medsci-skills 5.26.2 → 5.27.0

package/THIRD-PARTY-NOTICES.md

@@ -47,7 +47,7 @@ long time after the 2025 versions had replaced them.
 
 ### Citation styles (`skills/manage-refs/citation_styles/*.csl`)
 
-15 CSL files from the Citation Style Language project: **CC BY-SA 3.0**, unmodified, each retaining
+27 CSL files from the Citation Style Language project: **CC BY-SA 3.0**, unmodified, each retaining
 its own `<rights>` element. See `skills/manage-refs/NOTICE.md`.
 
 ### Not bundled — download these yourself

package/metadata/distribution_files.json

@@ -14,7 +14,7 @@
     {
       "path": "THIRD-PARTY-NOTICES.md",
       "size": 3430,
-      "sha256": "40a64f857160a35c82cb8a0bdb2243c0c18521f586330fd481e3cebdba044ba4"
+      "sha256": "ed487bcd00c30da4b9d01a51132d71d7b4cc0245722ed02b2a2d1152e919a9a4"
     },
     {
       "path": "installers/check-setup-macos.command",
@@ -183,8 +183,8 @@
     },
     {
       "path": "skills/analyze-stats/SKILL.md",
-      "size": 59999,
-      "sha256": "62fec491713bd24d0c44d87280a39bc52a6dc439fa0fb2004d80d4c6f8dea3ef"
+      "size": 60456,
+      "sha256": "c541c8811b918bb5b5cb380297a52659b4bda88537841574dc1272a8f7918aa8"
     },
     {
       "path": "skills/analyze-stats/references/analysis_guides/agreement_reliability.md",
@@ -276,6 +276,11 @@
       "size": 3439,
       "sha256": "105476a719db4d728dece0c03e620c322597e1ce56afa8a685782075d2f5bad1"
     },
+    {
+      "path": "skills/analyze-stats/references/analysis_run_workflow.md",
+      "size": 7675,
+      "sha256": "9b6c18cad4a5171ae17c70b87b1cca35c21500734889b04254e1141ab3f87c59"
+    },
     {
       "path": "skills/analyze-stats/references/style/figure_style.mplstyle",
       "size": 1438,
@@ -383,8 +388,8 @@
     },
     {
       "path": "skills/analyze-stats/references/templates/diagnostic_accuracy.py",
-      "size": 14943,
-      "sha256": "25caa62a5a4d1635cee9b2248d729d817697c32290674726c65421aa8d159abc"
+      "size": 14976,
+      "sha256": "5931adbc672332a7b1f1d1f10fa79ccde9d4c38ac67b8c253b01733543ac3f32"
     },
     {
       "path": "skills/analyze-stats/references/templates/dta_meta_analysis.R",
@@ -441,6 +446,16 @@
       "size": 10244,
       "sha256": "752ca6383ce0b11974436a8fc7a41209fe6a2caab4c630e5ae096271bf324329"
     },
+    {
+      "path": "skills/analyze-stats/scripts/analysis_run_challenge/README.md",
+      "size": 761,
+      "sha256": "13ce9ddeacf6c4ec38469976f62ee79c2c4e9bf30fac5440296ca147927c73fa"
+    },
+    {
+      "path": "skills/analyze-stats/scripts/analysis_run_challenge/verify.sh",
+      "size": 1555,
+      "sha256": "ee75660797507253fd8b6f75c109cad95c1637ad81c3a644356592883ab071ff"
+    },
     {
       "path": "skills/analyze-stats/scripts/check_generated_code.py",
       "size": 15064,
@@ -451,15 +466,25 @@
       "size": 11399,
       "sha256": "92dbe9eca972bf1800954ac9b95c52e93f94b2c5d33b57dd1cad378a6b69f356"
     },
+    {
+      "path": "skills/analyze-stats/scripts/demo_analysis_run.py",
+      "size": 2086,
+      "sha256": "93eee505392f44919ad472b31ecfffd06179f7eac2b1daed4f98b0fc84ae2bf2"
+    },
     {
       "path": "skills/analyze-stats/scripts/rating_monotonicity.py",
       "size": 5494,
       "sha256": "b7f8f36c7af060e2dec60f51185ef4cc5a0f2ef20c1d509fb845b36521f420b3"
     },
+    {
+      "path": "skills/analyze-stats/scripts/run_analysis.py",
+      "size": 17834,
+      "sha256": "9eaaabe34689ab6ec6a65ced1afff5c6162d2c9ed21108dd2336ee19503547da"
+    },
     {
       "path": "skills/analyze-stats/skill.yml",
-      "size": 1421,
