ThomasMoreAI/legal-skills-open / au/general/skills/claude-submission-drafting-acor8826
claude-submission-drafting-acor8826
VerifiedPersuasive writing as a multi-agent orchestration modelled on Chester Porter QC's The Gentle Art of Persuasion. Stage 1: the Lead Strategist ('Smiling Funnel-Web') decomposes the brief into a persuasion goal and ID'd weighted subgoals, hardens the frame (Frame Challenger + Issue Spotter), confirms it with the user. Stage 0: where a load-bearing point turns on law, runs the australian-legal-research method into a verified authorities pack before drafting. Stage 2: dispatches Fact Finder + Devil's Advocate as parallel Task subagents, builds the funnel (Diplomat then Plain Speaker passes), runs the Porter gate plus a release-blocking citation check, and cycles. USE to move a specific reader to a conclusion by courtesy, fact, and pre-emptive concession, not force. Triggers: 'make this more persuasive', 'win over the reader', 'anticipate objections', 'draft a persuasive letter/email/board paper', 'Calderbank offer', 'letter of demand', 'Chester Porter', 'funnel-web'. For court filings see written-submissions.
| File | Kind | Size |
|---|---|---|
| .gitignore | other | 139 B |
| LICENSE | other | 1.0 KB |
| README.md | markdown | 4.2 KB |
| SKILL.md | skill md | 32.7 KB |
| references/agent-devils-advocate.md | markdown | 3.6 KB |
| references/agent-diplomat.md | markdown | 2.9 KB |
| references/agent-fact-finder.md | markdown | 3.8 KB |
| references/agent-lead-strategist.md | markdown | 5.1 KB |
| references/agent-plain-speaker.md | markdown | 2.8 KB |
| references/frame-hardening.md | markdown | 6.5 KB |
| references/legal-intelligence.md | markdown | 5.0 KB |
| references/porter-gate.md | markdown | 10.8 KB |
| references/porter-method.md | markdown | 3.1 KB |
| references/templates.md | markdown | 14.0 KB |
README.md
View on GitHub# Submission Drafting — a Claude Code Skill
A multi-agent [Claude Code](https://claude.com/claude-code) **skill** for persuasive writing, modelled on Chester Porter QC's *The Gentle Art of Persuasion*. It turns a brief or a draft into a piece that moves a **specific reader** to a conclusion the way Porter persuaded a tribunal: by courtesy, undisputed fact, and frank pre-emptive concession — never by force.
> ⚠️ **Not legal advice.** This skill is a drafting aid. Where a document has legal consequences (a Calderbank offer, a letter of demand), have it reviewed by a qualified practitioner before it is sent.
## What it does
The skill is register-general — the reader may be an opponent's solicitor, a regulator, a board, a client, a counterparty, or the reader of an essay. It runs as an orchestrated, multi-agent pass:
1. **Stage 1 — Orchestration.** The Lead Strategist ("Smiling Funnel-Web") decomposes the brief into a persuasion goal and weighted subgoals, hardens the frame (Frame Challenger + Issue Spotter passes), and confirms it with the user.
2. **Stage 0 — Legal intelligence** *(conditional)*. Where a load-bearing point turns on law, the orchestrator runs the [`australian-legal-research`](https://github.com/acor8826/claude-australian-legal-research) method to build a verified authorities pack before drafting.
3. **Stage 2 — Diverge-converge.** It dispatches Fact Finder and Devil's Advocate as parallel subagents, builds the **funnel** (Diplomat pass, then Plain Speaker pass), runs the Porter gate plus a release-blocking citation check, and cycles until the piece passes.
### The persuasion roster
| Agent | Role |
|---|---|
| **Lead Strategist — "Smiling Funnel-Web"** | The orchestrator: frames the goal, decomposes, converges, builds the funnel, makes the final call |
| **Fact Finder** | Verifies facts, strips hyperbole, sequences the fact base chronologically |
| **Devil's Advocate** | Maps every objection the reader could raise, each with its disarming concession |
| **Diplomat** | The register pass: courtesy, charm, humility; aggression rewritten into reasonable queries |
| **Plain Speaker** | The clarity pass: jargon and friction removed so the logic lands first time |
Every agent reads `references/porter-method.md` — Porter's doctrines distilled into nine operational rules — before writing anything.
## Installation
Clone this repo straight into your Claude Code skills directory:
```bash
# Personal (all projects)
git clone https://github.com/acor8826/claude-submission-drafting.git \
~/.claude/skills/submission-drafting
```
Or, for a single project, copy this folder into that project's `.claude/skills/` directory.
Claude Code auto-discovers any folder containing a `SKILL.md`, so once `submission-drafting/SKILL.md` is in a skills directory it is available.
**Optional companion:** Stage 0 (legal intelligence) works best with the [`australian-legal-research`](https://github.com/acor8826/claude-australian-legal-research) skill installed alongside; without it the skill still runs, but load-bearing legal points cannot be verified against primary sources.
## Usage
Once installed, the skill triggers automatically on persuasive-drafting requests, or you can invoke it explicitly. Triggers include:
- "make this more persuasive", "win over the reader", "anticipate objections"
- "draft a persuasive letter / email / board paper"
- "Calderbank offer", "letter of demand"
- any mention of Chester Porter or the funnel-web
## Repository layout
```
submission-drafting/
├── SKILL.md # Skill definition + orchestration architecture
└── references/
├── porter-method.md # Porter's doctrines as nine operational rules
├── agent-lead-strategist.md # Per-agent briefs …
├── agent-fact-finder.md
├── agent-devils-advocate.md
├── agent-diplomat.md
├── agent-plain-speaker.md
├── frame-hardening.md # Frame Challenger + Issue Spotter passes
├── legal-intelligence.md # Stage-0 bridge to australian-legal-research
├── porter-gate.md # The release-blocking quality gate
└── templates.md # Subagent prompt + output templates
```
## License
[MIT](./LICENSE)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |