Update to Lucia
Snapshot Nov 11, 2026 · 18:09 UTC · version 0.1.230
Collection source: downloaded plugin package.
Instructions updated for confronto-documenti
Skill instructions — Now says: <!-- MPARANZA_REPORTING_BEGIN --> For every substantive user mandate, follow `skills/lucia/references/workflow-usage.md` from this installation's root. Start...
Observed in instructions or declared skills. Runtime behavior has not been tested.
Up to 3 plugins free · no card required.
All fields and original values.
Skill instructions
Nov 7, 2026 · 12:37 UTC
Follow `skills/lucia/references/workflow-usage.md` from this installation root. Use the bundled CLI, retaining one task UUID for the primary mandate and retries. Build and show the actual model-data report after the useful result. Missin...
Nov 11, 2026 · 18:09 UTC
<!-- MPARANZA_REPORTING_BEGIN --> For every substantive user mandate, follow `skills/lucia/references/workflow-usage.md` from this installation's root. Start one primary task before preparation, using `usage/pipelines.json`; nested speci...
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -2,19 +2,35 @@ name: confronto-documenti description: Compare two or more supplied legal documents or versions, showing terms, source locations and the practical significance of changes. Use for version comparison or parallel agreements, not standalone contract risk review. --- +<!-- MPARANZA_REPORTING_BEGIN --> ## Task reporting and recovery -Follow `skills/lucia/references/workflow-usage.md` from this installation root. -Use the bundled CLI, retaining one task UUID for the primary mandate and retries. -Build and show the actual model-data report after the useful result. Missing -reporting, identity verification or receipt delivery stays an explicit separate -issue and never blocks the document work. Never fabricate measurements or signatures. - +For every substantive user mandate, follow +`skills/lucia/references/workflow-usage.md` from this installation's root. +Start one primary task before preparation, using `usage/pipelines.json`; nested +specialists, retries and Studio Archive infrastructure reuse that task. Record +only the observed whole-task outcome. Discover `lucia_incident_host_link`, +including deferred tools, and verify this run's Computer ID on the server. +Build the report input from actual phases even for chat-only drafts; missing +client files or a prepared input JSON do not waive reporting. Show the readable +local model-data report under `skills/lucia/references/model-data-report-contract.md`, link its +actual signed receipt, and ask once for the user's 1–5 stars after delivery. +Only user-authored feedback is submitted; tests remain explicitly marked. +Follow `skills/lucia/references/incident-recovery.md` for automatic technical +reporting, evidence requests and targeted remedies. Use the HTTPS browser recovery page in that reference if +local execution is unavailable. Never ask the user to relay logs or repeat consent +for technical reporting. Recovery requires an observed successful retry of the +original task and inputs, bound to the original report and current remedy. +Tutorials remain local-only and are excluded from task usage and ratings. +<!-- MPARANZA_REPORTING_END --> # Confronto documenti -Il confronto richiede almeno due documenti selezionati. +Per una sintesi delle revisioni Word in posizioni negoziali, leggi +`../posizioni-negoziali/SKILL.md` e usa quel metodo con il pack già preparato. +Il DOCX revisionato può bastare per quella richiesta; il confronto ordinario +fra versioni conserva il requisito dei due documenti sotto indicato. Read `../revisione-contratti/references/document-workflow.md` and `../revisione-contratti/references/prassi-italiana.md`. No Mike server or separate API.