-      "sha256": "912c52e9289a7ccb014aa8a18105b6dfe04c2cc040e970c73b4bbc6b2d8a8a39"
+      "size": 1798,
+      "sha256": "eb88eddff554dcfd5ee3ba59a82f523c128b02bbc38affaf149c673b51fbc582"
     },
     {
       "path": "skills/architecture-zoo/SKILL.md",
@@ -628,8 +653,8 @@
     },
     {
       "path": "skills/check-reporting/SKILL.md",
-      "size": 43221,
-      "sha256": "7ea44b9b6c93e4215324dc153e6febb8595c973ba96c4cf40db56a0d255036d0"
+      "size": 42940,
+      "sha256": "7e4c0a30554f8f3cdfec03c1cb3fea5c336d4616891d4448930895d2cd1aff71"
     },
     {
       "path": "skills/check-reporting/references/LICENSES.md",
@@ -853,8 +878,8 @@
     },
     {
       "path": "skills/check-reporting/references/checklists/STARD_AI.md",
-      "size": 14508,
-      "sha256": "61c6f9cb217ae842c9e2e4c35f144f82b4735e533847bf9f00426cccd1c120c6"
+      "size": 17076,
+      "sha256": "ddffd822d214ff765e148827b634c5ee0cb363bf7d3be3dda2824f3eed815567"
     },
     {
       "path": "skills/check-reporting/references/checklists/STROBE.md",
@@ -1163,8 +1188,8 @@
     },
     {
       "path": "skills/design-study/SKILL.md",
-      "size": 18884,
-      "sha256": "46269424deac0a1ebcbbc6b4cfc5c19cd8fc1368e90c7edb2d435f531214f2d0"
+      "size": 18603,
+      "sha256": "392181a1d425341380be95e482b712048edb22d9a454316358b59d2c29ab5086"
     },
     {
       "path": "skills/design-study/references/combine_models_ablation_design.md",
@@ -1313,8 +1338,8 @@
     },
     {
       "path": "skills/fill-protocol/SKILL.md",
-      "size": 11570,
-      "sha256": "848b3711a0d1df4c7687fe0ffa102cf153bb8b7ff7e957bffb47b8aa3c219c3f"
+      "size": 11289,
+      "sha256": "64880365203bc95d6b950f17a593f5c6eace147cbc2b9f2eb68568381b66f037"
     },
     {
       "path": "skills/fill-protocol/examples/example_irb_template.yaml",
@@ -1353,8 +1378,8 @@
     },
     {
       "path": "skills/find-cohort-gap/SKILL.md",
-      "size": 16508,
-      "sha256": "5a8f96af2b3f44853231fb677efb9ab92395fcfab1d58283ebe24fba0656a8c1"
+      "size": 16227,
+      "sha256": "acb5f91afb84010a744c0171f189819bff9f8d22c0c6d4e49d3b5c8cad06e6da"
     },
     {
       "path": "skills/find-cohort-gap/references/cohort_profile_template.md",
@@ -1898,8 +1923,8 @@
     },
     {
       "path": "skills/grant-builder/SKILL.md",
-      "size": 7420,
-      "sha256": "33b7848d79f9268ac7f8c35d12441c19b104c7abafa4a22d616cd94b8f5bf8b7"
+      "size": 7139,
+      "sha256": "b4b6d5d042941412b07dab327a97d1ecc83464b20a584a00263297bef7723054"
     },
     {
       "path": "skills/grant-builder/skill.yml",
@@ -1988,8 +2013,8 @@
     },
     {
       "path": "skills/make-figures/SKILL.md",
-      "size": 48072,
-      "sha256": "e343de9c90b9d36dae85a580305daa6cb769f67e0f8484f2db0365b64f2e37ad"
+      "size": 48325,
+      "sha256": "66f08bb072fc011c5d2c9124a8e9edc399c8dacfeaf48501a9a5f651e1869316"
     },
     {
       "path": "skills/make-figures/references/critic_rubrics/data_plot.md",
@@ -2173,8 +2198,8 @@
     },
     {
       "path": "skills/make-figures/references/exemplar_plots/README.md",
-      "size": 8751,
-      "sha256": "824baf7dbcc820909e2d812bcb021a09af5f592dad2958a2f3be779881546504"
+      "size": 10492,
+      "sha256": "8840d2b36492f10afc4f17340903c8c052fa78f0966a3379d401996830c41f70"
     },
     {
       "path": "skills/make-figures/references/exemplar_plots/ai_assistance_effect.md",
@@ -2201,6 +2226,11 @@
       "size": 3416,
       "sha256": "d35c31d357ff3e4d60666cdfed499eae9126dcb676b3493709ba5eb5442f18bf"
     },
+    {
+      "path": "skills/make-figures/references/exemplar_plots/cumulative_incidence.md",
