Skip to content
Agentmart
Submit a tool

counsel-research-draft-pipeline

Use when researching and drafting BC legal documents.

Skill by dmang69

IndexedMIT★ 3
Write a review

Chalk Labs

Need help deploying counsel-research-draft-pipeline?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/dmang69-counsel-research-draft-pipeline

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when researching and drafting BC legal documents.

Use cases: data, research, legal

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/counsel-research-draft-pipeline

What's inside

Skill name
counsel-research-draft-pipeline
Description
Use when researching and drafting BC legal documents.
License
MIT
Instructions
294 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • counsel-framework.md · references/

SKILL.md (first lines)

# Counsel Research & Draft Pipeline

## Overview

Mandatory production pipeline for elite BC superior-court / tribunal research and
drafting. Implements the operational half of the counsel mandate; full professional
framework lives in `references/counsel-framework.md` (synced from monorepo
`skills/supreme-court-civil-counsel/counsel-framework.md`).

**Trigger detail (full):** Research and summarize applicable authorities (verify
every citation) → Analyze facts against governing principles → Address
counterarguments and weaknesses → Draft in court-ready *format* → Pre-finalization
quality review (logic, chronology, citations, procedure, evidence, grammar,
formatting, cross-refs).

**Not legal advice.** Outputs are legal information and drafting support.
Default label every work product:

> **WORKING DRAFT — HUMAN VERIFICATION REQUIRED BEFORE FILING**

unless the human release gate in Step 5 has expressly passed.

## When to Use

- User asks for research + analysis + draft of any legal document
- Petitions, applications, responses, affidavits, briefs, submissions, BOAs
- Decision review memos, issue matrices, written argument
- Any task that would otherwise skip verification or counterargument work

**Don’t use for:** pure product-engineering on the monorepo (use `bc-legal-ai-product`);
casual Q&A that is not heading toward a citable work product.

**Companion loads (BC RTB → JR):**
`legal-document-preparation` + monorepo `bc-judicial-review-guide` +
`supreme-court-civil-counsel` (+ tenancy / `canlii-boa-builder` as needed).

## Absolute rules

1. Never invent facts.
2. Never present unverified authority as settled.
3. Do not claim certainty where the law is unsettled.
4. Identify assumptions, missing evidence, and issues requiring verification.
5. Every material FACT needs a record pinpoint or is labeled **ALLEGATION**.
6. Unverified citations = research leads only — never props for conclusions,
   deadlines, or “court-ready” claims.
7. Respect locked product corrections (below).

### Locked design corrections

| # | Rule |
|---|------|
| 1 | Consent ≠ privilege |
| 2 | Consent withdrawal ≠ unconditional deletion (PIPA; holds separate) |
| 3 | Forms: **66** petition · **67** response · **32** interlocutory · **33** app response · **109** affidavit |
| 4 | JR clock: **60 days from issuance** (ATA s.57 when incorporated); s.57(2); **alternatives** when uncertain |
| 5 | Honest encryption posture only |
| 6 | RTB published archive incomplete; absence ≠ non-existence |

### Mandatory analytical framework (strict separation — label everything)

| Category | Description |
|----------|-------------|
| **FACT** | Evidence-supported, verified, documented findings drawn directly from the record |
| **ALLEGATION** | Asserted but unproven claims requiring evidentiary substantiation before reliance |
| **LEGAL ARGUMENT** | Formal submissions grounded in statute, binding precedent, and common law |
| **INFERENCE** | Reasoned conclusions logically and defensibly drawn from established evidence |
| **ASSUMPTION** | Unverified propositions explicitly flagged as requiring investigation |
| **PROCEDURAL HISTORY** | Chronological record of all prior proceedings and interlocutory steps |
| **RECOMMENDATION** | Advisory positions identified as professional guidance subject to independent counsel review |

Prefix labels:

`[FACT]` · `[ALLEGATION]` · `[LAW]` · `[ARGUMENT]` · `[INFERENCE]` · `[ASSUMPTION]` ·
`[PROCEDURAL HISTORY]` · `[RECOMMENDATION]` · `[REMEDY]` · `[CITATION UNVERIFIED]` ·
`[LAW CURRENCY UNVERIFIED]` · `[INDEPENDENT COUNSEL RECOMMENDED]`

Also keep **FACT / LAW / ARGUMENT / ANALYSIS / REMEDY** visibly separated in structure.

**Boundary (always):** legal information and drafting support — not legal advice. SRL-primary use: flag independent counsel; never present unverified authority as settled. Full role/competencies: `references/counsel-framework.md`.

---

## Five-step pipeline (do not skip or reorder)

### Step 1 — Research and summarize applicable authorities (verify every citation)

**Do**

1. Confirm forum and jurisdiction before diving into merits.
2. Map governing statutes/regulations (BC Laws / Justice Canada), Rules/forms,
   practice directions, limitation / JR clock candidates.
3. Pull case law via CanLII hierarchy: binding → persuasive → guidance.
4. For **every** authority you will rely on:
   - Verify **existence** and citation format
   - Record: jurisdiction, court/tribunal, date, neutral citation, URL, **access date**, pinpoint, treatment/history
   - State the legal principle in one tight sentence
   - Mark `[AUTHORITY VERIFIED — source, access date, pinpoint, treatment]` **or**
     `[CITATION UNVERIFIED — do not rely on or file]`
5. Produce an **Authorities Summary** table before drafting prose:

| Authority | Citation | Pinpoint | Principle | Application lean | Status |
|-----------|----------|----------|-----------|------------------|--------|

**Statutes:** operative text only from **BC Laws** (BC) or Justice Canada (federal).
CanLII statute mirrors are research aids only.
**Cases:** CanLII/official reporters. Automated CanLII case PDF fetch is blocked
(DataDome) — mark download/verification path; never fabricate the text.

**Done when:** every authority that will appear in the draft is either VERIFIED with
pinpoint or explicitly UNVERIFIED and quarantined from reliance; JR/limitation
candidates listed if posture engages them.

### Step 2 — Analyze the facts against the governing legal principles

**Do**

1. Extract facts **only** from the record with pinpoints (transcript timestamps,
   affidavit paras, exhibit tabs, decision paragraphs).
2. Build chronology + PROCEDURAL HISTORY; list missing record pieces.

From dmang69/bc-legal-ai, MIT.

More from dmang69/bc-legal-ai

Signals

Stars
3
Forks
0
Open issues
0
Last commit (this folder)
Jul 29, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from dmang69

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get counsel-research-draft-pipeline running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying counsel-research-draft-pipeline?

CallGet help
Cite this page

counsel-research-draft-pipeline skill. Agent Mart. https://agentmart.dev/skills/dmang69-counsel-research-draft-pipeline (last updated 2026-10-24)