website-build-skill 0.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (109) hide show
  1. package/.claude-plugin/marketplace.json +12 -0
  2. package/.claude-plugin/plugin.json +10 -0
  3. package/AGENTS.md +19 -0
  4. package/CHANGELOG.md +42 -0
  5. package/CLAUDE.md +16 -0
  6. package/CODE_OF_CONDUCT.md +127 -0
  7. package/CONTRIBUTING.md +49 -0
  8. package/LICENSE +21 -0
  9. package/MAINTAINERS.md +12 -0
  10. package/README.md +148 -0
  11. package/RELEASING.md +133 -0
  12. package/REPO_SETTINGS.md +91 -0
  13. package/SECURITY.md +28 -0
  14. package/adapters/agents-md.md +26 -0
  15. package/adapters/antigravity.md +68 -0
  16. package/adapters/chatgpt-project.md +57 -0
  17. package/adapters/claude-code.md +25 -0
  18. package/adapters/claude-desktop.md +33 -0
  19. package/adapters/codex.md +21 -0
  20. package/adapters/custom-gpt.md +57 -0
  21. package/adapters/grok.md +100 -0
  22. package/adapters/hermes.md +49 -0
  23. package/adapters/team.yaml +42 -0
  24. package/adapters/zero-install.md +17 -0
  25. package/bin/website-build-skill.mjs +6 -0
  26. package/docs/COMPATIBILITY.md +34 -0
  27. package/docs/EVALUATION.md +109 -0
  28. package/docs/INSTALLER.md +73 -0
  29. package/docs/LIBRARY-CHECK.md +95 -0
  30. package/docs/METHOD.md +32 -0
  31. package/docs/PROVENANCE.md +36 -0
  32. package/docs/TIPS.md +18 -0
  33. package/docs/bundles/checklists.md +414 -0
  34. package/docs/bundles/method.md +1398 -0
  35. package/docs/bundles/playbooks.md +1566 -0
  36. package/docs/bundles/prompts.md +987 -0
  37. package/docs/bundles/team.md +1781 -0
  38. package/docs/evaluation/host-trial.md +95 -0
  39. package/docs/evaluation/receipt-template.json +18 -0
  40. package/docs/evidence/audit-baseline.json +61 -0
  41. package/docs/evidence/content-review.json +141 -0
  42. package/docs/evidence/floor.json +345 -0
  43. package/docs/evidence/library-check.json +164 -0
  44. package/docs/evidence/local-checks.json +156 -0
  45. package/llms.txt +74 -0
  46. package/package.json +68 -0
  47. package/skills/website-build-skill/SKILL.md +124 -0
  48. package/skills/website-build-skill/archive/graphics-design-original.md +70 -0
  49. package/skills/website-build-skill/checklists/accessibility.md +38 -0
  50. package/skills/website-build-skill/checklists/brand-and-mockups.md +43 -0
  51. package/skills/website-build-skill/checklists/build.md +39 -0
  52. package/skills/website-build-skill/checklists/performance-seo.md +40 -0
  53. package/skills/website-build-skill/checklists/research.md +91 -0
  54. package/skills/website-build-skill/checklists/security.md +38 -0
  55. package/skills/website-build-skill/checklists/ship.md +59 -0
  56. package/skills/website-build-skill/examples/audit-cases.md +66 -0
  57. package/skills/website-build-skill/examples/fictional-studio-brief.md +73 -0
  58. package/skills/website-build-skill/examples/fictional-studio-handoff.md +98 -0
  59. package/skills/website-build-skill/manifest.json +1474 -0
  60. package/skills/website-build-skill/playbooks/accessibility.md +91 -0
  61. package/skills/website-build-skill/playbooks/choose-stack.md +69 -0
  62. package/skills/website-build-skill/playbooks/data-and-templates.md +89 -0
  63. package/skills/website-build-skill/playbooks/deploy-and-operate.md +87 -0
  64. package/skills/website-build-skill/playbooks/embed-facades.md +59 -0
  65. package/skills/website-build-skill/playbooks/image-pipeline.md +73 -0
  66. package/skills/website-build-skill/playbooks/performance-budgets.md +76 -0
  67. package/skills/website-build-skill/playbooks/research-and-memory.md +398 -0
  68. package/skills/website-build-skill/playbooks/security-headers.md +132 -0
  69. package/skills/website-build-skill/playbooks/self-hosted-fonts.md +62 -0
  70. package/skills/website-build-skill/playbooks/structured-data-and-llms.md +84 -0
