{
  "updated_at": "2026-09-12T10:43:42.721675+00:00",
  "scope": "Selected additional execution and mechanical checks from the full collection. Counts measure checks or answers, never additional skill comparisons. Original failures are retained. No package is activated or approved for its full workflow.",
  "cards": [
    {
      "id": "supplemental-helpers",
      "domain": "SEO",
      "title": "Supplemental search-data helpers",
      "state": "Two inactive package copies",
      "metric": "73 / 73 repaired-helper cases",
      "result": "The original PAA parser and supplemental-file validator pass 27 of 73 cases. Their inactive repairs pass all 73 cases and 341 checks, including quoted multiline CSV, Unicode, missing fields, strict section markers and size limits. Both complete package copies retain the earlier sitemap repair.",
      "limits": "Local synthetic inputs only. These results do not establish current search facts, live crawling, WordPress upload or full plugin operation. Fifteen original companion files remain unchanged. Earlier failures and repair attempts are retained.",
      "source_ids": [
        "llms-amplifier-supplemental--30524c2223",
        "llms-amplifier-supplemental--3a99c65e72"
      ],
      "evidence_sha256": "932a7c03e537912f4ad485cc5f6dd925a381e355e67e1cfa1cf893379f3cb487",
      "evidence_file": "delivery.json",
      "evidence_url": "http://127.0.0.1:8768/full-collection/supplemental-helpers-runtime-2026-09-12/delivery.json",
      "readme_url": "http://127.0.0.1:8768/full-collection/supplemental-helpers-runtime-2026-09-12/README.md"
    },
    {
      "id": "diagram-model-render",
      "domain": "Design",
      "title": "Diagram imports and paired outputs",
      "state": "All 18 fresh requests completed",
      "metric": "7 / 12 generated diagrams pass",
      "result": "Three inactive skill versions received fresh same-provider baselines, guided outputs and independent reviews. All 12 unchanged diagrams were imported and exported in Excalidraw 0.18.1, then visually inspected. Seven pass every local check; five retain connector or layout defects. The suite passes 146 of 156 checks.",
      "limits": "One refund-flowchart fixture only. Requested Astra outputs pass with and without the skill, so these runs do not establish added skill value or general model superiority. Hosted imports, VS Code extensions and other diagram formats remain untested. Earlier root-authored repairs are separate.",
      "source_ids": [
        "diagram-generator--5e1238b48b",
        "diagram-generator--88af44558a",
        "diagram-generator--d5c77c31f0"
      ],
      "evidence_sha256": "b8482e0ec0cbbd2059d37afb9ae1a14800e4f00e6cb5ec90fef87ec38d5083fe",
      "evidence_file": "delivery.json",
      "evidence_url": "http://127.0.0.1:8768/full-collection/diagram-import-runtime-2026-09-12/fresh-model-comparison/delivery.json",
      "readme_url": "http://127.0.0.1:8768/full-collection/diagram-import-runtime-2026-09-12/fresh-model-comparison/README.md"
    },
    {
      "id": "sheets-command-contracts",
      "domain": "Documents",
      "title": "Sheets command construction",
      "state": "Three inactive package copies",
      "metric": "4 / 4 repaired drafts pass local checks",
      "result": "All three source versions and four retained Claude drafts were checked. One original draft passes every local payload check; four separate root-authored copies pass all 51. The isolated gws 0.22.5 CLI accepts 96 of 96 repaired example/draft dry runs. Helper controls expose comma splitting and input-mode defaults.",
      "limits": "No live Sheet or real credentials were used. curl and gcloud were inert capture functions. The four original model drafts cover two versions; the third source was checked but its model comparison remains separate. Repairs do not replace model grades, and successful request previews do not prove live integration.",
      "source_ids": [
        "gws-sheets--7c90119728",
        "gws-sheets--b3c6fef68e",
        "gws-sheets--f186b49ac3"
      ],
      "evidence_sha256": "b1b6dce9a94173d6877e54643b5d9b9923b1f8d7b95601bb97077e05ff791fd3",
      "evidence_file": "delivery.json",
      "evidence_url": "http://127.0.0.1:8768/full-collection/sheets-command-contracts-2026-09-12/delivery.json",
      "readme_url": "http://127.0.0.1:8768/full-collection/sheets-command-contracts-2026-09-12/README.md"
    },
    {
      "id": "ghl-listener",
