website-build-skill 0.1.0 → 0.1.1

package/llms.txt

@@ -1,65 +1,72 @@
 # website-build-skill
 
-> Research-first website instructions, role boundaries and evidence gates.
+> A skill pack that turns your AI into an expert website builder. It teaches your LLM or agent current, researched practice in design, brand, accessibility, performance, search, security, stacks and code, so the sites it builds look and work like a professional made them.
 
-Generated from skills/website-build-skill/manifest.json. Published at https://github.com/aunysillyme/website-build-skill. Host loading is UNVERIFIED.
+Generated from skills/website-build-skill/manifest.json. Repository: https://github.com/aunysillyme/website-build-skill.
+
+## Start here
+
+- [Quick start](README.md#quick-start): run `npx website-build-skill` or paste the starter into your AI
+- [Installer](docs/INSTALLER.md): headless setup, destinations, receipts, exit codes and uninstall
+- [Compatibility](docs/COMPATIBILITY.md): host setup routes and the evidence for each
+- [Documentation](docs/README.md): method, tips, provenance and evaluation
 
 ## Active sources
 
-- [SKILL.md](skills/website-build-skill/SKILL.md): entrypoint
+- [SKILL.md](skills/website-build-skill/SKILL.md): Website Build Skill
 - [manifest.json](skills/website-build-skill/manifest.json): manifest
-- [prompts/00-start.md](skills/website-build-skill/prompts/00-start.md): prompt
-- [prompts/01-website-deep-research.md](skills/website-build-skill/prompts/01-website-deep-research.md): prompt
-- [prompts/03-extract-brand-kit.md](skills/website-build-skill/prompts/03-extract-brand-kit.md): prompt
-- [prompts/04-three-mockups.md](skills/website-build-skill/prompts/04-three-mockups.md): prompt
-- [prompts/05-stack-and-build.md](skills/website-build-skill/prompts/05-stack-and-build.md): prompt
-- [prompts/06-site-audit.md](skills/website-build-skill/prompts/06-site-audit.md): prompt
-- [prompts/07-accessibility-contrast.md](skills/website-build-skill/prompts/07-accessibility-contrast.md): prompt
-- [prompts/08-seo-aeo.md](skills/website-build-skill/prompts/08-seo-aeo.md): prompt
-- [prompts/09-security-headers.md](skills/website-build-skill/prompts/09-security-headers.md): prompt
-- [prompts/10-adversarial-pre-ship.md](skills/website-build-skill/prompts/10-adversarial-pre-ship.md): prompt
-- [prompts/11-ship-and-verify.md](skills/website-build-skill/prompts/11-ship-and-verify.md): prompt
-- [prompts/12-web-design-team.md](skills/website-build-skill/prompts/12-web-design-team.md): prompt
-- [roles/researcher.md](skills/website-build-skill/roles/researcher.md): role
-- [roles/coordinator.md](skills/website-build-skill/roles/coordinator.md): role
-- [roles/designer.md](skills/website-build-skill/roles/designer.md): role
-- [roles/graphics.md](skills/website-build-skill/roles/graphics.md): role
-- [roles/builder.md](skills/website-build-skill/roles/builder.md): role
-- [roles/optimizer.md](skills/website-build-skill/roles/optimizer.md): role
-- [roles/reviewer.md](skills/website-build-skill/roles/reviewer.md): role
-- [playbooks/choose-stack.md](skills/website-build-skill/playbooks/choose-stack.md): playbook
-- [playbooks/data-and-templates.md](skills/website-build-skill/playbooks/data-and-templates.md): playbook
-- [playbooks/image-pipeline.md](skills/website-build-skill/playbooks/image-pipeline.md): playbook
-- [playbooks/self-hosted-fonts.md](skills/website-build-skill/playbooks/self-hosted-fonts.md): playbook
-- [playbooks/embed-facades.md](skills/website-build-skill/playbooks/embed-facades.md): playbook
-- [playbooks/security-headers.md](skills/website-build-skill/playbooks/security-headers.md): playbook
-- [playbooks/structured-data-and-llms.md](skills/website-build-skill/playbooks/structured-data-and-llms.md): playbook
-- [playbooks/performance-budgets.md](skills/website-build-skill/playbooks/performance-budgets.md): playbook
-- [playbooks/accessibility.md](skills/website-build-skill/playbooks/accessibility.md): playbook
-- [playbooks/research-and-memory.md](skills/website-build-skill/playbooks/research-and-memory.md): playbook
-- [playbooks/deploy-and-operate.md](skills/website-build-skill/playbooks/deploy-and-operate.md): playbook
-- [checklists/research.md](skills/website-build-skill/checklists/research.md): checklist
-- [checklists/brand-and-mockups.md](skills/website-build-skill/checklists/brand-and-mockups.md): checklist
-- [checklists/build.md](skills/website-build-skill/checklists/build.md): checklist
