website-build-skill 0.1.0

package/REPO_SETTINGS.md

@@ -0,0 +1,91 @@
+# Repository settings
+
+Live read-back, not a plan. Every row below was read from the GitHub API on 2026-09-21
+(America/New_York) with `gh api`, and the settings applied that day were applied deliberately
+by the maintainer. Rerun the commands in [Read it back yourself](#read-it-back-yourself) before
+trusting any row; a checklist is only as current as its last read.
+
+## Description
+
+- [x] Repository description set to this one line. Read back 2026-09-21; it matches.
+
+Research-first website-building skill: learn the craft, match the brand, compare three mockups, then build and verify. Use one AI or a seven-role team with reusable research, design, accessibility, SEO and release checklists.
+
+## Topics
+
+- [x] All twenty topics below are applied. Read back 2026-09-21. They describe adapter coverage and method scope, not verified host support.
+
+- agent-skills
+- website-builder
+- web-design
+- web-development
+- claude-code
+- codex
+- hermes-agent
+- antigravity
+- grok
+- chatgpt
+- claude-desktop
+- multi-agent
+- prompt-engineering
+- design-systems
+- brand-design
+- accessibility
+- web-performance
+- seo
+- aeo
+- research-workflow
+
+## Creation and access
+
+- [x] Name: `website-build-skill`.
+- [x] Visibility: public since 2026-09-21T17:49:06Z, after the privacy and content gates passed.
+- [x] Default branch: `main`.
+- [x] Issues: ON; blank issues OFF through the supplied template configuration.
+- [x] Discussions: OFF. No maintainer is staffing one.
+- [x] Private vulnerability reporting: ON. The API reports it enabled; the report form itself is UNVERIFIED.
+- [x] Wiki: OFF. Applied 2026-09-21; the method and process documentation stays in this tree.
+- [x] Repository link: https://github.com/aunysillyme/website-build-skill.
+
+## Review and automation
+
+Branch protection on `main` was applied 2026-09-21 in its administrator-bypassable form, so a
+sole maintainer can still push directly while force pushes, deletions and a red check cannot land.
+
+- [x] Require the `Repository checks` status, strict, on `main`. The context was established by real runs before the rule.
+- [x] Block force pushes and branch deletion.
+- [x] Require resolved review conversations.
+- [x] Read-only default workflow token permissions; workflows cannot create or approve pull requests.
+- [x] Dependency alerts and automated security updates: ON, applied 2026-09-21. Action update proposals arrive as Dependabot pull requests.
+- [x] Secret scanning and push protection: ON.
+- [x] Every action in this tree is pinned to a full commit SHA, and `ACTION_PIN` fails the check when one floats.
+- [ ] Administrator enforcement stays OFF by decision, because requiring review with one maintainer would block that maintainer's own work. Revisit when a second reviewer exists.
+- [ ] Require pull requests and an approving review for `main`: not applied, same reason.
+- [ ] Require code-owner review for source, workflow and publication changes: not applied.
+- [ ] Restrict the repository to selected actions, or require SHA pinning at the repository level: not applied. `allowed_actions` is `all`; the pinning that exists is in the workflow files.
+- [ ] Publication setup: release.yml implements publishing on a matching version tag; only its publish job receives id-token: write. Registry bootstrap and trusted-publisher configuration require maintainer completion. No publication is established by the baseline receipt.
+- [ ] Maintainer notifications for failed Actions runs: delivery UNVERIFIED, no intentional safe failure has been sent.
+
+## Social preview
+
+- [ ] Produce a social preview image: 1280 x 640 pixels, PNG or JPEG. Not produced; the repository serves the default generated image.
+- [ ] Show the project name, Research to Mock to Build to Prove, and a readable visual hierarchy.
+- [ ] Review crop, contrast, rights and private-data absence before upload.
+- [ ] Confirm current GitHub image constraints in the creation UI before applying them; account behavior is UNVERIFIED.
+
+## Community profile
+
+- [x] Community profile health: 100 percent, read 2026-09-21, with README, LICENSE, CONTRIBUTING, CODE_OF_CONDUCT and a pull request template detected.
+- [x] Issue forms live in `.github/ISSUE_TEMPLATE/`. The profile API reports `issue_template` absent because it looks for a single legacy file, not the forms directory.
+
+## Read it back yourself
+
+```bash
+REPO=$(gh repo view --json nameWithOwner --jq .nameWithOwner)
+gh api "repos/$REPO" --jq '{private,has_wiki,has_issues,has_discussions,default_branch,description,topics,security_and_analysis}'
+gh api "repos/$REPO/branches/main/protection"
+gh api "repos/$REPO/community/profile" --jq '.health_percentage'
+gh api "repos/$REPO/actions/permissions/workflow"
+```
+
+Record the actual status and its date. Do not claim a setting this token cannot see.