      "domain": "Marketing",
      "title": "GHL message-listener repair",
      "state": "Two inactive package copies",
      "metric": "32 / 32 repaired browser scenarios",
      "result": "Both source versions and four retained Claude answers were checked. Inactive package and output repairs pass 136 listener cases plus two diagnostic cases, and 32 real browser scenarios. Tests cover duplicate IDs, exact message origins, absent/replaced iframes and preserving the data layer. Originals pass 60 of 138 local cases and 8 of 32 browser scenarios.",
      "limits": "Synthetic forms and messages only: the real GHL payload contract, deployed GTM tags and GA4 collection/key events remain unverified. Browser pages were supplied locally; no external service was loaded. Corrected reviews retract unfair variable and length objections but still fail all four original answers. Root repairs do not inherit model grades.",
      "source_ids": [
        "ghl-conversion-tracking--0b267883e1",
        "ghl-conversion-tracking--f2baefa98a"
      ],
      "evidence_sha256": "520b9992df6103aca82421c272fb1ed71d3f257ba49c4866db510560891ac4dc",
      "evidence_file": "delivery.json",
      "evidence_url": "http://127.0.0.1:8768/full-collection/ghl-listener-runtime-2026-09-12/delivery.json",
      "readme_url": "http://127.0.0.1:8768/full-collection/ghl-listener-runtime-2026-09-12/README.md"
    },
    {
      "id": "sitemap-fetch",
      "domain": "SEO",
      "title": "Sitemap URL discovery repair",
      "state": "Two inactive package copies",
      "metric": "48 / 48 repaired-script cases",
      "result": "The original helper shared by two versions passes 20 of 48 cases. Its inactive repair passes all 48 cases and 383 checks, including 27 real loopback HTTP requests. Checks cover XML namespaces, escaped URLs, metadata exclusion, gzip, recursive indexes and output handling.",
      "limits": "Synthetic files and a local test server only. The first repair still crashed on corrupt compressed data; that failure and the final correction are retained. Page facts, HTTPS/TLS, other supplemental-file scripts and WordPress upload remain unverified. Twenty-one companion files stay unchanged.",
      "source_ids": [
        "llms-amplifier-supplemental--30524c2223",
        "llms-amplifier-supplemental--3a99c65e72"
      ],
      "evidence_sha256": "7903a361537a3ffedde37c68b764a2677794d9f53c993f20f63d9a1039db73e7",
      "evidence_file": "delivery.json",
      "evidence_url": "http://127.0.0.1:8768/full-collection/sitemap-fetch-runtime-2026-09-12/delivery.json",
      "readme_url": "http://127.0.0.1:8768/full-collection/sitemap-fetch-runtime-2026-09-12/README.md"
    },
    {
      "id": "image-exif",
      "domain": "SEO",
      "title": "Image metadata repair",
      "state": "Seven inactive package copies",
      "metric": "45 image cases + 31 follow-up checks",
      "result": "All seven archived EXIF examples fail Python parsing. After restoring indentation, real writes reproduce wrong GPS hemispheres, omitted zero coordinates and joined keywords. The final helper passes 45 JPEG, PNG and WebP cases plus replacement, repeat-write and error checks.",
      "limits": "The 45 cases include 27 real writes and 18 rejected invalid requests. Follow-up checks include 12 real update writes and three injected failure contracts. The full renaming CLI, image analysis, profile storage and MCP integration remain missing or untested. Originals stay unchanged.",
      "source_ids": [
        "seo-image-renamer--107cfcdaab",
        "seo-image-renamer--1e75d66a6b",
        "seo-image-renamer--23f5f7f6a0",
        "seo-image-renamer--56d78a1227",
        "seo-image-renamer--2b3d905db5",
        "seo-image-renamer--deeebfdbb6",
        "seo-image-renamer--5c81ffd762"
      ],
      "evidence_sha256": "f123c7108f6e95ee67d57f4a85a664aa6d304c0c1081ed5fbb053e8985e9daf2",
      "evidence_file": "RESULTS.json",
      "evidence_url": "http://127.0.0.1:8768/full-collection/seo-image-renamer-runtime-2026-09-12/RESULTS.json",
      "readme_url": "http://127.0.0.1:8768/full-collection/seo-image-renamer-runtime-2026-09-12/README.md"
    },
    {
      "id": "html-parser",
      "domain": "SEO",
      "title": "HTML audit parser repair",
      "state": "Six inactive package copies",
      "metric": "114 / 114 repaired-script checks",