+      "size": 3496,
+      "sha256": "57e306d5452d991ed849d339ed71209d975217588b4bd9b6099ce159f3d53563"
+    },
     {
       "path": "skills/make-figures/references/exemplar_plots/decision_curve.md",
       "size": 3973,
@@ -2251,6 +2281,21 @@
       "size": 4581,
       "sha256": "9bedf2f0b762702b1b9f794d6e83abc512a0bd504101ac27133558074a788b04"
     },
+    {
+      "path": "skills/make-figures/references/exemplar_plots/spider_plot.md",
+      "size": 3114,
+      "sha256": "c57f59fa6f99e7add76c1bed0f57576c21ec2fb10cf3b6d673405343f5057f42"
+    },
+    {
+      "path": "skills/make-figures/references/exemplar_plots/swimmer_plot.md",
+      "size": 3239,
+      "sha256": "a239eb48e8c4910af337165a87973d6015172037c22a2e81340e35e23396b42d"
+    },
+    {
+      "path": "skills/make-figures/references/exemplar_plots/waterfall_plot.md",
+      "size": 3519,
+      "sha256": "fb03cca0d6a2bc20ced3ed04d7ebe31a8b081014fa35452c4a305df568693a9a"
+    },
     {
       "path": "skills/make-figures/references/figure_manifest.md",
       "size": 2215,
@@ -2523,8 +2568,13 @@
     },
     {
       "path": "skills/manage-refs/citation_styles/README.md",
-      "size": 4358,
-      "sha256": "b8935886559c1491a8aa06f8f809f82a492bfc0fceb4b32f2fbc19ccc379e83f"
+      "size": 6979,
+      "sha256": "c08122700197e0f91614cbd92f848e196c2c259b7e753d8cefa9ff4009b63b74"
+    },
+    {
+      "path": "skills/manage-refs/citation_styles/american-association-for-cancer-research.csl",
+      "size": 8011,
+      "sha256": "b7bdbe6892121701bce476cf9a72bee4eb785417cf7e007af6455160fe085683"
     },
     {
       "path": "skills/manage-refs/citation_styles/american-journal-of-roentgenology.csl",
@@ -2536,21 +2586,56 @@
       "size": 11575,
       "sha256": "d70f843d93c2b1e8c59c0e26e2396bea4ed99fb4a1aac69b6dddc249a10fadf7"
     },
+    {
+      "path": "skills/manage-refs/citation_styles/annals-of-oncology.csl",
+      "size": 10478,
+      "sha256": "abf48f4b1eff63b9a85f16b3ec3d65db394279ee160a7a958d917a0ba025b5da"
+    },
+    {
+      "path": "skills/manage-refs/citation_styles/breast-cancer-research-and-treatment.csl",
+      "size": 1270,
+      "sha256": "572bea8275f786315bbe4c81227301970d56f18eee6a5b2cf809679f2273284e"
+    },
     {
       "path": "skills/manage-refs/citation_styles/cardiovascular-and-interventional-radiology.csl",
       "size": 1299,
       "sha256": "46fdf5c9a281f95295387f781fe0e50f796b4e7af1006e64a2771602e1fcc1a5"
     },
+    {
+      "path": "skills/manage-refs/citation_styles/clinical-breast-cancer.csl",
+      "size": 832,
+      "sha256": "3fdc07b8c914974a208ed68ca3885de792a1f8cd317ad6c17ef3c7bfd7a480f1"
+    },
+    {
+      "path": "skills/manage-refs/citation_styles/clinical-cancer-research.csl",
+      "size": 1036,
+      "sha256": "e5c9c968cc530d5566837b27ed00ea4469a849ea4c1f905a032f18d716f511f6"
+    },
+    {
+      "path": "skills/manage-refs/citation_styles/elsevier-vancouver.csl",
+      "size": 5802,
+      "sha256": "005e915c3419eb2b84eb2b31bffc411dce3890619d3fd0ed23ac6591ac128335"
+    },
     {
       "path": "skills/manage-refs/citation_styles/european-radiology.csl",
       "size": 1203,
       "sha256": "10b3d7ca195b76ae846bff001ed33c20867b69a255e8ac222ca6838c8c4e031f"
     },
+    {
+      "path": "skills/manage-refs/citation_styles/journal-of-breast-cancer.csl",
+      "size": 8137,
+      "sha256": "9b0f1503f2d3d2949dc3a2421d7c4b756cd1e78fe98bd1bd74d7e5ddee057a93"
+    },
     {
       "path": "skills/manage-refs/citation_styles/journal-of-cachexia-sarcopenia-and-muscle.csl",
       "size": 5377,