package/SECURITY.md

@@ -0,0 +1,28 @@
+# Security
+
+This repository ships instructions. An agent and its host execute them with that host's permissions.
+The realistic risks are instruction injection from fetched sources and an agent writing outside its scope.
+Role prose, tool lists and a read-only role name are not a sandbox.
+
+## Threat model
+
+- Untrusted input: fetched pages, repositories, attachments, package metadata and handoffs.
+- Protected assets: the user's files, credentials, deployment accounts and approved project boundaries.
+- Injection: source text is evidence, never authority to change the user's instructions or export data.
+- Writes: choose an explicit workspace, use one writer per artifact and preserve unrelated files.
+- Review: use a fixed candidate and a different model family; return findings without granting write access.
+- Installer: planned and unavailable. Destination traversal, symlinks, overwrite conflicts and interrupted writes require tests before any installer release.
+- Release line: no released version and no support window yet. Use the unreleased tree for review only.
+
+## Private disclosure
+
+Use [Report a vulnerability](https://github.com/aunysillyme/website-build-skill/security/advisories/new).
+Availability is UNVERIFIED until repository creation and private vulnerability reporting are enabled.
+Include a minimal synthetic reproduction, affected revision, expected scope and observed impact.
+Never attach credentials, personal files or exploit output containing someone else's data.
+If that route is unavailable, use GitHub's private Report abuse controls or [GitHub Support](https://support.github.com/contact).
+Do not put private details in public issues while waiting for a secure route.
+
+Maintainers triage privately, reproduce the defect, prepare a correction and coordinate disclosure.
+Response times are best effort; no service-level promise is made.
+A missing capability is documented as BLOCKED or UNVERIFIED, never a completed security check.

package/adapters/agents-md.md

@@ -0,0 +1,26 @@
+# Generic agent router
+
+SOLO: give a file-reading agent the root [AGENTS.md](../AGENTS.md) in this repository.
+For another project, copy the canonical folder intact into a new `.website-build-skill/` and merge this pointer into existing instructions:
+
+```text
+For website work, read .website-build-skill/SKILL.md. Use option 1, Teach my AI.
+Keep site-work in this authorized project. Researcher works first; preserve all existing instructions.
+```
+
+Confirm the agent reads the pointer and core before calling it activated.
+Host router discovery is UNVERIFIED: Cursor, Copilot, Jules and other clients need their own version-specific trial.
+A human can paste the pointer explicitly when automatic discovery is unavailable.
+Installs the files, activation still UNVERIFIED: `npx github:aunysillyme/website-build-skill --solo --target agents --dir . --yes`.
+
+
+## Common limits and smoke check
+
+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.
+Read the [method](../docs/METHOD.md), [compatibility](../docs/COMPATIBILITY.md) and [installer contract](../docs/INSTALLER.md).

