Skip to content

ThomasMoreAI/legal-skills-open / br/litigation/skills/juriscan-brunobracaioli

juriscan-brunobracaioli

Verified

Análise 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.

FileKindSize
.claude/agents/juriscan-advogado-autor.mdmarkdown4.3 KB
.claude/agents/juriscan-advogado-reu.mdmarkdown3.6 KB
.claude/agents/juriscan-auditor-processual.mdmarkdown7.0 KB
.claude/agents/juriscan-echo.mdmarkdown2.0 KB
.claude/agents/juriscan-parser.mdmarkdown4.7 KB
.claude/agents/juriscan-segmenter.mdmarkdown4.9 KB
.claude/agents/juriscan-sintetizador.mdmarkdown3.1 KB
.claude/agents/juriscan-verificador.mdmarkdown4.8 KB
.github/FUNDING.ymlconfig77 B
.github/workflows/ci.ymlconfig1.0 KB
.gitignoreother121 B
CHANGELOG.mdmarkdown20.6 KB
CLAUDE.mdmarkdown10.6 KB
LICENSEother1.0 KB
README.mdmarkdown16.9 KB
SKILL.mdskill md26.3 KB
assets/banner.svgother4.7 KB
docs/architecture.mdmarkdown10.3 KB
docs/index.htmlother4.3 KB
docs/operations.mdmarkdown6.7 KB
docs/subagent_contract.mdmarkdown6.0 KB
docs/subagents.mdmarkdown5.5 KB
install.shscript3.2 KB
pyproject.tomlmanifest272 B
references/agent_schemas/advogado_output.jsonconfig2.7 KB
references/agent_schemas/auditor_output.jsonconfig4.8 KB
references/agent_schemas/echo_output.jsonconfig666 B
references/agent_schemas/parser_output.jsonconfig4.4 KB
references/agent_schemas/recommendations_output.jsonconfig2.5 KB
references/agent_schemas/segmenter_output.jsonconfig2.9 KB
references/agent_schemas/sintetizador_output.jsonconfig2.7 KB
references/agent_schemas/verificador_output.jsonconfig2.3 KB
references/appellate_structure.mdmarkdown2.0 KB
references/binding_precedents.mdmarkdown2.2 KB
references/brazilian_legal_entities.mdmarkdown3.2 KB
references/chunk_analysis_schema.jsonconfig6.7 KB
references/cpc_prazos.jsonconfig4.4 KB
references/feriados_forenses.jsonconfig2.1 KB
references/output_schema.jsonconfig11.0 KB
references/output_schema_v2.jsonconfig11.0 KB
references/output_schema_v3.jsonconfig5.3 KB
references/piece_type_taxonomy.jsonconfig7.5 KB
references/prompt_templates.mdmarkdown11.8 KB
references/risk_scoring_rubric.mdmarkdown2.4 KB
references/whitelist_fontes.jsonconfig1.8 KB
requirements.txtmanifest250 B
scripts/__init__.pyscript0 B
scripts/agent_io.pyscript12.2 KB
scripts/analyzed_init.pyscript3.3 KB
scripts/audit.pyscript4.8 KB
scripts/cleanup_audit.pyscript2.0 KB
scripts/confidence_rules.pyscript6.4 KB
scripts/content_quality_check.pyscript11.1 KB
scripts/enrich_deterministic.pyscript10.3 KB
scripts/extract_and_chunk.pyscript14.3 KB
scripts/finalize.pyscript10.2 KB
scripts/finalize_legacy.pyscript7.4 KB
scripts/generate_report.pyscript29.8 KB
scripts/instance_tracker.pyscript6.7 KB
scripts/integrity_check.pyscript11.0 KB
scripts/integrity_gate.pyscript4.6 KB
scripts/legacy/__init__.pyscript0 B
scripts/legacy/contradiction_report.pyscript11.9 KB
scripts/legacy/risk_scorer.pyscript10.2 KB
scripts/merge_chunk_analysis.pyscript14.8 KB
scripts/migrate_v2_to_v3.pyscript3.1 KB
scripts/obsidian_export.pyscript28.0 KB
scripts/persist_chunks.pyscript6.2 KB
scripts/prazo_calculator.pyscript14.2 KB
scripts/report_metrics.pyscript8.4 KB
scripts/schema_validator.pyscript5.2 KB
scripts/utils/__init__.pyscript0 B
scripts/utils/cnj.pyscript4.4 KB
scripts/utils/dates.pyscript7.8 KB
scripts/utils/filenames.pyscript2.6 KB
scripts/utils/monetary.pyscript5.2 KB
tests/__init__.pyscript0 B
tests/conftest.pyscript1.1 KB
tests/fixtures/agent_io/echo_invalid_missing_field.jsonconfig45 B
tests/fixtures/agent_io/echo_invalid_wrong_const.jsonconfig70 B
tests/fixtures/agent_io/echo_valid.jsonconfig103 B
tests/fixtures/agent_io/segmenter_valid.jsonconfig359 B
tests/fixtures/sample_analyzed.jsonconfig10.0 KB
tests/fixtures/sample_analyzed_with_prazos.jsonconfig470 B
tests/fixtures/sample_chunk_acordao.txtmarkdown3.4 KB
tests/fixtures/sample_chunk_peticao.txtmarkdown3.4 KB
tests/fixtures/sample_chunk_sentenca.txtmarkdown2.9 KB
tests/fixtures/sample_index.jsonconfig1.6 KB
tests/golden/_pdf_builder.pyscript6.1 KB
tests/golden/processo_01_sintetico_simples/expected_invariants.jsonconfig993 B
tests/golden/processo_01_sintetico_simples/source.txtmarkdown3.3 KB
tests/golden/processo_02_sintetico_art942/expected_art_942.jsonconfig898 B
tests/golden/processo_02_sintetico_art942/expected_invariants.jsonconfig1.3 KB
tests/golden/processo_02_sintetico_art942/source.txtmarkdown7.8 KB
tests/test_agent_io.pyscript4.4 KB
tests/test_analyzed_init.pyscript5.6 KB
tests/test_audit.pyscript4.4 KB
tests/test_cnj.pyscript2.9 KB
tests/test_confidence_rules.pyscript4.8 KB
tests/test_content_quality_check.pyscript14.5 KB
tests/test_contradiction_report.pyscript3.5 KB
tests/test_dates.pyscript5.0 KB
tests/test_enrich_deterministic.pyscript6.3 KB
tests/test_filenames.pyscript2.1 KB
tests/test_finalize.pyscript5.8 KB
tests/test_finalize_legacy.pyscript6.5 KB
tests/test_generate_report.pyscript24.0 KB
tests/test_golden_regression.pyscript6.3 KB
tests/test_instance_tracker.pyscript4.2 KB
tests/test_integrity_check.pyscript4.8 KB
tests/test_integrity_gate.pyscript3.6 KB
tests/test_merge_chunk_analysis.pyscript20.9 KB
tests/test_migrate_v2_to_v3.pyscript4.3 KB
tests/test_monetary.pyscript3.4 KB
tests/test_obsidian_export_v3.pyscript6.9 KB
tests/test_persist_chunks.pyscript6.1 KB
tests/test_prazo_calculator.pyscript14.1 KB
tests/test_report_metrics.pyscript5.3 KB
tests/test_risk_scorer.pyscript5.7 KB
tests/test_whitelist_enforcement.pyscript6.1 KB