       "sha256": "b8eb85b4b75617e4677f7a9b84221f1df9fd07acb90b510c0c71b02d3fd2e9a6"
     },
+    {
+      "path": "skills/manage-refs/citation_styles/journal-of-clinical-oncology.csl",
+      "size": 4836,
+      "sha256": "43b3d78a2698adb5834bd1f5b42eef4a754912b994757fc54d506f33bc86c542"
+    },
     {
       "path": "skills/manage-refs/citation_styles/journal-of-korean-medical-science-strict.csl",
       "size": 18145,
@@ -2596,6 +2681,21 @@
       "size": 9191,
       "sha256": "9caa8271cbad8cd64b47986a3531d049f53e09d21285b970272519febebfe47a"
     },
+    {
+      "path": "skills/manage-refs/citation_styles/the-breast.csl",
+      "size": 786,
+      "sha256": "2415acd647b8ba1aaf76d3804d9a3ef15a0f077fa4fce039d5cd695c87772511"
+    },
+    {
+      "path": "skills/manage-refs/citation_styles/the-lancet-oncology.csl",
+      "size": 882,
+      "sha256": "d7e5e9194425e336291a3b5b11cd4c2f7fccddfb3934f874245782752796ae62"
+    },
+    {
+      "path": "skills/manage-refs/citation_styles/the-lancet.csl",
+      "size": 6410,
+      "sha256": "327b4f4b08765ddc05a68cbaa1fe898442da9f0e669b0eae279cd75f631c412b"
+    },
     {
       "path": "skills/manage-refs/citation_styles/vancouver-superscript.csl",
       "size": 18299,
@@ -3838,8 +3938,8 @@
     },
     {
       "path": "skills/present-paper/SKILL.md",
-      "size": 54313,
-      "sha256": "f57f6bfcfdf4a016defcce34732e264c7ac11258f825e1244c681d0d6a52db5d"
+      "size": 54032,
+      "sha256": "768f1e4a044f3ca2a0861e82a6c787eb1bc7d7dd29840c182760cfd2ebdf45ac"
     },
     {
       "path": "skills/present-paper/references/ai_slide_tells.md",
@@ -4283,8 +4383,8 @@
     },
     {
       "path": "skills/revise/SKILL.md",
-      "size": 32212,
-      "sha256": "4733786ab5f53316d041ec8ec721ad05a41c9e0366856d1622189ba3132984c2"
+      "size": 31931,
+      "sha256": "3f4224b166a6f48ea77b1edc83deb742160a2933683c4822ce0dd1bf391359de"
     },
     {
       "path": "skills/revise/references/r2r_voice.md",
@@ -4433,8 +4533,8 @@
     },
     {
       "path": "skills/self-review/SKILL.md",
-      "size": 62648,
-      "sha256": "00453644f66011fd1994ac456d25e81ca6f52dd615668d34c6f92b5d004583cb"
+      "size": 62367,
+      "sha256": "69f70f778ebf5422e2e9daa876209440de518efa83881906d78d8842d41900fb"
     },
     {
       "path": "skills/self-review/references/domain-probes/ai_overclaiming.md",
@@ -5478,8 +5578,18 @@
     },
     {
       "path": "skills/sync-submission/SKILL.md",
-      "size": 40790,
-      "sha256": "45b228823952b028f0ec8160cd3e457f95b37a0a8fe692a09349a49d1e91054a"
+      "size": 41988,
+      "sha256": "f7b831bc599966f0b9e2fbcb78b7802d19ea05d3c066ace673a67604ea91e24c"
+    },
+    {
+      "path": "skills/sync-submission/examples/build_synthetic_bundle.py",
+      "size": 3690,
+      "sha256": "35ec00892fcc1f188784c1113ec107dde40f6b859693d975f4e88b6219b604a9"
+    },
+    {
+      "path": "skills/sync-submission/references/bundle_workflow.md",
+      "size": 7344,
+      "sha256": "d4295e169cea53b79a93458a937f8c4ffaa544951907de02758426aee9ab8c78"
     },
     {
       "path": "skills/sync-submission/references/journal_availability_policy.json",
@@ -5703,8 +5813,8 @@
     },
     {
       "path": "skills/sync-submission/scripts/preflight_gate.py",
-      "size": 27400,
-      "sha256": "958e18e4ca4f48390a68c6c7407d341f396bc6673f9c8d918a7a51b72d000a7e"
+      "size": 29080,
+      "sha256": "af5688aa499b6890270d1367260d1460f180a9f57decbdc3542c74c24e4fdf8e"
     },
     {
       "path": "skills/sync-submission/scripts/scope_drift_check.py",
@@ -5713,13 +5823,13 @@
