 | AD02: no date solicitation | Reject any active instruction asking the user to supply or confirm the date, regardless of wording. Scan prompts, roles, playbooks, checklists, references, templates, adapters, README, SKILL.md and generated bundles; combine pattern checks with a semantic read for paraphrases. Negative test strings in explicitly inactive fixtures are data, never executable instructions. |
-| AD03: acted-on claim dates | Every acted-on claim has its actual access date equal to or later than ASK DATE inside this engagement, a fetch-time source-opening receipt at `research/library/receipts/<CLAIM-ID>.md` relative to `site-work/`, and a separate source publication/update date or explicit unknown. Reject earlier, missing, future-fabricated or merely restamped access dates, including in downstream top-ups. Apply the qualified floor procedure only with matching scope provenance and disclosed precision. Require the `check-library` command, exit code and output, or the recorded five-rule manual equivalent below when no shell exists. |
-| AD04: source integrity | Every cited claim requires a fetch receipt at `research/library/receipts/<CLAIM-ID>.md` relative to `site-work/`, with URL and a verbatim supporting excerpt of at least 80 characters. Without it the claim is UNVERIFIED; acting on it keeps research acceptance BLOCKED. Require source date evidence in the excerpt, otherwise `published: unknown`. Require the `website-build-skill check-library <root>/site-work` command, exit code and output, or the recorded five-rule manual equivalent below when no shell exists. A self-assigned Verified label is not evidence. Reject confident undated claims as findings, regardless of familiarity. |
+| AD03: acted-on claim dates | Every acted-on claim has its actual access date equal to or later than ASK DATE inside this engagement, a fetch-time source-opening receipt at `research/library/receipts/<CLAIM-ID>.md` relative to `site-work/`, and a separate source publication/update date or explicit unknown. Reject earlier, missing, future-fabricated or merely restamped access dates, including in downstream top-ups. Apply the qualified floor procedure only with matching scope provenance and disclosed precision. Require the `check-library` checker ladder above, with command, exit code and output for each rung tried, or the recorded five-rule manual equivalent below only under rung 4. |
+| AD04: source integrity | Every cited claim requires a fetch receipt at `research/library/receipts/<CLAIM-ID>.md` relative to `site-work/`, with URL and a verbatim supporting excerpt of at least 80 characters. Without it the claim is UNVERIFIED; acting on it keeps research acceptance BLOCKED. Require source date evidence in the excerpt, otherwise `published: unknown`. Require the `check-library` checker ladder above, with command, exit code and output for each rung tried, or the recorded five-rule manual equivalent below only under rung 4. A self-assigned Verified label is not evidence. Reject confident undated claims as findings, regardless of familiarity. |
 | AD05: library stamps and reuse | Every library Markdown file opens with `Research as of <ASK DATE>` from scope, with the floor qualification where required. Reject an older or different stamp, a new stamp over unrevalidated content, or any prior-run claim without original access and recorded revalidation decision/current source-opening evidence. Old dates in labelled history may remain only alongside current evidence; they cannot support reliance themselves. |
 | AD06: domain coverage and expiry | Every applicable domain has a substantive file/checklist and at least one access-dated source, or an explicit NOT APPLICABLE with a reason. `staleness.md` contains all thirteen windows, current-version checks, the earliest-expiring domain, its window and recheck date relative to ASK DATE. Reject elapsed windows or change triggers without rechecks before reliance, including on later engagement days. |
-| AD07: capability and gate status | No web access leaves the current-research gate BLOCKED with `query-plan.md` and `unresolved-claims.md`, even when a prior library exists. Reject PASS or PASSED without actual web evidence, complete date provenance, saved/read-back files and required domain coverage. PASS additionally requires zero exit from `check-library` for `research/library/receipts/<CLAIM-ID>.md` relative to `site-work/`, or its recorded five-rule manual equivalent, and no acted-on UNVERIFIED claims. A derived-floor result repeats its limitation; it never claims exact-day currency. |
+| AD07: capability and gate status | No web access leaves the current-research gate BLOCKED with `query-plan.md` and `unresolved-claims.md`, even when a prior library exists. Reject PASS or PASSED without actual web evidence, complete date provenance, saved/read-back files and required domain coverage. PASS additionally requires exit 0 from a mechanical rung of the `check-library` checker ladder above for `research/library/receipts/<CLAIM-ID>.md` relative to `site-work/`, or its recorded five-rule manual equivalent only under rung 4, and no acted-on UNVERIFIED claims. A derived-floor result repeats its limitation; it never claims exact-day currency. |
 | AD08: relative active recency | Reject literal calendar years/ranges used as recency instructions in active prompts, playbooks, checklists, roles, references, templates, adapters, bundles, README and SKILL.md. Permit only bounded ARCHIVE, QUOTE and EVIDENCE contexts identified by the manifest context allowlist; inspect adjacent active text and generated copies too. |
 | AD09: independent freshness review | Reviewer repeats AD01 through AD08 against the actual candidate library, acted-on claim IDs, top-ups and `research/library/receipts/<CLAIM-ID>.md` relative to `site-work/`, including `check-library` output or the recorded manual equivalent. Independently re-fetch at least 3 acted-on sources or 20 percent rounded up, whichever is larger. Confirm each receipt excerpt appears on the live page and record URL, tool, outcome and supporting page text. Any excerpt mismatch is a finding that keeps research acceptance BLOCKED. Reject missing URL/access, access dates before ASK DATE, and stamped-but-unrevalidated material; treat confident undated claims as findings. Coordinator records those findings and keeps dependent research/ship acceptance BLOCKED until Researcher corrects evidence and the normal reproduction/disposition checks pass. |
 
@@ -68,10 +78,15 @@ prerequisite that would activate Reviewer before Researcher finishes.
 
 ## Receipt check and manual equivalent
 
-When a shell exists, save the exact `website-build-skill check-library <root>/site-work`
-command, exit code and output with the gate receipt. A repository checkout can use
-`node bin/website-build-skill.mjs check-library <site-work-dir>`. Without a shell,
-Reviewer records each rule's result, claim IDs and evidence paths by hand:
+1. `website-build-skill check-library <root>/site-work`, when that command is on PATH.
+2. Otherwise `npx -y website-build-skill@<packageVersion> check-library <root>/site-work`, where `<packageVersion>` is read from the installed `manifest.json`. Never write the literal version into prose, or it goes stale on every bump.
+3. From a repository checkout: `node bin/website-build-skill.mjs check-library <site-work-dir>`.
+4. When no rung can run, meaning no shell, no PATH command and npx fails or has no network: Reviewer records the five-rule manual equivalent. Also record each rung tried, with its command, exit code and output, as the reason.
+
+For every rung that runs, save the command, exit code and output. PASS still needs exit 0 from a mechanical rung, or a recorded manual equivalent for rung 4. Acted-on UNVERIFIED claims still keep research acceptance BLOCKED.
+
+Save the ladder evidence with the gate receipt. For rung 4, Reviewer records each
+rule's result, claim IDs and evidence paths by hand:
 
 1. Reject an OPENED or Verified row, regardless of case, without its claim receipt.
 2. Reject a receipt missing url, fetched_at, tool or excerpt, or an excerpt shorter