docs/subagents.md

View on GitHub
# Juriscan — Subagents

All seven juriscan subagents live in `.claude/agents/juriscan-*.md` and are
symlinked into `~/.claude/agents/` by `install.sh`. Each has a strict
JSON Schema in `references/agent_schemas/<role>_output.json` and is
validated post-hoc by `scripts/agent_io.py validate --agent <role>`.

| Role | Model | Tools | Phase | Critical? |
|---|---|---|---|---|
| [`juriscan-echo`](#echo) | haiku | Read | 0 | Selftest only |
| [`juriscan-segmenter`](#segmenter) | haiku | Read, Bash | 2 | Yes — all downstream depends on coverage |
| [`juriscan-parser`](#parser) | haiku | Read, Bash | 2 | Load-bearing for `votos_divergentes` |
| [`juriscan-advogado-autor`](#advogado-autor) | sonnet | Read, Bash | 3 | Dialectic half #1 |
| [`juriscan-advogado-reu`](#advogado-reu) | sonnet | Read, Bash | 3 | Dialectic half #2 |
| [`juriscan-auditor-processual`](#auditor) | sonnet | Read, Bash | 3 | **MOST CRITICAL** — art. 942 gate |
| [`juriscan-verificador`](#verificador) | haiku | Read, WebFetch, Bash | 4 | Whitelist-restricted |
| [`juriscan-sintetizador`](#sintetizador) | sonnet | Read, Bash | 3 | Cannot drop findings |

## Contract (common to all)

1. SKILL.md invokes via `Task(subagent_type="juriscan-<role>", prompt=...)`.
2. The subagent writes its output JSON to the path passed in the prompt
   (never returns it as text).
3. SKILL.md runs `agent_io.py validate --agent <role> --input <path>`.
4. If exit 0 → log + consume. If exit ≠ 0 → retry once with the error
   message as feedback. Second failure → abort pipeline.
5. Every successful or failed invocation is logged to
   `.juriscan/audit/<run_id>.jsonl`.