-- [checklists/accessibility.md](skills/website-build-skill/checklists/accessibility.md): checklist
-- [checklists/performance-seo.md](skills/website-build-skill/checklists/performance-seo.md): checklist
-- [checklists/security.md](skills/website-build-skill/checklists/security.md): checklist
-- [checklists/ship.md](skills/website-build-skill/checklists/ship.md): checklist
-- [references/stacks/static-html.md](skills/website-build-skill/references/stacks/static-html.md): reference
-- [references/stacks/scripted-static.md](skills/website-build-skill/references/stacks/scripted-static.md): reference
-- [references/stacks/framework.md](skills/website-build-skill/references/stacks/framework.md): reference
-- [templates/install-choice.txt](skills/website-build-skill/templates/install-choice.txt): template
-- [templates/brief.md](skills/website-build-skill/templates/brief.md): template
-- [templates/brand.md](skills/website-build-skill/templates/brand.md): template
-- [templates/tokens.json](skills/website-build-skill/templates/tokens.json): template
-- [templates/evidence.md](skills/website-build-skill/templates/evidence.md): template
-- [templates/handoff.yaml](skills/website-build-skill/templates/handoff.yaml): template
-- [templates/audit-brief.md](skills/website-build-skill/templates/audit-brief.md): template
-- [templates/site-operations.md](skills/website-build-skill/templates/site-operations.md): template
-- [templates/status.md](skills/website-build-skill/templates/status.md): template
-- [examples/fictional-studio-brief.md](skills/website-build-skill/examples/fictional-studio-brief.md): example
-- [examples/fictional-studio-handoff.md](skills/website-build-skill/examples/fictional-studio-handoff.md): example
-- [examples/audit-cases.md](skills/website-build-skill/examples/audit-cases.md): example
+- [prompts/00-start.md](skills/website-build-skill/prompts/00-start.md): Help me build a website using Research. Learn. Ingest. Execute: Match. Mock. Build. Pro...
+- [prompts/01-website-deep-research.md](skills/website-build-skill/prompts/01-website-deep-research.md): Deep Research prompt to make your agent good at building websites:
+- [prompts/03-extract-brand-kit.md](skills/website-build-skill/prompts/03-extract-brand-kit.md): Turn my approved materials into a brand kit that a website builder can use and test.
+- [prompts/04-three-mockups.md](skills/website-build-skill/prompts/04-three-mockups.md): Show me three visual mockups for this website before writing any website code.
+- [prompts/05-stack-and-build.md](skills/website-build-skill/prompts/05-stack-and-build.md): Build the selected design using the smallest stack that meets the approved brief.
+- [prompts/06-site-audit.md](skills/website-build-skill/prompts/06-site-audit.md): Audit this website against the current brief, learned design research, and brand kit.
+- [prompts/07-accessibility-contrast.md](skills/website-build-skill/prompts/07-accessibility-contrast.md): Audit accessibility on the built site, with WCAG 2.2 AA as the stated baseline target.
+- [prompts/08-seo-aeo.md](skills/website-build-skill/prompts/08-seo-aeo.md): Research and implement discoverability for this site's actual audience and content.
+- [prompts/09-security-headers.md](skills/website-build-skill/prompts/09-security-headers.md): Configure security headers for the real host and built site, then verify their behavior.
+- [prompts/10-adversarial-pre-ship.md](skills/website-build-skill/prompts/10-adversarial-pre-ship.md): Run one independent adversarial audit of this fixed release candidate.
+- [prompts/11-ship-and-verify.md](skills/website-build-skill/prompts/11-ship-and-verify.md): Ship the checked website only within the release authorization already on record.
+- [prompts/12-web-design-team.md](skills/website-build-skill/prompts/12-web-design-team.md): Run option 2, Give me the team, using the human's recorded install choice.
+- [roles/researcher.md](skills/website-build-skill/roles/researcher.md): You are Website Researcher, agent one, accountable for the team's current full-stack re...
+- [roles/coordinator.md](skills/website-build-skill/roles/coordinator.md): You are Website Coordinator, accountable for scope, stage state, gates, and integration...
+- [roles/designer.md](skills/website-build-skill/roles/designer.md): You are Website Designer, accountable for the brand system and three usable visual dire...
+- [roles/graphics.md](skills/website-build-skill/roles/graphics.md): You are Website Graphics, accountable for usable image assets, exports, and rights evid...