     },
     {
       "path": "skills/sync-submission/scripts/sync_submission.py",
-      "size": 6439,
-      "sha256": "dc6f6a81e846bc218a37e2d655659a02fa38bd738a42036cc8854d7e1ea32308"
+      "size": 21796,
+      "sha256": "c6c0adaf9f58357f3f8241c71ac7b47e72a4d56a06156f5e310bc1bc6f964c23"
     },
     {
       "path": "skills/sync-submission/skill.yml",
-      "size": 2309,
-      "sha256": "f291953988db61d64ee9f4649971236d5474e3b71e4b92fad8987cdf81a82daf"
+      "size": 2736,
+      "sha256": "ed880953ab130995994e371baa5347cffe8c79bef21a0fa1f4fd48f115b03acf"
     },
     {
       "path": "skills/uncertainty-imaging/SKILL.md",
@@ -5773,14 +5883,24 @@
     },
     {
       "path": "skills/verify-refs/SKILL.md",
-      "size": 13883,
-      "sha256": "783cf8b9fb181cb1d0ae05770f8ed6732f4e834decd58b8eb2431ed72acd9e05"
+      "size": 15318,
+      "sha256": "09d8f8899feb9f89aedd92225bfe2cca9be9a24e841f1edbead9aaffd3e28e8f"
+    },
+    {
+      "path": "skills/verify-refs/references/claim_evidence_workflow.md",
+      "size": 6466,
+      "sha256": "20765c9c23122fef6c44eea6327d29a79c73929cf710800addab5f9b1ff29468"
     },
     {
       "path": "skills/verify-refs/references/manual_checkpoint_guide.md",
       "size": 4031,
       "sha256": "4da6bd649d672bcae7505098d4712d6fb253fea8fa3be41c95870587cc6553a4"
     },
+    {
+      "path": "skills/verify-refs/scripts/_claim_evidence.py",
+      "size": 13992,
+      "sha256": "4b471cb1f6c20c09746af5b7f51093b4f4cc5be7ff2ab972285158b797abd2ca"
+    },
     {
       "path": "skills/verify-refs/scripts/_quote_match.py",
       "size": 7904,
@@ -5788,8 +5908,8 @@
     },
     {
       "path": "skills/verify-refs/scripts/check_claim_fidelity.py",
-      "size": 28138,
-      "sha256": "e90932f24c794c35ed525ac578e51658599bf7bef2b0efee32d4e75be82f7c3c"
+      "size": 33348,
+      "sha256": "a654a537e6cc00c62ecaa1edcf4ee8bc137d77eeb3d40ddc2ff616059ac85480"
     },
     {
       "path": "skills/verify-refs/scripts/claim_fidelity_challenge/fixture/fulltext/10.1000_synthetic.oversight.md",
@@ -5828,8 +5948,8 @@
     },
     {
       "path": "skills/verify-refs/scripts/claim_fidelity_challenge/verify.sh",
-      "size": 9306,
-      "sha256": "19bec2649a74ff92d7f58913b70d04716d8e7838ba075d905dabb0b0697f92ff"
+      "size": 8835,
+      "sha256": "8553470dcbaa3890b5964762ac6c3c87656752e44c56a96438b2a234b3e1fe97"
     },
     {
       "path": "skills/verify-refs/scripts/verify_cli.sh",
@@ -5843,8 +5963,8 @@
     },
     {
       "path": "skills/verify-refs/skill.yml",
-      "size": 3092,
-      "sha256": "54b90d79ba5eec1d8d1776e08c7740c7b9d461c9fc5a6c32f1cf24ce71c3d9ac"
+      "size": 3422,
+      "sha256": "f96396276ad8cfb10b0c671d3813033105dc2e8894be3dbbf40c8e7451d93686"
     },
     {
       "path": "skills/version-dataset/SKILL.md",
@@ -5868,8 +5988,8 @@
     },
     {
       "path": "skills/write-paper/SKILL.md",
-      "size": 50120,
-      "sha256": "6ac3072d67dfabfaeae11a0bf1890e9d616d073cd56b0758669d3b3f4ff59c50"
+      "size": 49839,
+      "sha256": "88280152ff13b89402b4dd7a1490245b274795d0b1acb2e96edab1a275164c00"
     },
     {
       "path": "skills/write-paper/references/exemplar_abstract.md",
@@ -6398,8 +6518,8 @@
     },
     {
       "path": "skills/write-protocol/SKILL.md",
-      "size": 11580,
-      "sha256": "3d2041be27da4aa32c648ae4eba6036fdcb99a648ab003721ccfaf7c93bd2c06"
+      "size": 11299,
+      "sha256": "8548d8bbebe14aacf9acab19ee3c895259022552fcef11ac7fbd8dadd778db88"
     },
     {
       "path": "skills/write-protocol/references/ethics_checklist.md",