Full technical diff · 1 changed fields
changed /skill_md_contents
"---\nname: confronto-documenti\ndescription: Compare two or more supplied legal documents or versions, showing terms, source locations and the practical significance of changes. Use for version comparison or parallel agreements, not standalone contract risk review.\n---\n## Task reporting and recovery\n\nFollow `skills/lucia/references/workflow-usage.md` from this installation root.\nUse the bundled CLI, retaining one task UUID for the primary mandate and retries.\nBuild and show the actual model-data report after the useful result. Missing\nreporting, identity verification or receipt delivery stays an explicit separate\nissue and never blocks the document work. Never fabricate measurements or signatures.\n\n\n\n# Confronto documenti\n\nIl confronto richiede almeno due documenti selezionati.\n\nRead `../revisione-contratti/references/document-workflow.md` and\n`../revisione-contratti/references/prassi-italiana.md`. No Mike server or separate API.\nThe upstream snapshot is attribution/history, not an operational instruction.\n\nIdentify whether these are versions of one instrument or separate agreements.\nUse filenames, dates and the user's instruction to establish order; ask if the\nbaseline is ambiguous. Never infer that the last file supplied is the latest.\nFor versions, run the local `compare` helper for each relevant pair. Its literal\ndiff is a reading aid; it does not detect legal significance, prove equivalence,\nresolve renumbering or account for layout/images. Read the source texts too.\nWord paragraph anchors use the proposed/final text view; `/original` anchors\npreserve previous wording. The helper's `--view original` option compares original\ntext instead. Establish the intended view and explain existing unaccepted changes;\nnever treat combined deleted/inserted words as a single operative clause. For a\nrequested Word comparison/redline use the host Documents/Word skill following\n`../revisione-contratti/references/word-handoff.md`.\n\nUse a topic-by-document comparison with one column per document and a separate\nexplanation of the difference. Cover the material similarities as well as changes\nto rights, obligations, economics, deadlines, definitions and incorporated texts.\nTrace each term to its own document and anchor. Distinguish new, deleted, moved\nand reworded provisions through model judgment. Explain why a change matters for\nthe represented party. A changed word can matter more than a moved page. In Italian matters distinguish\nchanges to recesso, disdetta and risoluzione, not merely a generic termination row.\nA new forum is not necessarily a change of governing law. Compare approval blocks\nand annex relationships without treating a second signature as proof of validity.\nKeep textual changes, legal questions and firm-policy deviations distinct.\n\nKeep every document visible, including unreadable versions. “Not stated” requires\ncomplete reading coverage; an extraction gap is not deletion. If the documents\nare only partly comparable, explain the limit and compare the meaningful overlap.\n\nWrite the shared review JSON with one cell per source/topic and document-specific\nquotes. Populate `differences` with exactly one topic key per selected topic and\nthe model's explanation of the cross-document difference as its value; an\nunresolved comparison must explain the missing evidence. Put the main decisions\nin `takeaways`. Rendering creates a topic-by-document table with a separate\nDifference column in both HTML and Excel. Summarize its material conclusions in\nthe final answer.\nReturn no more than five main decisions/follow-up points unless the case needs\nmore. Preserve all originals; this workflow does not accept or reject changes.\n\nMIT source and pin: `references/upstream/PROVENANCE.json` and `LICENSE`.\n"
"---\nname: confronto-documenti\ndescription: Compare two or more supplied legal documents or versions, showing terms, source locations and the practical significance of changes. Use for version comparison or parallel agreements, not standalone contract risk review.\n---\n<!-- MPARANZA_REPORTING_BEGIN -->\n## Task reporting and recovery\n\nFor every substantive user mandate, follow\n`skills/lucia/references/workflow-usage.md` from this installation's root.\nStart one primary task before preparation, using `usage/pipelines.json`; nested\nspecialists, retries and Studio Archive infrastructure reuse that task. Record\nonly the observed whole-task outcome. Discover `lucia_incident_host_link`,\nincluding deferred tools, and verify this run's Computer ID on the server.\nBuild the report input from actual phases even for chat-only drafts; missing\nclient files or a prepared input JSON do not waive reporting. Show the readable\nlocal model-data report under `skills/lucia/references/model-data-report-contract.md`, link its\nactual signed receipt, and ask once for the user's 1–5 stars after delivery.