      "result": "Searching all 6,209 ledger rows found two distinct parser files across six source versions. Original scripts pass 76 of 114 checks; repaired copies pass all 114. Checks cover URL resolution, readable text, hidden content, JSON-LD syntax and malformed links.",
      "limits": "These are real local CLI checks on synthetic HTML. JavaScript and CSS rendering, live crawling and search eligibility are untested. Seven other seo-audit versions contain no parser. The six repaired packages preserve 77 unchanged companion files.",
      "source_ids": [
        "seo-audit--05624aa96b",
        "seo--705fdf9486",
        "seo--a3e697febe",
        "seo-audit--09106b4627",
        "seo-audit--f7ec1e4277",
        "seo-audit--07cae8c2a7"
      ],
      "evidence_sha256": "3b5eb75390ae2492b9e4c805329c62cf2a4ecd701085a9f4670377f392f06772",
      "evidence_file": "delivery.json",
      "evidence_url": "http://127.0.0.1:8768/full-collection/seo-html-parser-runtime-2026-09-12/delivery.json",
      "readme_url": "http://127.0.0.1:8768/full-collection/seo-html-parser-runtime-2026-09-12/README.md"
    },
    {
      "id": "frontend-animation",
      "domain": "Video",
      "title": "React animation execution",
      "state": "Both original examples pass",
      "metric": "160 / 160 browser checks",
      "result": "Both unchanged Astra hero components ran in real browsers at phone and desktop sizes, in development Strict Mode and production. Eight runs verify animation, no replay, listener removal and cleanup. Four screenshots were inspected.",
      "limits": "Only the supplied hero components ran. Other animation modes, missing implementations, reduced-motion behavior and a complete accessibility audit remain unverified. An initial checker syntax error and 16 incorrect expectations are retained; source components were unchanged.",
      "source_ids": [
        "frontend-animation--95651360ce"
      ],
      "evidence_sha256": "6e7a2f5401d423dd4c2fe98e78b768beda2a5d220f4255206a381977c9a09d42",
      "evidence_file": "delivery.json",
      "evidence_url": "http://127.0.0.1:8768/full-collection/frontend-animation-runtime-2026-09-12/delivery.json",
      "readme_url": "http://127.0.0.1:8768/full-collection/frontend-animation-runtime-2026-09-12/README.md"
    },
    {
      "id": "shared-contracts",
      "domain": "Tests",
      "title": "Nine corrected task contracts",
      "state": "Fresh model pairs reviewed",
      "metric": "18 answers + 152 bounded checks",
      "result": "An audit scanned 831 planned source versions and examined all 84 flagged contracts. Nine confirmed defects received new tasks with complete inputs. Astra generated 18 fresh guided and baseline answers; Claude reviewed every pair. All nine pairs passed their corrected offline cases.",
      "limits": "The 152 checks cover fields, isolated hook inputs and command text. Live media, provider calls, publishing and other named integrations remain untested for all nine versions. Eight extractor controls are separate. Original sources, tasks and failures remain preserved.",
      "source_ids": [
        "video-processor--f8bdd8799f",
        "video-seo-pipeline--e0bb3c7833",
        "infographic-generator--fd4091e5db",
        "claude-code-hooks-mastery--8612b0998a",
        "deepseek-cli--0ce067a52a",
        "deepseek-cli--487992496e",
        "branded-image-from-text--bd3c0bdbdc",
        "rapidapi-youtube--a3a584a2e4",
        "rapidapi-youtube--be7cf8daca"
      ],
      "evidence_sha256": "d297fcc2fdc99efc43608e9a1c688c666cfed50685d45cf51dffdc15e8f680a3",
      "evidence_file": "RESULTS.json",
      "evidence_url": "http://127.0.0.1:8768/deliveries/2026-09-12-shared-contract-evidence/RESULTS.json",
      "readme_url": "http://127.0.0.1:8768/deliveries/2026-09-12-shared-contract-evidence/README.md"
    },
    {
      "id": "pass-scope",
      "domain": "Tests",
      "title": "Offline pass scope corrected",
      "state": "Five integration flags corrected",
      "metric": "21 prior pass labels screened",
      "result": "The audit examined all 21 pass labels at its snapshot. Five versions now explicitly retain missing references or untested operations, including the partial animation example. Original task text, model answers and model verdicts were unchanged.",
      "limits": "This corrects coverage labels, not model grades or implementations. A successful bounded task still does not establish that missing SOPs, external frameworks or live workflows work. No skill was activated.",
      "source_ids": [