## juriscan-echo

Trivial selftest agent. Writes `{"ok": true, "agent": "juriscan-echo", "input_echo": ...}`.
Used by `/juriscan --selftest` to verify the plumbing before any real
analysis runs.

## juriscan-segmenter

Identifies boundaries between legal pieces in the raw extracted text.
Output: `chunks[] = {id, start_char, end_char, tipo_provavel, confianca, evidencia?}`.
Must cover the entire raw text without gaps or overlap —
`scripts/persist_chunks.py` verifies and will re-invoke with feedback if
coverage is violated.

**Confidence calibration:** `0.90+` for explicit headers, `0.70-0.89`
for inferred, `<0.50` only with `tipo_provavel="DESCONHECIDO"`.

## juriscan-parser

Analyzes one chunk per invocation. SKILL.md fires N `Task` calls in a
single assistant message to parallelize across chunks. Output shape is
compatible with legacy v2 chunk objects for backwards compat during the
transition.

**Load-bearing:** when `tipo_peca == "ACÓRDÃO"`, must fill
`acordao_detail.votos_divergentes[]` completely. The auditor uses this
to detect art. 942 CPC triggers; missing it breaks the Phase 3 gate.

## juriscan-advogado-autor

Represents the pole ativo. Produces `forcas`, `fraquezas`,
`recursos_cabiveis`, and a `risk_score` from the perspective of the
author only. Every item must cite `peca_refs` — the schema rejects
arguments without sources. Must never downplay weaknesses when the
autor has lost at first instance.

## juriscan-advogado-reu

Symmetric to advogado-autor for the polo passivo. Shares the same JSON
schema (`advogado_output.json`). Must handle the case where the réu has
already been condemned: reform base attackable? quantum excessive?
nullity arguable?

## juriscan-auditor-processual

**The critical subagent.** Impartial — not advocating for either side.
Produces `auditor_findings[]` and a mandatory 6-item checklist
(`checklist_resultado`). Each checklist entry is `{value, justificativa}`
and cannot be null.

The six items:
1. `art_942_cpc_triggered` — 5 objective conditions for the mandatory
   panel-expansion technique. The golden fixture
   `tests/golden/processo_02_sintetico_art942/` blocks CI on this.
2. `lei_14905_2024_applicable` — straddling 2024-08-30 cutover?
3. `honorarios_post_reform_omission` — embargos de declaração cabíveis?
4. `tempestividade_all_pieces_ok` — any piece out of deadline?
5. `citacao_ok` — art. 246 CPC compliant?
6. `preclusao_detected` — any central argument precluded?

For art. 942 detections, the finding description **must** contain the
literal words `ampliação`, `colegiado`, `maioria`. The golden gate checks
for these tokens.

## juriscan-verificador

Verifies jurisprudence citations against authoritative sources via
`WebFetch`. Restricted to `references/whitelist_fontes.json` — any
`source_url` host outside the whitelist fails
`agent_io.py validate --agent verificador` (post-hoc hard gate in
`scripts/agent_io.py _check_verificador_whitelist`).

**Never** produces `CONFIRMADO` without an in-session `WebFetch`. When
CONFIRMADO or DIVERGENTE, must include a literal `trecho_oficial` from
the fetched page.

## juriscan-sintetizador

Consolidates autor + reu + auditor outputs into a final report.
**Cannot** drop `auditor_findings` — `scripts/confidence_rules.py`
enforces `len(output) >= len(input)` and raises
`ConfidenceRuleError` if violated. Produces `dissensos[]` (original
contribution) by comparing the two advocate outputs.

## Adding a new subagent

1. Write `.claude/agents/juriscan-<role>.md` with frontmatter
   (`name`, `description`, `tools`, `model`) and a prompt body.
2. Add `references/agent_schemas/<role>_output.json` with required fields.
3. Register the role in `KNOWN_AGENTS` and `_SCHEMA_FILE_OVERRIDES` in
   `scripts/agent_io.py`.
4. Add fixtures under `tests/fixtures/agent_io/` and tests in
   `tests/test_agent_io.py`.
5. Wire the new role into `SKILL.md`'s `## Agents Pipeline` section,
   initially marked `[PENDING]` until the acceptance criteria of its
   phase are met.
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
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: 196kUpdated Claude CodeCodexVerifiedInstall