+- [roles/builder.md](skills/website-build-skill/roles/builder.md): You are Website Builder, accountable for implementation, performance, headers, and veri...
+- [roles/optimizer.md](skills/website-build-skill/roles/optimizer.md): You are Website Optimizer, accountable for truthful SEO/AEO inputs and measured discove...
+- [roles/reviewer.md](skills/website-build-skill/roles/reviewer.md): You are Website Reviewer, accountable for the last independent adversarial gate before...
+- [playbooks/choose-stack.md](skills/website-build-skill/playbooks/choose-stack.md): Choose the smallest stack
+- [playbooks/data-and-templates.md](skills/website-build-skill/playbooks/data-and-templates.md): Make repeated pages data changes
+- [playbooks/image-pipeline.md](skills/website-build-skill/playbooks/image-pipeline.md): Deliver images for their actual slots
+- [playbooks/self-hosted-fonts.md](skills/website-build-skill/playbooks/self-hosted-fonts.md): Serve licensed fonts from the site
+- [playbooks/embed-facades.md](skills/website-build-skill/playbooks/embed-facades.md): Load providers after deliberate activation
+- [playbooks/security-headers.md](skills/website-build-skill/playbooks/security-headers.md): Tailor headers to the real response
+- [playbooks/structured-data-and-llms.md](skills/website-build-skill/playbooks/structured-data-and-llms.md): Keep discovery content truthful
+- [playbooks/performance-budgets.md](skills/website-build-skill/playbooks/performance-budgets.md): Measure the experience against explicit budgets
+- [playbooks/accessibility.md](skills/website-build-skill/playbooks/accessibility.md): Test whether people can complete the task
+- [playbooks/research-and-memory.md](skills/website-build-skill/playbooks/research-and-memory.md): Research and memory
+- [playbooks/deploy-and-operate.md](skills/website-build-skill/playbooks/deploy-and-operate.md): Promote an exact, operable release
+- [checklists/research.md](skills/website-build-skill/checklists/research.md): Research gate
+- [checklists/brand-and-mockups.md](skills/website-build-skill/checklists/brand-and-mockups.md): Brand and three-mockup gate
+- [checklists/build.md](skills/website-build-skill/checklists/build.md): Build gate
+- [checklists/accessibility.md](skills/website-build-skill/checklists/accessibility.md): Accessibility gate
+- [checklists/performance-seo.md](skills/website-build-skill/checklists/performance-seo.md): Performance and discovery gate
+- [checklists/security.md](skills/website-build-skill/checklists/security.md): Security gate
+- [checklists/ship.md](skills/website-build-skill/checklists/ship.md): Ship gate
+- [references/stacks/static-html.md](skills/website-build-skill/references/stacks/static-html.md): Static HTML recipe
+- [references/stacks/scripted-static.md](skills/website-build-skill/references/stacks/scripted-static.md): Scripted static recipe
+- [references/stacks/framework.md](skills/website-build-skill/references/stacks/framework.md): Framework recipe
+- [templates/install-choice.txt](skills/website-build-skill/templates/install-choice.txt): How do you want to work?
+- [templates/brief.md](skills/website-build-skill/templates/brief.md): Website brief
+- [templates/brand.md](skills/website-build-skill/templates/brand.md): Brand rules
+- [templates/tokens.json](skills/website-build-skill/templates/tokens.json): Synthetic starting values for mapping primitive and semantic roles, not an approved brand.
+- [templates/evidence.md](skills/website-build-skill/templates/evidence.md): Claim and source evidence contract
+- [templates/handoff.yaml](skills/website-build-skill/templates/handoff.yaml): Package-owned transport contract, not a native vendor import format.
+- [templates/audit-brief.md](skills/website-build-skill/templates/audit-brief.md): Independent audit brief
+- [templates/site-operations.md](skills/website-build-skill/templates/site-operations.md): Site operations
+- [templates/status.md](skills/website-build-skill/templates/status.md): Website stage status
+- [examples/fictional-studio-brief.md](skills/website-build-skill/examples/fictional-studio-brief.md): Fictional Studio: paper workshop website
+- [examples/fictional-studio-handoff.md](skills/website-build-skill/examples/fictional-studio-handoff.md): Fictional Studio: research-to-design handoff walkthrough
+- [examples/audit-cases.md](skills/website-build-skill/examples/audit-cases.md): Synthetic audit cases
 