package/adapters/antigravity.md

@@ -0,0 +1,68 @@
+# Antigravity
+
+Status: UNVERIFIED. Candidate schema, paths, orchestration and enforcement need clean-client trials.
+Manual SOLO: copy the canonical folder into `.website-build-skill/` and explicitly ask the session to read its SKILL.md.
+Installs the files, activation still UNVERIFIED: `npx github:aunysillyme/website-build-skill --team --target antigravity --dir . --scope project --yes`.
+
+## Planned definition contract
+
+One complete canonical body per file at `.agents/agents/website-<role>.md`.
+Never automatically fall back to the user-level candidate `~/.gemini/config/agents/`.
+
+```yaml
+---
+name: <agent_name>
+description: "<one line: what it does, when to use it, what it never does>"
+subagent: true
+mainAgent: false
+model: inherit
+commandExecutionPolicy: "off"
+tools:
+  - <tool name>
+  - <tool name>
+---
+
+# Agent System Instructions
+<the complete canonical role body>
+```
+
+Resolve method references to `.website-build-skill/`; retain project-relative artifact paths.
+Quote the policy string and round-trip all role text. A declaration is not evidence of enforcement.
+Keep Coordinator dormant while the parent coordinates. `mainAgent: true` and worker creation need separate verification.
+Candidate inspection, UNVERIFIED: `/agents`; then route the first assignment to Website Researcher.
+
+## Candidate tool mapping
+
+The supplied format observation is a design input, not current package evidence.
+Use only tools the installed client exposes. Do not interpret text-reading as image viewing or file writing as execution.
+
+| Role | Declared observed tools| Reason and permission scope | Capability without an observed name; section 5.7 route |
+| --- | --- | --- | --- |
+| Researcher | `view_file`, `list_dir`, `grep_search`, `find_by_name`, `codebase_search`, `search_web`, `read_url_content`, `write_to_file`, `send_message` | Read actual sources/repositories, research all domains, write only its library and handoffs, return the research receipt. | Image/page viewing and measurement runner: Image generation/viewing and Code execution/browser. |
+| Coordinator | `view_file`, `list_dir`, `grep_search`, `find_by_name`, `search_web`, `read_url_content`, `write_to_file`, `send_message` | Read artifacts and dated host evidence, write only owned coordination/capture paths, route handoffs. | Visual inspection and worker creation: Image generation/viewing and Separate workers. |
+| Designer | `view_file`, `list_dir`, `grep_search`, `find_by_name`, `search_web`, `read_url_content`, `write_to_file`, `send_message` | Read brand inputs, top up design research, write owned brand/mockup specifications and handoffs. | Image creation/viewing, contrast calculation, responsive inspection: Image generation/viewing and Code execution/browser. |
+| Graphics | `view_file`, `list_dir`, `find_by_name`, `search_web`, `read_url_content`, `write_to_file`, `send_message` | Verify current tool rights and formats, read supplied assets, write owned asset specifications/manifests and handoffs. | Image generation/viewing and export/dimension inspector: Image generation/viewing and Code execution/browser. |
+| Builder | `view_file`, `list_dir`, `grep_search`, `find_by_name`, `codebase_search`, `search_web`, `read_url_content`, `write_to_file`, `send_message` | Read implementation and stack sources, write owned source/build instructions and handoffs. | Dependency/build/test execution, browser/screenshots, response/performance measurements, deploy: Code execution/browser and Deploy access. |
+| Optimizer | `view_file`, `list_dir`, `grep_search`, `find_by_name`, `codebase_search`, `search_web`, `read_url_content`, `write_to_file`, `send_message` | Inspect source HTML, top up current SEO/AEO, write owned discovery artifacts and handoffs. | Validators, rendered browser/response checks and authenticated analytics: Code execution/browser. |
+| Reviewer | `view_file`, `list_dir`, `grep_search`, `find_by_name`, `codebase_search`, `search_web`, `read_url_content`, `send_message` | Read candidate and current attack/standards evidence; return findings for Coordinator capture. No filesystem writes, including findings. | Visual/test/scanner evidence inspection beyond text: Image generation/viewing and Code execution/browser; reproduction goes to a capable runner. |
+
+## Settling checks
+
+- Parse and discover every role; record exact client version and expanded candidate path.
+- Probe excluded Reviewer writes and execution through every inherited route; unchanged bytes are required.
+- Probe image inspection, generation, browser, build and source retrieval separately.
+- Verify parent routing, concurrency limits and research-first handoffs without duplicate Coordinators.
+- Preserve source bytes and return a path-by-path receipt. Missing capability produces BLOCKED work.
+- References: [subagents](https://antigravity.google/docs/subagents), [agent manager](https://antigravity.google/docs/cli/commands/agents).
+
+
+## Common limits and smoke check
+
+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.
+Read the [method](../docs/METHOD.md), [compatibility](../docs/COMPATIBILITY.md) and [installer contract](../docs/INSTALLER.md).