  71. package/skills/website-build-skill/prompts/00-start.md +94 -0
  72. package/skills/website-build-skill/prompts/01-website-deep-research.md +233 -0
  73. package/skills/website-build-skill/prompts/03-extract-brand-kit.md +46 -0
  74. package/skills/website-build-skill/prompts/04-three-mockups.md +44 -0
  75. package/skills/website-build-skill/prompts/05-stack-and-build.md +46 -0
  76. package/skills/website-build-skill/prompts/06-site-audit.md +39 -0
  77. package/skills/website-build-skill/prompts/07-accessibility-contrast.md +38 -0
  78. package/skills/website-build-skill/prompts/08-seo-aeo.md +72 -0
  79. package/skills/website-build-skill/prompts/09-security-headers.md +40 -0
  80. package/skills/website-build-skill/prompts/10-adversarial-pre-ship.md +44 -0
  81. package/skills/website-build-skill/prompts/11-ship-and-verify.md +44 -0
  82. package/skills/website-build-skill/prompts/12-web-design-team.md +141 -0
  83. package/skills/website-build-skill/references/stacks/framework.md +76 -0
  84. package/skills/website-build-skill/references/stacks/scripted-static.md +76 -0
  85. package/skills/website-build-skill/references/stacks/static-html.md +72 -0
  86. package/skills/website-build-skill/roles/builder.md +139 -0
  87. package/skills/website-build-skill/roles/coordinator.md +132 -0
  88. package/skills/website-build-skill/roles/designer.md +125 -0
  89. package/skills/website-build-skill/roles/graphics.md +126 -0
  90. package/skills/website-build-skill/roles/optimizer.md +129 -0
  91. package/skills/website-build-skill/roles/researcher.md +202 -0
  92. package/skills/website-build-skill/roles/reviewer.md +139 -0
  93. package/skills/website-build-skill/templates/audit-brief.md +63 -0
  94. package/skills/website-build-skill/templates/brand.md +53 -0
  95. package/skills/website-build-skill/templates/brief.md +51 -0
  96. package/skills/website-build-skill/templates/evidence.md +100 -0
  97. package/skills/website-build-skill/templates/handoff.yaml +23 -0
  98. package/skills/website-build-skill/templates/install-choice.txt +28 -0
  99. package/skills/website-build-skill/templates/site-operations.md +71 -0
  100. package/skills/website-build-skill/templates/status.md +47 -0
  101. package/skills/website-build-skill/templates/tokens.json +72 -0
  102. package/src/agents.mjs +7 -0
  103. package/src/bundle.mjs +106 -0
  104. package/src/catalog.mjs +12 -0
  105. package/src/choice.mjs +6 -0
  106. package/src/cli.mjs +96 -0
  107. package/src/install.mjs +344 -0
  108. package/src/library-check.mjs +106 -0
  109. package/src/validate.mjs +351 -0
@@ -0,0 +1,66 @@
1
+ # Synthetic audit cases
2
+
3
+ Date rule: [ASK DATE and evidence discipline](../playbooks/research-and-memory.md#ask-date-rule).
4
+ Everything in this example is invented. It is not a real organization, person, project,
5
+ source-opening receipt, measurement, approval, or deployment.
6
+ Do not import example state as evidence for a live engagement.
7
+
8
+ Use these invented cases to rehearse rejection behavior on a disposable candidate.
9
+ They are test data, not claims that measurements or browser tests have been run.
10
+
11
+ ## Two accents doing one job
12
+
13
+ Input: primary actions use #DA6736 on the home page and #D85F30 on workshop cards.
14
+ Both claim the same action token and no state distinction or approved exception exists.
15
+ Expected finding: token drift with both exact values, roles and locations.
16
+ Reject with brand-and-mockups.md BM02 until source evidence resolves intentionality.
17
+ Do not merge them solely because they look similar.
18
+ Retest: inspect the approved action mapping on every route and in hover/focus states.
19
+
20
+ ## A weak primary action
21
+
22
+ Input: the inquiry action is visually quiet and described as accessible without a ratio.
23
+ Expected finding: contrast is UNVERIFIED; appearance is insufficient evidence.
24
+ Reject with accessibility.md AX01 and brand-and-mockups.md BM03.
25
+ Record actual rendered foreground/background, opacity, font size/weight, criterion,
26
+ calculator or runner, unrounded ratio, and result before proposing a shade or role change.
27
+ No ratio is invented in this example.
28
+ Retest: compute again after the approved correction and complete the real inquiry journey.
29
+
30
+ ## Empty provider identifier
31
+
32
+ Input: a published workshop record has an empty optional demonstration-provider ID.
33
+ Faulty output: a Watch demonstration link whose URL has an empty provider suffix.
34
+ Expected finding: dead control generated from absent optional data.
35
+ Reject with build.md B04, including whitespace-only and malformed-ID variants.
36
+ Correct behavior: keep the workshop content, omit the provider link and player,
37
+ record the omission, and emit no provider request before or after absent-control handling.
38
+ Required provider data would instead fail validation with record/field context.
39
+ Retest: inspect generated HTML, DOM and network requests; verify a valid ID still works.
40
+
41
+ ## Stale metadata after a content change
42
+
43
+ Input: the workshop title changes in its visible record but the social title, sitemap
44
+ location, or llms.txt entry still comes from an independently maintained list.
45
+ Expected finding: source-to-output drift on the identified candidate.
46
+ Reject with performance-seo.md PS06 and build.md B03.
47
+ Correct behavior: derive the public surfaces from the same validated route/content registry.
48
+ Retest: change one synthetic record, rebuild, and inspect initial HTML and discovery output.
49
+ Verify intentional private or draft exclusions remain excluded.
50
+
51
+ ## False completion labels
52
+
53
+ Input: no source was opened, but research is labeled complete.
54
+ Reject with research.md AD07; query plans do not satisfy current research.
55
+ Input: Builder reviews its own work and marks independent review complete.
56
+ Reject with ship.md SH01; record INTERNAL and independent gate NOT MET, ship BLOCKED.
57
+ Retest: require actual source-opening evidence or different-family review as applicable.
58
+ Changing the label cannot repair either missing capability.
59
+
60
+ ## Capture a useful finding
61
+
62
+ Record case, candidate identity, location, preconditions, reproduction action, observed
63
+ result, user impact, confidence, smallest fix and the check proving the fix.
64
+ A pattern match is a lead. A defect claim requires reachable behavior and evidence.
65
+ Builder reproduces returned allegations before fixing or reporting them as confirmed.
66
+ Record ROUND 1 dispositions and before/after regression results without adding an audit loop.
@@ -0,0 +1,73 @@
1
+ # Fictional Studio: paper workshop website
2
+
3
+ Date rule: [ASK DATE and evidence discipline](../playbooks/research-and-memory.md#ask-date-rule).
4
+ Everything in this example is invented. It is not a real organization, person, project,
5
+ source-opening receipt, measurement, approval, or deployment.
6
+ Do not import example state as evidence for a live engagement.
7
+
8
+ ## Confirm the job
9
+
10
+ - Organization: Fictional Studio, an invented paper craft workshop.
11
+ - Audience: adults choosing a small group activity, including first-time visitors.
12
+ - Primary action: send a workshop inquiry with group size and preferred session type.
13
+ - Success event: the intended receiving system confirms one valid inquiry.
14
+ - Draft domain: https://studio.example.invalid, reserved example data, never a live destination.
15
+ - Mode: SOLO for the walkthrough; independent review remains a separate required job.
16
+ - Stage: intake prepared, research BLOCKED until a capable run establishes ASK DATE and source evidence.
17
+
18
+ ## Give each route a purpose
19
+
20
+ | Route | Visitor question | Required content | Action |
21
+ | --- | --- | --- | --- |
22
+ | / | Is this workshop for my group? | Plain offer, example activity, access summary, workshop choices. | Choose a workshop. |
23
+ | /workshops/ | Which activity fits us? | Comparable activity records with duration, materials and accessibility notes to be confirmed. | Read a workshop. |
24
+ | /workshops/folded-landscapes/ | What will we make? | Representative description, making steps, skill assumptions, safe materials and group requirements. | Inquire about this workshop. |
25
+ | /visit/ | Can we get there and take part? | Owner-confirmed access information, transport guidance and arrival process. | Ask an access question. |
26
+ | /inquire/ | How do I request a session? | Group-size and session-type fields, labels, consent text if applicable, errors and confirmation. | Send inquiry. |
27
+ | /404.html | How do I recover? | Clear missing-page explanation and useful navigation. | Return to workshops. |
28
+
29
+ ## Use representative copy
30
+
31
+ Hero: Make a paper landscape together.
32
+ Supporting copy: Choose a guided paper workshop for your group. Compare the activities,
33
+ then tell us what you would like to make and what access support would help.
34
+ Workshop heading: Folded landscapes for a mixed-experience group.
35
+ Workshop description: Build a layered paper scene using folds, simple shapes and texture.
36
+ The facilitator demonstrates each step and offers an alternative for intricate cuts.
37
+ This text is synthetic draft copy; the real owner must confirm any service claim.
38
+
39
+ ## Keep facts and assumptions separate
40
+
41
+ - Supplied fixture facts: the site needs an inquiry journey and repeated workshop pages.
42
+ - Assumption: the same activity record can supply cards, detail pages and discovery metadata.
43
+ - Assumption: a local-poster demonstration may help explain the craft.
44
+ - Missing fact: who receives inquiries and what confirms delivery.
45
+ - Missing fact: actual venue access, activity duration, capacity and asset rights.
46
+ - Missing mandate: production target and release authorization.
47
+ - Date: no runtime ASK DATE is invented by this example; Researcher must establish it.
48
+
49
+ ## Explore brand choices
50
+
51
+ Suggested words: patient, tactile, clear.
52
+ Translate them into readable hierarchy, generous grouping and close-up material images.
53
+ These are proposed interpretations, not approved tokens or a selected design.
54
+ No logo or font files are supplied. Request current guidelines or profile/banner screenshots.
55
+ Compute real contrast after colors and states are chosen.
56
+
57
+ ## Compare three directions before code
58
+
59
+ - Workshop Table: process photos and a clear sequence from selection to inquiry.
60
+ - Paper Gallery: spacious compositions with activity comparisons below the first action.
61
+ - Field Notebook: compact type-led explanations, diagrams and clear access information.
62
+
63
+ These are direction briefs, not completed visual mockups.
64
+ Designer must create and inspect desktop/mobile visuals with the same content,
65
+ then obtain a named user selection before Builder chooses a stack or writes site code.
66
+
67
+ ## Define verification and boundaries
68
+
69
+ Test inquiry validation, keyboard completion, delivery confirmation and recovery.
70
+ Test an absent demonstration-provider ID: omit both player and provider link.
71
+ Test a new workshop record: its route, card, metadata and discovery entries stay aligned.
72
+ Apply all research, rights, design, build, QA, security and independent review gates.
73
+ No accounts, purchases, external submissions or deployment are authorized by this fixture.
@@ -0,0 +1,98 @@
1
+ # Fictional Studio: research-to-design handoff walkthrough
2
+
3
+ Date rule: [ASK DATE and evidence discipline](../playbooks/research-and-memory.md#ask-date-rule).
4
+ Everything in this example is invented. It is not a real organization, person, project,
5
+ source-opening receipt, measurement, approval, or deployment.
6
+ Do not import example state as evidence for a live engagement.
7
+
8
+ ## Inspect the prepared input
9
+
10
+ Read fictional-studio-brief.md for the invented audience, routes and inquiry action.
11
+ The fixture runner has file access but no web access and has not established date provenance.
12
+ This example therefore returns a complete BLOCKED receipt rather than fabricated current research.
13
+ Its package-local files are real readable inputs; runtime library paths below are requested outputs.
14
+
15
+ ## Researcher returns this receipt
16
+
17
+ ```yaml
18
+ stage: research
19
+ status: BLOCKED
20
+ input_revision: fictional-brief-1
21
+ artifact_revision: fictional-research-packet-1
22
+ producer_role: researcher
23
+ producer_model_family: synthetic-runner-no-family-claim
24
+ artifacts:
25
+ - examples/fictional-studio-brief.md
26
+ - examples/fictional-studio-handoff.md
27
+ checks:
28
+ - name: AD01
29
+ result: BLOCKED
30
+ evidence: "No authentic runtime date-source evidence was collected in this invented example."