 ## Bundles
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "website-build-skill",
-  "version": "0.1.0",
-  "description": "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.",
+  "version": "0.1.1",
+  "description": "Skills that make your AI an expert website builder: current research, design, accessibility, performance, SEO, security and code, for any LLM or agent.",
   "type": "module",
   "license": "MIT",
   "bin": {
@@ -16,24 +16,24 @@
   },
   "keywords": [
     "agent-skills",
-    "website-builder",
+    "ai-skills",
+    "llm-skills",
+    "claude-skills",
+    "skill-pack",
     "web-design",
     "web-development",
     "claude-code",
     "codex",
-    "hermes-agent",
-    "antigravity",
-    "grok",
     "chatgpt",
-    "claude-desktop",
+    "grok",
+    "antigravity",
     "multi-agent",
-    "prompt-engineering",
-    "design-systems",
-    "brand-design",
     "accessibility",
     "web-performance",
     "seo",
     "aeo",
+    "design-systems",
+    "brand-design",
     "research-workflow"
   ],
   "scripts": {

package/skills/website-build-skill/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: website-build-skill
-description: Research, design, build, audit, and prepare websites for release. Use for a new website, redesign, or whole-site review, including brand extraction and three visual mockups before site code. For a small isolated fix, load only the relevant audit or playbook.
+description: "Current website-building expertise for an AI: research, design, code, accessibility, performance, search and security. Research, design, build, audit, and prepare websites for release. Use for a new website, redesign, or whole-site review, including brand extraction and three visual mockups before site code. For a small isolated fix, load only the relevant audit or playbook."
 ---
 
 # Website Build Skill
@@ -15,7 +15,7 @@ How do you want to work?
                           Needs Claude Code, Codex, Hermes, Antigravity, or Grok Bot.
                           One command installs their files; you open each session yourself.
 
-Not sure? Pick 1. Moving to 2 later costs you nothing you have already done.
+Not sure? Pick 1. Moving to 2 later keeps everything you have already done.
 
 Where should the work be saved?
 
@@ -110,15 +110,16 @@ An INTERNAL critique cannot pass independence or a completed ship checklist.
 Reproduce findings, record ROUND 1 dispositions, and test fixes without an automatic second audit.
 Keep all project content and generated output outside the installed method directory.
 
-## Missing capabilities and support status
+## Working with the tools you have
 
-Use the complete missing-capability table in playbooks/research-and-memory.md.
+Use the complete tool table in playbooks/research-and-memory.md.
 Return named artifacts and exact settling checks for unavailable tools.
-No images means the mockup gate remains incomplete; no execution means untested code.
+Complete the mockup gate with inspected images and mark code tested after execution.
 A saved-file claim requires a successful write and read-back; memory needs its own receipt.
-No deployment access yields an operator handoff, not a released site.
-Native loading, installation, automated team creation, permissions and host integrations
-are UNVERIFIED until a recorded test proves them on the chosen surface.
-The install question describes the intended setup; definitions do not start workers
-or supply an independent model provider. Portable role prose is not a permission boundary.
-
+Hand deployment to an authorized operator when deploy access is unavailable.
+Check the chosen host's loading, installation, team creation, permissions and integrations
+with a recorded trial. See the repository's docs/COMPATIBILITY.md for host evidence.
+After installation, open the role sessions and provide a different model family for
+independent review. Enforce permissions through the host's own controls.
+Role text guides behaviour; real permissions come from the host's own settings and
+tools. Definitions start no workers and supply no second model provider.

package/skills/website-build-skill/checklists/research.md

@@ -18,15 +18,25 @@ Date rule: [ASK DATE, source evidence, and revalidation](../playbooks/research-a
 
 ## 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. |
 
@@ -46,10 +56,15 @@ 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

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

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "packageVersion": "0.1.0",
+  "packageVersion": "0.1.1",
   "skillName": "website-build-skill",
   "pathBase": "All asset paths resolve from this manifest directory; runtime paths resolve in the authorized user project.",
   "assets": [
@@ -17,7 +17,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "a9778cb747ebf96c8283bd4d814037b74df77e9256166159cbf39be6c05ef91c"
+      "sha256": "14083527283bb68e11a073776e48aa758514e934064ec24e0f83d131549eec76"
     },
     {
       "path": "manifest.json",
@@ -45,7 +45,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "a505d4678267dbace9bbd38eb8ed35f4ce46cfb13318317aa521df7a733c750b"
+      "sha256": "f9be73afb8f0e7746f2e24db5131270ab6cbf7cf3e7636473b51962a679bdfe3"
     },
     {
       "path": "prompts/01-website-deep-research.md",
@@ -60,7 +60,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "233b0834ecd4a0c47f7d300c6e0f57c896a92b6c10899d985a676e246452c8b1"
+      "sha256": "3577554da4ddf2be09783e72a45fc84d39d79673b414408eee7a16c57efdb7c4"
     },
     {
       "path": "archive/graphics-design-original.md",
@@ -240,7 +240,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "b03951027d4c51cfcba27ea2245b635a3e254b912639f13e58a3002df65c6005"
+      "sha256": "245b0ee036e2c73619bab2c3b7585cf7b1cc7c5f9b7364dcd48a613ff2d1be78"
     },
     {
       "path": "roles/coordinator.md",
@@ -255,7 +255,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "8278f418fe13d8ee6ae554c28a2a3bdfe506952bbdf11b4059d9ba05ae19e0ac"
+      "sha256": "1049ee3d1d85976ed943d767d89814d9d83463707591c3bd0268a8be02f7fdca"
     },
     {
       "path": "roles/designer.md",
@@ -270,7 +270,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "1b416b4adc69b8e0a2f8a5c95249dbcd7fe6631459383d4f01f84f99ba89ed6f"
+      "sha256": "6b5cd29f2bdb3fa04fe09e336f9d4a9a02344b6afba7e8a33537dfd2f90b419a"
     },
     {
       "path": "roles/graphics.md",
@@ -285,7 +285,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "28f306cf62351bc9cd658323ab87fa6499b32d3c2f8bcfded67ec1c2502cb433"
+      "sha256": "7804f45877b93885c7b58767b2827f11164bd9a05728ef8f20db3a4c08e42428"
     },
     {
       "path": "roles/builder.md",
@@ -300,7 +300,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "391e2a89a6e9fe42a9481a6e9bef2f8254fb71fdc3c038fa82cc1a0894d04d9f"
+      "sha256": "7f7e957e65e2cff0d73baf6fd4dff5eb9468d451dbde792ddf4d5c143c6909b1"
     },
     {
       "path": "roles/optimizer.md",
@@ -315,7 +315,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "ae6f7dd1c9695c3f2b599ae04a6c32a84a5a3ea7489bac4463252fb6e0fe0470"
+      "sha256": "8ce2c1a4059f774df089a3716bc3e117e455e79aaeebb2021d394710bda981fb"
     },
     {
       "path": "roles/reviewer.md",
@@ -330,7 +330,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "a912bb208a4759c70709fad92442fc4af094104d33d1a68556b30ba1d9161a05"
+      "sha256": "85e8355c2b7996ec1304024db3760ff489f3fdfbc1f962e9d54649b647eae599"
     },
     {
       "path": "playbooks/choose-stack.md",
@@ -482,7 +482,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "3bf9c16c76d8741b27926eff45c122dbc75c1e8d470a99d751e799ab5714a3f2"
+      "sha256": "9ff5f322e6f80b8bf9d1daa39e9416933fa7c6b911c27a0b1a134e2714ba434b"
     },
     {
       "path": "playbooks/deploy-and-operate.md",
@@ -512,7 +512,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "4fa0f64ed012aa15aad274f7be330bcdcc676c069f660e1095f57984d557837e"
+      "sha256": "2bfc2be84723071e21dbcaa0eb607d5f08ef944b0eecc712f1ea16f95118c2a8"
     },
     {
       "path": "checklists/brand-and-mockups.md",
@@ -617,7 +617,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "30279786edb49ebdf4fd1116d326071f3fa84c25cc5575433f723150ca209ea8"
+      "sha256": "75f57202b34466534effc4f05918e51c9073b15c57e7d1c765426f68db4cfa25"
     },
     {
       "path": "references/stacks/scripted-static.md",
@@ -632,7 +632,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "c45a7f8f32254e3be4933be90ca729bbfabdde9c203db81ce4cff24fc40795ca"
+      "sha256": "277eb746a20d8185cc5e07cdd10702f85e68a3f6172dbf04b2b20b415a77cf9f"
     },
     {
       "path": "references/stacks/framework.md",
@@ -647,7 +647,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "1f8b528af930748a2d68d4cdd290ad9413a8e5ad05466d8a9b9f67bc9e099fc3"
+      "sha256": "059ed2167912c80787fcc72cceb14ec8bea2c991056f95e03c7be4f25dab30cc"
     },
     {
       "path": "templates/install-choice.txt",
@@ -662,7 +662,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "86e729beecba45c1e08da6e3aa91c4e968fa86a08c1f3a27873bb29c56415a9e"
+      "sha256": "d90a9274f6f34126a5a8816f9ba3905b7f38435ccf2296b446ec67962ce0b518"
     },
     {
       "path": "templates/brief.md",
@@ -722,7 +722,7 @@
         "skill-zip",
         "native-skill"
       ],
-      "sha256": "c29019ab6e1294c74c66642297da95eafb61c6c5e2b2e19fde449d354213017f"
+      "sha256": "9bb043eb71a2f9f1c8b293efa91bb1b5b844db91456571cab01e6e2f6bd60f9f"
     },
     {
       "path": "templates/handoff.yaml",

package/skills/website-build-skill/playbooks/research-and-memory.md

@@ -193,14 +193,20 @@ milliseconds in fetched_at use three digits before Z. If the environment cannot
 supply a UTC timestamp, leave that claim UNVERIFIED; never invent precision.
 An existing qualified ASK DATE does not authorize a fabricated fetch timestamp.
 
-**Check before reliance.** Run `website-build-skill check-library <root>/site-work`
-when a shell exists. From a repository checkout the equivalent is
-`node bin/website-build-skill.mjs check-library <site-work-dir>`. Save the exact
-command, exit code and output with the research gate evidence. Exit 0 means
+**Check before reliance.** Use this checker ladder:
+
+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 research gate evidence. Exit 0 means
 receipt consistency, not proof that a passage is true or supports a decision;
 exit 2 reports problems, one per line. The checker lists UNVERIFIED rows even
 when it exits 0. Any acted-on UNVERIFIED claim keeps research acceptance BLOCKED.
-Without a shell, Reviewer records the same five checks in
+For rung 4, Reviewer records the same five checks in
 checklists/research.md by hand. Independent AD09 re-fetching remains required.
 
 Example: a provider's paid-tier export right needs the exact tier's current terms,
@@ -352,26 +358,25 @@ Reopen the received files at the next session and run the prior-library or resum
 freshness procedure as appropriate. Missing disk persistence still blocks research.
 Optional memory being unsupported does not invalidate a verified disk library.
 
-## Missing-capability table
-
-| Missing capability | Still works | Cannot honestly complete | Recovery artifact |
-| --- | --- | --- | --- |
-| Web search | Request clarification, supplied-source review, query planning. | Current-to-ASK-DATE research or revalidation, including a prior library; gate stays BLOCKED. | `query-plan.md`, `unresolved-claims.md`, and BLOCKED receipt. |
-| URL retrieval | Pasted/uploaded core method. | Raw-URL bootstrap and unopened-source citations. | Self-contained bundles from the human. |
-| File writing | Draft prompts, specifications, named file bodies. | Saved disk research or a claimed local install. | Downloadable files or copyable labeled blocks. |
-| Persistent memory | Current-session workflow and project documents. | Automatic durable memory across future sessions. | `MEMORY.md` proposal plus explicit save/reattach steps. |
-| Image generation/viewing | Brief and wireframe planning. | Three inspected visual mockups and visual approval. | Designer handoff with required assets and criteria. |
-| Code execution/browser | Draft implementation and test plan. | Measured contrast, functional tests, lab scores, live QA. | Commands and exact expected evidence for a capable runner. |
-| Separate workers | Sequential SOLO jobs, role learning, and saved self-handoffs. | A claimed TEAM or concurrent worker independence. | SOLO capability receipt and role-boundary packets. |
-| Independent model family | Internal critique and review packet. | Independent adversarial gate. | AUDIT_BRIEF plus immutable artifact for another family. |
-| Deploy access | Reviewable local/preview artifact where available. | Production release and live verification. | Operations doc and authorized operator handoff. |
-
-
-Capability gaps accumulate. One working tool cannot stand in for another.
-A URL reader is not a browser, image inspector, response-header reader, or calculator.
-An installed role definition is not a worker, tool permission, or different model family.
-Actual host loading, orchestration, isolation, memory, and deployment support are
-UNVERIFIED until tested in that session. Record the probe and result separately.
+## Working with the tools you have
+
+| Tool | What it enables | Next step when it is absent |
+| --- | --- | --- |
+| Web search | Current-to-ASK-DATE research and revalidation, including a prior library. | Clarify the request, review supplied sources and plan queries. Return `query-plan.md`, `unresolved-claims.md`, and a BLOCKED receipt; current research resumes with web evidence. |
+| URL retrieval | Raw-URL bootstrap and opened-source citations. | Use a pasted or uploaded core method and ask the human for self-contained bundles. Cite sources after opening them. |
+| File writing | Saved disk research and a local install confirmed by read-back. | Draft prompts, specifications and named file bodies. Return downloadable files or copyable labeled blocks for saving and read-back. |
+| Persistent memory | Durable memory across future sessions. | Continue the current-session workflow and project documents. Return a `MEMORY.md` proposal plus explicit save/reattach steps. |
+| Image generation/viewing | Three inspected visual mockups and visual approval. | Plan the brief and wireframes. Return a Designer handoff with required assets and criteria; complete visual approval after inspecting the images. |
+| Code execution/browser | Measured contrast, functional tests, lab scores and live QA. | Draft implementation and a test plan. Return commands and exact expected evidence for a capable runner; record measured results after execution. |
+| Separate workers | TEAM jobs and concurrent workers with verified independence. | Run sequential SOLO jobs, role learning and saved self-handoffs. Return a SOLO capability receipt and role-boundary packets. |
+| Independent model family | The independent adversarial gate. | Run an internal critique and prepare a review packet. Return AUDIT_BRIEF plus an immutable artifact for another family; that review completes the independent gate. |
+| Deploy access | Production release and live verification. | Prepare a reviewable local/preview artifact where available. Return an operations doc and authorized operator handoff for release and live checks. |
+
+Check each tool separately. A working URL reader still needs separate browser,
+image inspection, response-header and calculator checks. After installing role
+definitions, verify running workers, tool permissions and the actual model families.
+Record a session probe and result for host loading, orchestration, isolation,
+memory and deployment before relying on each capability.
 