\nOnly user-authored feedback is submitted; tests remain explicitly marked.\nFollow `skills/lucia/references/incident-recovery.md` for automatic technical\nreporting, evidence requests and targeted remedies. Use the HTTPS browser recovery page in that reference if\nlocal execution is unavailable. Never ask the user to relay logs or repeat consent\nfor technical reporting. Recovery requires an observed successful retry of the\noriginal task and inputs, bound to the original report and current remedy.\nTutorials remain local-only and are excluded from task usage and ratings.\n<!-- MPARANZA_REPORTING_END -->\n\n\n# Confronto documenti\n\nPer una sintesi delle revisioni Word in posizioni negoziali, leggi\n`../posizioni-negoziali/SKILL.md` e usa quel metodo con il pack già preparato.\nIl DOCX revisionato può bastare per quella richiesta; il confronto ordinario\nfra versioni conserva il requisito dei due documenti sotto indicato.\n\nRead `../revisione-contratti/references/document-workflow.md` and\n`../revisione-contratti/references/prassi-italiana.md`. No Mike server or separate API.\nThe upstream snapshot is attribution/history, not an operational instruction.\n\nIdentify whether these are versions of one instrument or separate agreements.\nUse filenames, dates and the user's instruction to establish order; ask if the\nbaseline is ambiguous. Never infer that the last file supplied is the latest.\nFor versions, run the local `compare` helper for each relevant pair. Its literal\ndiff is a reading aid; it does not detect legal significance, prove equivalence,\nresolve renumbering or account for layout/images. Read the source texts too.\nWord paragraph anchors use the proposed/final text view; `/original` anchors\npreserve previous wording. The helper's `--view original` option compares original\ntext instead. Establish the intended view and explain existing unaccepted changes;\nnever treat combined deleted/inserted words as a single operative clause. For a\nrequested Word comparison/redline use the host Documents/Word skill following\n`../revisione-contratti/references/word-handoff.md`.\n\nUse a topic-by-document comparison with one column per document and a separate\nexplanation of the difference. Cover the material similarities as well as changes\nto rights, obligations, economics, deadlines, definitions and incorporated texts.\nTrace each term to its own document and anchor. Distinguish new, deleted, moved\nand reworded provisions through model judgment. Explain why a change matters for\nthe represented party. A changed word can matter more than a moved page. In Italian matters distinguish\nchanges to recesso, disdetta and risoluzione, not merely a generic termination row.\nA new forum is not necessarily a change of governing law. Compare approval blocks\nand annex relationships without treating a second signature as proof of validity.\nKeep textual changes, legal questions and firm-policy deviations distinct.\n\nKeep every document visible, including unreadable versions. “Not stated” requires\ncomplete reading coverage; an extraction gap is not deletion. If the documents\nare only partly comparable, explain the limit and compare the meaningful overlap.\n\nWrite the shared review JSON with one cell per source/topic and document-specific\nquotes. Populate `differences` with exactly one topic key per selected topic and\nthe model's explanation of the cross-document difference as its value; an\nunresolved comparison must explain the missing evidence. Put the main decisions\nin `takeaways`. Rendering creates a topic-by-document table with a separate\nDifference column in both HTML and Excel. Summarize its material conclusions in\nthe final answer.\nReturn no more than five main decisions/follow-up points unless the case needs\nmore. Preserve all originals; this workflow does not accept or reject changes.\n\nMIT source and pin: `references/upstream/PROVENANCE.json` and `LICENSE`.\n"
Full snapshot data
{
"description": "Compare two or more supplied legal documents or versions, showing terms, source locations and the practical significance of changes. Use for version comparison or parallel agreements, not standalone contract risk review.",
"included_files": [
{
"relative_path": "references/upstream/LICENSE",
"size_in_bytes": 1061
},
{
"relative_path": "references/upstream/PROVENANCE.json",
"size_in_bytes": 1041
},
{
"relative_path": "references/upstream/compare-documents.md",
"size_in_bytes": 2772
}
],
"name": "confronto-documenti",