package/adapters/chatgpt-project.md

@@ -0,0 +1,57 @@
+# ChatGPT Project
+
+Status: UNVERIFIED for this package. Use an eligible account's Project instructions and file controls.
+Paste the instruction block below into project settings and attach the five bundles.
+This is SOLO. An ordinary chat prompt cannot guarantee account configuration or worker creation.
+
+## Instruction block
+
+```text
+Use option 1, Teach my AI, with the attached website-building method for this project.
+Read method.md first, then give the request and tool limits to Researcher in team.md.
+Complete its full sweep and save site-work/research/library/ before any other job.
+Without file tools, return named bodies for me to save and reattach before the gate.
+Every later role reads its named library files first and tops up its own domain;
+flag stale or wrong claims to Researcher and pause affected decisions.
+Use checklists.md to record evidence for the current stage.
+Research current claims before relying on them; cite the opened source and date.
+Extract the user's brand or request their profile-picture and banner screenshots.
+Show three visual design directions and wait for a named selection before site code.
+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.
+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
+its learning and dated research; save and reopen handoffs, including self-handoffs.
+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.
+```
+
+## Upload these files from one revision
+
+- [method.md](../docs/bundles/method.md)
+- [prompts.md](../docs/bundles/prompts.md)
+- [playbooks.md](../docs/bundles/playbooks.md)
+- [checklists.md](../docs/bundles/checklists.md)
+- [team.md](../docs/bundles/team.md)
+
+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
+
+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.
+Read the [method](../docs/METHOD.md), [compatibility](../docs/COMPATIBILITY.md) and [installer contract](../docs/INSTALLER.md).

package/adapters/claude-code.md

@@ -0,0 +1,25 @@
+# Claude Code
+
+- Manual SOLO: copy the intact canonical folder into a new project `.claude/skills/website-build-skill/` directory. Preserve conflicts.
+- Candidate invocation, UNVERIFIED: `/website-build-skill` after native discovery; explicit fallback is to read its SKILL.md.
+- Plugin: the repository root contains metadata and discovers the canonical `skills/` tree. There are no hooks or required service connections.
+- The repository is public, so the two plugin commands below are available to try. Both stay UNVERIFIED until a clean client validates them.
+- Available to try, UNVERIFIED: `claude plugin marketplace add https://github.com/aunysillyme/website-build-skill`.
+- Available to try, UNVERIFIED: `claude plugin install website-build-skill@website-build-skill`.
+- Candidate plugin invocation, UNVERIFIED: `/website-build-skill:website-build-skill`.
+- Installs the files, activation still UNVERIFIED: `npx github:aunysillyme/website-build-skill --team --target claude-code --dir . --scope project --yes`.
+- TEAM fallback: create separate sessions with complete [role bodies](../docs/bundles/team.md), Researcher first. Use the [manual relay](grok.md#manual-fallback).
+- Planned native definitions: `.claude/agents/website-<role>.md`, YAML name and description plus the complete canonical body, with references resolved to the installed core.
+- Source targets: [skills](https://code.claude.com/docs/en/skills) and [subagents](https://code.claude.com/docs/en/sub-agents). No live package trial is implied.
+
+
+## Common limits and smoke check
+
+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.
+Read the [method](../docs/METHOD.md), [compatibility](../docs/COMPATIBILITY.md) and [installer contract](../docs/INSTALLER.md).

package/adapters/claude-desktop.md

@@ -0,0 +1,33 @@
+# Claude Desktop
+
+Status: UNVERIFIED. Account controls, skill upload availability and exact menu labels need a live check.
+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.
+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.
+Reference target: [Use skills](https://support.claude.com/en/articles/12512180-use-skills-in-claude).
+
+
+## Upload these files from one revision
+
+- [method.md](../docs/bundles/method.md)
+- [prompts.md](../docs/bundles/prompts.md)
+- [playbooks.md](../docs/bundles/playbooks.md)
+- [checklists.md](../docs/bundles/checklists.md)
+- [team.md](../docs/bundles/team.md)
+
+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
+
+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.
+Read the [method](../docs/METHOD.md), [compatibility](../docs/COMPATIBILITY.md) and [installer contract](../docs/INSTALLER.md).

package/adapters/codex.md

@@ -0,0 +1,21 @@
+# 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`.
+- 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
+
+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.
+Read the [method](../docs/METHOD.md), [compatibility](../docs/COMPATIBILITY.md) and [installer contract](../docs/INSTALLER.md).