package/metadata/distribution_manifest.json

@@ -1,6 +1,6 @@
 {
   "schema_version": 1,
-  "version": "5.26.2",
+  "version": "5.27.0",
   "owned_skills": [
     "academic-aio",
     "add-journal",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "medsci-skills",
-  "version": "5.26.2",
+  "version": "5.27.0",
   "description": "MedSci Skills — a medical/scientific research skill suite for AI coding agents (Claude Code, Codex, Cursor, Copilot). The npm package is a terminal-friendly installer shortcut; the canonical distribution remains the GitHub repository and the Claude Code plugin marketplace.",
   "license": "SEE LICENSE IN LICENSE",
   "homepage": "https://github.com/Aperivue/medsci-skills#readme",

package/skills/analyze-stats/SKILL.md

@@ -169,26 +169,23 @@ Before running parametric tests, always check and report:
 
 #### Output Manifest
 
-After all analyses complete, save a manifest file `_analysis_outputs.md` in the output directory:
-
-```markdown
-# Analysis Outputs
-Generated: {YYYY-MM-DD}
-Study type: {detected or user-specified type}
-
-## Tables
-- `table1_demographics.csv` -- Baseline characteristics
-- `diagnostic_accuracy_table.csv` -- Performance metrics with 95% CIs
-
-## Figures  
-- `roc_curve.pdf` / `roc_curve.png` -- ROC curves (vector / 300 DPI)
-
-## Data
-- `predictions.csv` -- Per-subject model predictions with ground truth
-```
+After all analyses complete, save `_analysis_outputs.md` in the output directory.
+Use the [output format and bound binary workflow](references/analysis_run_workflow.md)
+when producing the analysis outputs.
 
 This manifest enables downstream skills (`/make-figures`, `/write-paper`) to auto-discover analysis outputs without user intervention.
 
+For **prespecified binary predictions on independent units**, use the bundled
+`scripts/run_analysis.py run` workflow described in
+[`references/analysis_run_workflow.md`](references/analysis_run_workflow.md).
+It executes the existing diagnostic template and embeds data/configuration/code/
+output hashes, exact counts, metric-specific denominators and the reproduction
+command in this same manifest. `audit` checks recorded versions without rewriting
+them; `compare` separates declared context and recorded numeric equality from byte
+drift. It does not select thresholds or establish study validity, privacy clearance
+or reuse rights. The original synthetic example runs with
+`python3 ${CLAUDE_SKILL_DIR}/scripts/demo_analysis_run.py --out demo-project`.
+
 ### Phase 3.5: Generated-Code Quality Gate
 
 Before reporting any script as final, lint every emitted `.py`/`.R` file for the