"skill_md_contents": "---\nname: confronto-documenti\ndescription: Compare two or more supplied legal documents or versions, showing terms, source locations and the practical significance of changes. Use for version comparison or parallel agreements, not standalone contract risk review.\n---\n<!-- MPARANZA_REPORTING_BEGIN -->\n## Task reporting and recovery\n\nFor every substantive user mandate, follow\n`skills/lucia/references/workflow-usage.md` from this installation's root.\nStart one primary task before preparation, using `usage/pipelines.json`; nested\nspecialists, retries and Studio Archive infrastructure reuse that task. Record\nonly the observed whole-task outcome. Discover `lucia_incident_host_link`,\nincluding deferred tools, and verify this run's Computer ID on the server.\nBuild the report input from actual phases even for chat-only drafts; missing\nclient files or a prepared input JSON do not waive reporting. Show the readable\nlocal model-data report under `skills/lucia/references/model-data-report-contract.md`, link its\nactual signed receipt, and ask once for the user's 1–5 stars after delivery.\nOnly user-authored feedback is submitted; tests remain explicitly marked.\nFollow `skills/lucia/references/incident-recovery.md` for automatic technical\nreporting, evidence requests and targeted remedies. Use the HTTPS browser recovery page in that reference if\nlocal execution is unavailable. Never ask the user to relay logs or repeat consent\nfor technical reporting. Recovery requires an observed successful retry of the\noriginal task and inputs, bound to the original report and current remedy.\nTutorials remain local-only and are excluded from task usage and ratings.\n<!-- MPARANZA_REPORTING_END -->\n\n\n# Confronto documenti\n\nPer una sintesi delle revisioni Word in posizioni negoziali, leggi\n`../posizioni-negoziali/SKILL.md` e usa quel metodo con il pack già preparato.\nIl DOCX revisionato può bastare per quella richiesta; il confronto ordinario\nfra versioni conserva il requisito dei due documenti sotto indicato.\n\nRead `../revisione-contratti/references/document-workflow.md` and\n`../revisione-contratti/references/prassi-italiana.md`. No Mike server or separate API.\nThe upstream snapshot is attribution/history, not an operational instruction.\n\nIdentify whether these are versions of one instrument or separate agreements.\nUse filenames, dates and the user's instruction to establish order; ask if the\nbaseline is ambiguous. Never infer that the last file supplied is the latest.\nFor versions, run the local `compare` helper for each relevant pair. Its literal\ndiff is a reading aid; it does not detect legal significance, prove equivalence,\nresolve renumbering or account for layout/images. Read the source texts too.\nWord paragraph anchors use the proposed/final text view; `/original` anchors\npreserve previous wording. The helper's `--view original` option compares original\ntext instead. Establish the intended view and explain existing unaccepted changes;\nnever treat combined deleted/inserted words as a single operative clause. For a\nrequested Word comparison/redline use the host Documents/Word skill following\n`../revisione-contratti/references/word-handoff.md`.\n\nUse a topic-by-document comparison with one column per document and a separate\nexplanation of the difference. Cover the material similarities as well as changes\nto rights, obligations, economics, deadlines, definitions and incorporated texts.\nTrace each term to its own document and anchor. Distinguish new, deleted, moved\nand reworded provisions through model judgment. Explain why a change matters for\nthe represented party. A changed word can matter more than a moved page. In Italian matters distinguish\nchanges to recesso, disdetta and risoluzione, not merely a generic termination row.\nA new forum is not necessarily a change of governing law. Compare approval blocks\nand annex relationships without treating a second signature as proof of validity.\nKeep textual changes, legal questions and firm-policy deviations distinct.\n\nKeep every document visible, including unreadable versions. “Not stated” requires\ncomplete reading coverage; an extraction gap is not deletion. If the documents\nare only partly comparable, explain the limit and compare the meaningful overlap.\n\nWrite the shared review JSON with one cell per source/topic and document-specific\nquotes. Populate `differences` with exactly one topic key per selected topic and\nthe model's explanation of the cross-document difference as its value; an\nunresolved comparison must explain the missing evidence. Put the main decisions\nin `takeaways`. Rendering creates a topic-by-document table with a separate\nDifference column in both HTML and Excel. Summarize its material conclusions in\nthe final answer.\nReturn no more than five main decisions/follow-up points unless the case needs\nmore. Preserve all originals; this workflow does not accept or reject changes.\n\nMIT source and pin: `references/upstream/PROVENANCE.json` and `LICENSE`.\n"
}SHA-256 of public snapshot: acb47541639460f9a6a29f61beda20725eac9882b3ad8e4822ffe0fec9414e73