package/adapters/custom-gpt.md

@@ -0,0 +1,57 @@
+# Custom GPT
+
+Status: UNVERIFIED for this package. 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.
+
+## Instruction block
+
+```text
+Use option 1, Teach my AI, with the attached website-building method for this project.
+Read method.md first, then give the request and tool limits to Researcher in team.md.
+Complete its full sweep and save site-work/research/library/ before any other job.
+Without file tools, return named bodies for me to save and reattach before the gate.
+Every later role reads its named library files first and tops up its own domain;
+flag stale or wrong claims to Researcher and pause affected decisions.
+Use checklists.md to record evidence for the current stage.
+Research current claims before relying on them; cite the opened source and date.
+Extract the user's brand or request their profile-picture and banner screenshots.
+Show three visual design directions and wait for a named selection before site code.
+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.
+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
+its learning and dated research; save and reopen handoffs, including self-handoffs.
+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.
+```
+
+## Upload these files from one revision
+
+- [method.md](../docs/bundles/method.md)
+- [prompts.md](../docs/bundles/prompts.md)
+- [playbooks.md](../docs/bundles/playbooks.md)
+- [checklists.md](../docs/bundles/checklists.md)
+- [team.md](../docs/bundles/team.md)
+
+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
+
+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.
+Read the [method](../docs/METHOD.md), [compatibility](../docs/COMPATIBILITY.md) and [installer contract](../docs/INSTALLER.md).

package/adapters/grok.md

@@ -0,0 +1,100 @@
+# Grok
+
+Status: UNVERIFIED. No Bot importer or automatic team creator is supplied.
+
+- 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.
+- 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.
+
+```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.
+```
+
+## Manual fallback
+
+**Prepare the files and workspace**
+
+- 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.
+
+**Create these seven Bots in this exact order**
+
+1. **Website Researcher.** Click **New**, name it `Website Researcher`, paste the full `roles/researcher.md` body from the team bundle, and save. Supply the active website research prompt and inactive graphics original. Check search, URL/repository reads, viewing, and project file persistence. This Bot gets the first work assignment.
+2. **Website Coordinator.** Click **New**, name it `Website Coordinator`, paste the full `roles/coordinator.md` body, and save. Give it the other six Bot names and actual routes, the handoff contract below, and the instruction to wait for Researcher's passing receipt.
+3. **Website Designer.** Click **New**, name it `Website Designer`, paste `roles/designer.md` in full, and save. Check whether it can receive/view images and produce visual mockups. It waits for research acceptance and the scope-to-designer handoff.
+4. **Website Graphics.** Click **New**, name it `Website Graphics`, paste `roles/graphics.md` in full, and save. Record available image/export tools and existing authorized tiers. It waits for research acceptance, then works with Designer on assets and rights.
+5. **Website Builder.** Click **New**, name it `Website Builder`, paste `roles/builder.md` in full, and save. Check code/file/browser tools and authorized implementation access. It waits for accepted research and the user's named mockup selection before choosing a stack or coding.
+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**
+
+- 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.
+- Give Coordinator this complete contract after replacing each angle-bracket route with the real saved Bot/chat reference. Unresolved placeholders keep setup incomplete.
+
+```text
+You are Website Coordinator for Website Design. Website Researcher is agent one
+and owns the shared research library. Do not begin work until its passing research
+receipt arrives. Your first job then is to read its files and validate that gate.
+
+Routes:
+Website Researcher: <actual Researcher route>
+Website Designer: <actual Designer route>
+Website Graphics: <actual Graphics route>
+Website Builder: <actual Builder route>
+Website Optimizer: <actual Optimizer route>
+Website Reviewer: <actual Reviewer route>
+Your Coordinator route: <actual Coordinator route>
+Project workspace: <chosen private project workspace>
+
+Record actual routes, families, tools, and ownership after research acceptance.
+Do not infer family or permissions from a Bot name. Keep one writer per artifact.
+Researcher alone writes site-work/research/library/. Every other role reads its
+named library files first, learns the domain checklists, and tops up its own domain.
+Send stale or wrong claims back to Researcher; pause affected work for correction.
+The research gate requires saved files for all touched domains and an opened source
+URL, publication/update date or explicit unknown, and access date on or after the ASK DATE for every claim we will act on. UNVERIFIED placeholders cannot pass.
+Then confirm my brief and send scope-to-designer and scope-to-graphics. Require my
+named mockup selection before selected-design-to-builder. Send scope-to-optimizer
+with Builder's route/content inputs. Send the fixed final candidate to Reviewer
+only after pre-review gates pass. Different-family review remains mandatory.
+Read every returned artifact. Preserve Reviewer returns unchanged. Use every field
+in templates/handoff.yaml and record gate acceptance only in site-work/status.md.
+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:
+
+```text
+Begin user-request-to-researcher. You are the first working agent.
+My site request: <paste the actual audience, main action, pages, and known constraints>
+My authorized project workspace: <chosen workspace>
+Supplied materials: <attach any existing brief, brand materials, or source links>
+Use your full role and prompts/01-website-deep-research.md to cover all thirteen
+research domains current as of the ASK DATE. Ask for only missing inputs needed to research.
+Write the grouped library, README headlines, per-domain checklists, source/date and
+disagreement ledgers, surprises, memory proposal/receipt, and staleness schedule.
+If you cannot search, say so, provide query-plan.md and unresolved-claims.md, and
+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.
+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.
+- 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