        "frontend-animation--95651360ce",
        "tommy-youtube-titles-thumbnails--4b9e5e3ed9",
        "javascript-core-language--db81c17168",
        "content-humanizer--5d4ba76965",
        "ixo-blueprint--b26348067a"
      ],
      "evidence_sha256": "6fc9e91f81de67c2ece229e4e8251490f96abba9832eea898306571dc6cfea46",
      "evidence_file": "RESULTS.json",
      "evidence_url": "http://127.0.0.1:8768/full-collection/bounded-pass-scope-audit-2026-09-12/RESULTS.json",
      "readme_url": "http://127.0.0.1:8768/full-collection/bounded-pass-scope-audit-2026-09-12/README.md"
    },
    {
      "id": "ad-local-regrades",
      "domain": "Tests",
      "title": "Video-ad and campaign regrades",
      "state": "All four answers still fail",
      "metric": "Two fresh independent reviews",
      "result": "Two hidden rubric requirements were removed before Astra regraded four unchanged Claude answers. The local campaign answers contain 409 and 382 words against a fewer-than-350 limit. Both video storyboards add B-roll beyond the requested two scenes.",
      "limits": "These are offline answer comparisons. Unsupported claims and omitted qualifications still fail. Independent word measurements are retained separately from reviewer judgments. No media, account creation or publication was tested; all four unrelated negative requests passed.",
      "source_ids": [
        "ai-video-ad-script--925bb08f48",
        "ghost-local-destroyers-seo--76774e2990"
      ],
      "evidence_sha256": "494486b43f05e8f1858a86e2f1a624e9fd397cf2143a3f3af8cd18a0a520d8f2",
      "evidence_file": "RESULTS.json",
      "evidence_url": "http://127.0.0.1:8768/full-collection/ad-local-campaign-fairness-2026-09-12/RESULTS.json",
      "readme_url": "http://127.0.0.1:8768/full-collection/ad-local-campaign-fairness-2026-09-12/README.md"
    },
    {
      "id": "concat",
      "domain": "Video",
      "title": "Video concatenation",
      "state": "Originals fail; repairs pass",
      "metric": "72 / 72 repair checks",
      "result": "Four original executions failed. A requested nine-second sequence became a 614.546-second container in the completed guided run. Four selected repaired executions preserve all 270 frames and pass timing, audio and clip-order checks.",
      "limits": "Repairs change copies of generated scripts. The original skill remains failed and inactive. Two audio scenarios and this FFmpeg version were checked; arbitrary formats and perceptual audio quality were not.",
      "source_ids": [
        "safe-video-concat-workflow--ac608e02b7"
      ],
      "evidence_sha256": "eecc73257cb23f3de4c9b6700a662eee94f3f3a6f45a051cf4faec46691d80d4",
      "evidence_file": "RESULTS.json",
      "evidence_url": "http://127.0.0.1:8768/full-collection/concat-paired-runtime-2026-09-12/RESULTS.json",
      "readme_url": "http://127.0.0.1:8768/full-collection/concat-paired-runtime-2026-09-12/README.md"
    },
    {
      "id": "ascii",
      "domain": "Video",
      "title": "ASCII animation",
      "state": "Original examples pass",
      "metric": "32 / 32 artifact checks",
      "result": "Both original Astra scripts rendered 15-second, 1920 by 1080 GIFs. FFmpeg and Pillow each decoded all 300 frames of both files. Claude passed both unchanged answers after correcting the rubric.",
      "limits": "This checks the generative GIF example. Eight referenced files are missing; other modes and full package behavior remain unverified.",
      "source_ids": [
        "ascii-video--1ab5bddb35"
      ],
      "evidence_sha256": "d8a7b3fe4be9728156c82ee82c4c22dac08f6a1fe14d2b5a666f3dcd7fc244cd",
      "evidence_file": "RESULTS.json",
      "evidence_url": "http://127.0.0.1:8768/full-collection/ascii-video-runtime-2026-09-12/RESULTS.json",
      "readme_url": "http://127.0.0.1:8768/full-collection/ascii-video-runtime-2026-09-12/README.md"
    },
    {
      "id": "loopjar",
      "domain": "Video",
      "title": "Readable video on phones",
      "state": "Inactive example repair passes",
      "metric": "115 / 115 browser checks",
      "result": "The guided example repair keeps required copy at least 12 pixels across five tested widths, from 320 to 1280 pixels. Each run observes two full 20-second loops and the next opening.",
      "limits": "Playback used a test-owned host simulation. The baseline mobile issue, actual recording hook and exported video remain unverified. The original output is preserved.",