31
+ - name: AD07
32
+ result: BLOCKED
33
+ evidence: "The fixture runner has no live web access; no sources were opened."
34
+ - name: R01
35
+ result: BLOCKED
36
+ evidence: "No saved runtime library or source-opening receipt is supplied."
37
+ limitations:
38
+ - "No current claims, measurements, memory save, visuals, or deployment are asserted."
39
+ - "Design and implementation must wait for accepted research."
40
+ next_owner: researcher
41
+ changed_assumptions:
42
+ - "A descriptive workshop brief does not establish asset rights or inquiry delivery."
43
+ framing_reset: "Treat draft direction names as questions to explore, not approved designs."
44
+ ```
45
+
46
+ ## Query plan included in the packet
47
+
48
+ - Implementation: inspect real static and scripted sites, revisions, licenses and derived route behavior.
49
+ - Stack: compare repeated workshop publishing and form delivery without choosing a stack yet.
50
+ - Design: inspect award work from the last two to three years relative to the established ASK DATE.
51
+ - Graphics: verify chosen-tool/tier rights, material photo provenance and destination crops.
52
+ - UI/UX: research inquiry, group-size validation, access questions, error recovery and mobile use.
53
+ - Accessibility: verify current criteria and plan contrast, keyboard and assistive journeys.
54
+ - Performance: verify metric definitions and propose repeatable route budgets.
55
+ - SEO: map useful initial HTML, canonical routes, sitemap and metadata from workshop records.
56
+ - AEO: distinguish truthful answer structure from unsupported citation promises.
57
+ - Security: research form inputs, host headers, URL validation and provider-ID omission.
58
+ - Hosting: compare preview, HTTPS, form endpoint, response headers and rollback behavior.
59
+ - Measurement: identify receiving-property proof for a successful inquiry.
60
+ - Legal: verify exact font, image and intended-use rights; keep uncertain questions visible.
61
+
62
+ ## Unresolved claims included in the packet
63
+
64
+ | Claim ID | Unknown | Dependent work | Next evidence action |
65
+ | --- | --- | --- | --- |
66
+ | F-RIGHTS | Permission for workshop photographs and fonts. | Final assets and release. | Obtain original asset/license evidence and open current terms. |
67
+ | F-DELIVERY | Inquiry receiver and confirmation behavior. | Stack decision and functional test. | Confirm owner-approved destination, inspect current integration docs, then test within authority. |
68
+ | F-ACCESS | Venue and activity access facts. | Visit copy and structured data. | Obtain owner-approved facts; do not infer them from imagery. |
69
+ | F-HOST | Host capabilities and response coverage. | Header and release configuration. | Open selected host/version documentation and test an authorized preview. |
70
+
71
+ No source URLs are invented for these unknowns. They remain UNVERIFIED and block reliance.
72
+
73
+ ## Coordinator's acceptance decision
74
+
75
+ Acceptance: BLOCKED. No scope-to-designer or scope-to-graphics work assignment is released.
76
+ Return the packet to Researcher with the missing tool and saved-library requirements.
77
+ Coordinator may inspect the blocked return to explain the failure; it does not start its own
78
+ scope/design stage or issue a false passing receipt.
79
+ Optional memory status: pending proposal only; there is no durable-save claim.
80
+
81
+ ## Complete the research-to-design transition
82
+
83
+ After a capable Researcher establishes date provenance and opens current sources,
84
+ it saves all grouped files, all thirteen checklists, claim ledgers, learning and staleness.
85
+ It reads them back, applies AD01 through AD08 and R01 through R06, and issues a new revision.
86
+ Coordinator reopens those artifacts before recording acceptance.
87
+ Only then does scope-to-designer carry the approved brief, accepted library revision,
88
+ named reading files, applicable checks, asset inputs, ownership and unresolved visual choices.
89
+ Designer records its learning/top-up receipt and creates the three real visual directions.
90
+ The selected direction is a user decision, never a value invented by this walkthrough.
91
+
92
+ ## What carries across a SOLO boundary
93
+
94
+ Preserve the packet and reopen its files in the next role.
95
+ Keep the blocked status, original assumptions and next actions visible.
96
+ Use framing_reset to release attachment to the proposed directions.
97
+ A future team can reuse the same files after freshness checks; worker creation alone
98
+ cannot change the status of this research receipt.