ThomasMoreAI/legal-skills-open / br/litigation/skills/juriscan-brunobracaioli
juriscan-brunobracaioli
VerifiedAnálise forense de processos judiciais brasileiros. Extrai, classifica e cruza peças processuais, detecta contradições, calcula prazos CPC e gera relatórios de risco com exportação para Obsidian. Use quando mencionar: processo judicial, petição, sentença, acórdão, contradições, prazos, timeline, análise forense, Obsidian.
references/agent_schemas/segmenter_output.json
View on GitHub{
"$schema": "https://json-schema.org/draft-07/schema#",
"$id": "juriscan/agent_schemas/segmenter_output.json",
"title": "juriscan-segmenter output",
"description": "Result of the juriscan-segmenter subagent: full segmentation of a raw extracted text into legal pieces (peças processuais). Char offsets are end-exclusive into raw_text. Coverage of the raw text must be total and non-overlapping — scripts/persist_chunks.py verifies that post-hoc.",
"type": "object",
"additionalProperties": false,
"required": ["schema_version", "raw_text_length", "chunks"],
"properties": {
"schema_version": {
"type": "string",
"const": "1.0"
},
"raw_text_length": {
"type": "integer",
"minimum": 0,
"description": "Length in characters of the raw text that was segmented. persist_chunks.py cross-checks this against len(raw_text.txt) to detect stale inputs."
},
"notes": {
"type": "string",
"description": "Optional free-form notes (e.g. 'detected 2 page headers that were preserved as DESCONHECIDO chunks')."
},
"chunks": {
"type": "array",
"minItems": 1,
"items": {
"type": "object",
"additionalProperties": false,
"required": ["id", "start_char", "end_char", "tipo_provavel", "confianca"],
"properties": {
"id": {
"type": "string",
"pattern": "^c[0-9]{2,4}$",
"description": "Sequential id c00, c01, ... used for downstream references."
},
"start_char": {
"type": "integer",
"minimum": 0,
"description": "Inclusive start offset into raw_text (characters, not bytes)."
},
"end_char": {
"type": "integer",
"minimum": 0,
"description": "Exclusive end offset into raw_text."
},
"tipo_provavel": {
"type": "string",
"description": "Legal piece type from references/piece_type_taxonomy.json, uppercase. Use 'DESCONHECIDO' when uncertain — downstream will handle it.",
"minLength": 1
},
"confianca": {
"type": "number",
"minimum": 0.0,
"maximum": 1.0,
"description": "Calibrated confidence: 0.9+ = piece header/footer clearly identified; 0.5-0.9 = inferred from content; <0.5 = last-resort guess."
},
"page_range": {
"type": "array",
"items": { "type": "integer", "minimum": 1 },
"minItems": 2,
"maxItems": 2,
"description": "Optional [first_page, last_page] covered by this chunk when page_map is available."
},
"evidencia": {
"type": "string",
"description": "Short literal snippet (≤120 chars) from the raw text that motivated the classification. Enables auditing and retry-with-feedback."
}
}
}
}
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |