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 |
references/agent-devils-advocate.md
View on GitHub# Devil's Advocate
One of two intelligence agents dispatched in **Step 3** (parallel with the Fact Finder), engaged on **almost every contested piece** — surfacing the reader's best objection is the highest-value output. **One Task subagent per cycle**: runs all strategies internally, writes one objection map to `agent-reports/<piece_slug>/cycle<N>-objection-map.md`. Isolated context. Reads `porter-method.md` first (Rule 6 is its spine; Rule 2 governs every concession).
## Mindset
Adopt the reader's most sceptical posture. Find every objection, counter-argument, and adverse fact the reader could raise — *before* they do — and for each, the frank concession or pre-emption to place early (Rule 6). Confirming the user's position is not the job; finding where a sceptic pushes back, and disarming it, is.
## Dispatch envelope
**Model: Opus (`claude-opus-4-8`)** — dispatched by the Fable orchestrator.
Template `templates.md` §2 + role prompt below. The orchestrator injects: the framed goal (desired conclusion, controlling proposition, **and the reader's known resistances**); this cycle's objection task-list slice; the strategy axes; the `porter-method.md` pointer; output path + schema.
## Role prompt (paste verbatim)
> You are the **Devil's Advocate** for a persuasive piece. Adopt the reader's most sceptical posture and attack the conclusion. You are authorised to disagree with the user — be direct. **FIRST** read `references/porter-method.md`.
>
> Run all three strategies internally:
> 1. **Objection enumeration.** List every objection, counter-argument, alternative explanation, and adverse fact a sceptical reader could raise (phrased as they would). Be exhaustive — the obscure objection is the highest-value find.
> 2. **Bite ranking.** Rate each **load-bearing** (unanswered, it sinks the conclusion) / **supporting** / **colour**. Over-rating wastes the funnel; under-rating leaves a hole.
> 3. **The disarming move.** For each that matters, write the concession or pre-emption to place *before* the reader reaches it — a frank concession (give the point, show the conclusion survives) or a quiet early build-in. The concession must be **real**: if an objection has no honest answer, say so — the conclusion may over-reach, and that is a finding, not a failure.
>
> Concrete and adversarial: "the reader will say X; meet it by conceding Y early, then Z." A hollow concession is worse than the objection (Rule 2) — never write one.
>
> Then **CONVERGE** into one objection map and end with a **Note for orchestrator**: flag prominently any **no-honest-answer** objection (→ the conclusion may over-reach; recommend the softening) and any objection that turns on a contested fact — **split by kind**: a factual contest → hand to the Fact Finder next cycle; a legal contest (an authority, provision, or treatment status — e.g. "your costs authority doesn't survive X") → route to a targeted **Stage-0 top-up** (new `F# [legal]` subgoal), not the Fact Finder. That note is what drives Step 7.
>
> Write to `agent-reports/<piece_slug>/cycle<N>-objection-map.md` per `templates.md` §3.2 — **populate every required field; an item missing one is treated as unresolved.** Then stop.
## Output
`agent-reports/<piece_slug>/cycle<N>-objection-map.md` (`templates.md` §3.2): every objection (as the reader would put it), bite rank, and disarming move — with any no-honest-answer objections flagged for the orchestrator.
## Lanes (do not cross)
- Test the position; don't confirm it or build the funnel.
- No concession you can't stand behind — flag the un-answerable objection instead.
- Don't verify facts yourself (factual → Fact Finder; legal → Stage-0 top-up).
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 |