 ## Verify and hand off
 

package/skills/website-build-skill/prompts/00-start.md

@@ -43,7 +43,7 @@ SOLO PATH
 SAME GATES
 Both paths hit the same gates. Solo work does not lower a threshold or waive a
 missing check. An INTERNAL review leaves independence unmet and release blocked.
-Read the missing-capability table in playbooks/research-and-memory.md.
+Read the Working with the tools you have table in playbooks/research-and-memory.md.
 
 FIRST
 - Tell me which of these you can actually use: search, URL reading, image viewing,
@@ -72,8 +72,15 @@ SAVE
   OPENED from memory or a search snippet. Without a receipt it is UNVERIFIED;
   an acted-on UNVERIFIED claim keeps research acceptance BLOCKED.
 - Complete prompts/01-website-deep-research.md and its library before any other role.
-  Record `website-build-skill check-library <root>/site-work` command, exit code
-  and output, or Reviewer's five-rule manual equivalent when no shell exists.
+  Use this checker ladder; the five-rule manual equivalent is in checklists/research.md:
+
+  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.
+
 - After its gate passes, Coordinator confirms brief.md, capabilities.md, and status.md
   under site-work/. If file tools are missing, return named bodies for me to save
   and reattach; wait for saved library read-back before any design work.

package/skills/website-build-skill/prompts/01-website-deep-research.md

@@ -204,11 +204,17 @@ B. Your memory: propose durable rules and the library location, then save throug
 RESEARCH GATE
 Apply checklists/research.md AD01 through AD08 and the canonical ASK DATE rule;
 record allowed rung/raw evidence, two-date claim coverage, matching openers,
-earliest expiry and per-claim reuse decisions. Run
-`website-build-skill check-library <root>/site-work` and save command, exit code
-and output; PASS needs exit 0. Without a shell record Reviewer's five-rule manual
-equivalent from checklists/research.md. Zero exit does not release acted-on
-UNVERIFIED claims: they keep research acceptance BLOCKED. Independent AD09 runs
+earliest expiry and per-claim reuse decisions. Use this checker ladder; the
+five-rule manual equivalent is in checklists/research.md:
+
+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.
+
+Independent AD09 runs
 before ship with live re-fetches of the required acted-on source sample.
 The library exists on disk, every domain this project touches has a substantive
 file and checklist, and every claim that will be acted on carries an opened source

package/skills/website-build-skill/references/stacks/framework.md

@@ -62,7 +62,7 @@ Keep client work small; add it for actual interaction rather than all page conte
 - Release: freeze a candidate, obtain different-family read-only review, reproduce findings,
   verify fixes, then promote the checked artifact within existing authorization.
 
-## Limits and exit
+## When to move to a bigger stack
 
 More runtime means more dependency, patching, secret, and operational responsibility.
 Record the upgrade cadence, watchers, failure recipient, and tested recovery commands.

package/skills/website-build-skill/references/stacks/scripted-static.md

@@ -62,7 +62,7 @@ Keep adverse cases for quotes, script terminators, unsafe schemes, empty IDs,
 duplicate slugs, missing assets, long copy, and publication boundaries.
 Apply checklists/build.md and the remaining QA/security/ship gates.
 
-## Limits and exit
+## When to move to a bigger stack
 
 A generated page changes only when rebuilt and promoted.
 A browser interaction cannot keep a private server credential.

package/skills/website-build-skill/references/stacks/static-html.md

@@ -58,7 +58,7 @@ When repeated structure or metadata requires recurring copy/edit work, revisit t
 scripted-static recipe before duplicating a growing set of pages.
 Record how shared navigation and discovery files remain consistent in the interim.
 
-## Limits and exit
+## When to move to a bigger stack
 
 Browser JavaScript cannot safely store server secrets or enforce private authorization.
 Use a separately justified endpoint or reconsider the framework branch for server state.