      "source_ids": [
        "video-js--f235d7e1a9"
      ],
      "evidence_sha256": "dd9b9962cb5e286de337805dd15874b5d39365f24b63930c8ff1e4ff401d17ed",
      "evidence_file": "RESULTS.json",
      "evidence_url": "http://127.0.0.1:8768/full-collection/loopjar-mobile-readability-2026-09-11/RESULTS.json",
      "readme_url": "http://127.0.0.1:8768/full-collection/loopjar-mobile-readability-2026-09-11/README.md"
    },
    {
      "id": "harbor",
      "domain": "SEO",
      "title": "Homepage keyboard access",
      "state": "Inactive example repair passes",
      "metric": "38 focus instances checked",
      "result": "Both originals passed 92 homepage checks each. Extra keyboard checks found invisible or obscured focus in the guided output. A three-rule CSS repair passes the same 92 checks and all 38 focus instances.",
      "limits": "One fictional homepage across four widths was checked. Live SEO performance and the complete workflow are unverified. Original content, links and markup are preserved.",
      "source_ids": [
        "local-seo-site-builder--23a6231f68"
      ],
      "evidence_sha256": "ad2d0559d1c8208b35641bbb99778e2a0d8517d8db2ac439e11fd7277afca21f",
      "evidence_file": "RESULTS.json",
      "evidence_url": "http://127.0.0.1:8768/full-collection/harbor-seo-homepage-runtime-2026-09-11/RESULTS.json",
      "readme_url": "http://127.0.0.1:8768/full-collection/harbor-seo-homepage-runtime-2026-09-11/README.md"
    },
    {
      "id": "jsonld",
      "domain": "SEO",
      "title": "Structured data audit",
      "state": "Seven unknown-type rows remain",
      "metric": "1,071 saved answers scanned",
      "result": "The snapshot contains 121 answers with JSON-LD markers: 114 rows use recognized vocabulary; seven retain the unknown ElectricalContractor type. Six selected answers pass 76 task-fact checks.",
      "limits": "This is a pinned-vocabulary and task-fact audit, including restricted interpretation of JSX data. Live URLs, complete JSON-LD semantics and search eligibility were not tested. Repeated rows are not additional skills.",
      "source_ids": [
        "aaron-geo-content-optimizer--56add038c8",
        "auto-schema-from-template--2e985c2a51",
        "auto-schema-from-template--3173409194",
        "auto-schema-from-template--3a0c02c02a",
        "auto-schema-from-template--44909dfde7",
        "auto-schema-from-template--d06cdd037a",
        "entity-seo--28ac398ed0",
        "entity-seo--bb72289c85",
        "full-website-writer--2fdeda8701",
        "full-website-writer--cb4708b312",
        "knowsabout-schema-generator--0a0c22a04a",
        "local-seo-site-builder--23a6231f68",
        "local-seo-site-builder--84b97f7903",
        "long-form-video-seo-2026--5200114ff9",
        "long-form-video-seo-2026--61cc935be8",
        "nextjs-seo-scaffold--5a2ad53a08",
        "schema-generator--09851d14fc",
        "schema-spider--2227b36315",
        "schema-template-library--92a7d86ffb",
        "schema-video-generator--ad85a20f65",
        "video-seo-sop--0cf6763117",
        "video-seo-sop--715da2eaf8"
      ],
      "evidence_sha256": "32605d696ec9a50201f8fa86ed2dda2ef80e1702bc5acca93e347142be764199",
      "evidence_file": "combined-results.json",
      "evidence_url": "http://127.0.0.1:8768/full-collection/jsonld-full-output-audit-2026-09-12/combined-results.json",
      "readme_url": "http://127.0.0.1:8768/full-collection/jsonld-full-output-audit-2026-09-12/README.md"
    },
    {
      "id": "utm",
      "domain": "SEO",
      "title": "Campaign tracking links",
      "state": "Original examples pass",
      "metric": "32 / 32 URL checks",
      "result": "Both retained Astra answers preserve the booking path, service selection and availability fragment. Four external placements use distinct tracking; the internal homepage link stays untagged.",
      "limits": "These are parser checks of two answers. No URL was visited and no analytics or attribution was verified.",
      "source_ids": [
        "utm-tags--ca399d7b72"
      ],
      "evidence_sha256": "c65859bc984c7d7d037ad182c35cdea7b2027cde36a2bd537f176ee65e500cb2",
      "evidence_file": "RESULTS.json",
      "evidence_url": "http://127.0.0.1:8768/full-collection/utm-url-checks-2026-09-12/RESULTS.json",
      "readme_url": "http://127.0.0.1:8768/full-collection/utm-url-checks-2026-09-12/README.md"
    }
  ],
  "concat_sample_href": "/skill-lab/runtime/recent/repaired-concat-guided.mp4"
}