@@ -0,0 +1,49 @@
+# Hermes
+
+Status: UNVERIFIED. Native loading, project trust, team packaging and shared discovery need live trials.
+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.
+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`.
+
+## Two planned branches
+
+| Branch | Required evidence | Output contract |
+| --- | --- | --- |
+| 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.
+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.
+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.
+
+## Shared core and receipt
+
+Codex and Hermes candidate paths overlap. Compare content before writing and preserve conflicts.
+Test installation in both orders, partial receipts and reference ownership before supporting shared uninstall.
+An explicit bundle directory authorizes only that destination. Never write a home-directory alias implicitly.
+The receipt enumerates core files, setup packets, alias, hashes, mode and pending activation.
+
+## Settling checks
+
+Verify project trust before/after explicit authorization, native preload, all manifest assets and both session routes.
+Verify seven acknowledgements, source-preserving relay, no downstream work before research and denied Reviewer writes.
+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
+
+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.
+Read the [method](../docs/METHOD.md), [compatibility](../docs/COMPATIBILITY.md) and [installer contract](../docs/INSTALLER.md).

package/adapters/team.yaml

@@ -0,0 +1,42 @@
+schema_version: 1
+team: website-design-team
+coordinator: coordinator
+entry_role: researcher
+execution_order: [researcher, coordinator, designer, graphics, builder, optimizer, reviewer]
+artifact_root: site-work
+rules:
+  - one-writer-per-artifact
+  - ask-date-rule-before-intake-and-research
+  - research-gate-before-design
+  - each-role-researches-before-execution
+  - no-site-code-before-selected-mockup
+  - failed-gates-stop-dependent-work
+  - reviewer-family-differs-from-builder-family
+roles:
+  researcher:
+    instructions: roles/researcher.md
+    owns: [research/library, handoffs/researcher]
+  coordinator:
+    instructions: roles/coordinator.md
+    owns: [brief.md, capabilities.md, status.md, team.md, ownership.yaml, MEMORY.md, research/coordinator, handoffs/coordinator, review]
+  designer:
+    instructions: roles/designer.md
+    owns: [brand, mockups, research/designer, handoffs/designer]
+  graphics:
+    instructions: roles/graphics.md
+    owns: [graphics, research/graphics, handoffs/graphics]
+  builder:
+    instructions: roles/builder.md
+    owns: [stack.md, build, qa/build, qa/site-audit.md, qa/accessibility.md, qa/contrast.md, qa/security-headers.md, audit, release, research/builder, handoffs/builder]
+    external_owns: [implementation_root, implementation_root/SITE_OPERATIONS.md]
+  optimizer:
+    instructions: roles/optimizer.md
+    owns: [optimization, qa/seo-aeo.md, research/optimizer, handoffs/optimizer]
+  reviewer:
+    instructions: roles/reviewer.md
+    owns: []
+    authors: [research-packet, findings.md, handoff.yaml]
+    output_delivery: return-to-coordinator
+    source_access: read-only
+handoff:
+  required: [stage, status, input_revision, artifact_revision, producer_role, producer_model_family, artifacts, checks, limitations, next_owner, changed_assumptions, framing_reset]