Author Brief — Development skill for Claude Code
Round {{ROUND}}/{{MAX_ROUNDS}} — {{ADVERSARY}} challenges your change.
How to install Author Brief
Installs to ~/.claude/skills/yuktmitash21-debater-author_brief/SKILL.md
mkdir -p ~/.claude/skills/yuktmitash21-debater-author_brief && curl -fsSL https://raw.githubusercontent.com/yuktmitash21/debater/HEAD/prompts/author_brief.md -o ~/.claude/skills/yuktmitash21-debater-author_brief/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Author Brief does
Round {{ROUND}}/{{MAX_ROUNDS}} — **{{ADVERSARY}}** challenges your change. Fresh session, different model, has not seen this conversation and did not write this code.
{{CLAIMS}}
Go read the `file:line` on each claim before answering. Agreeing without looking is the failure this exists to catch; so is dismissing a claim because you already believed you were right.
Answer every claim, one line each, exactly this shape:
`**C1 — CONCEDE**` / `**C1 — REJECT**` / `**C1 — PARTIAL**` — then you
Alternatives in Development
- Dario — A local OpenAI- and Anthropic-compatible proxy that brings your Claude Pro/Max subscription to Cursor, Cline 485 ★
- Htb Writeups — The most comprehensive Hack The Box writeup collection - 500+ machines, 400+ challenges, interactive knowledge 244 ★
- Voice Guard — Use to check ONE already-written piece of copy against a voice guide before it ships — it spawns ONE fresh sib 130 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Adversary Rebut
Round {{ROUND}} of {{MAX_ROUNDS}}. The author has responded to your claims.
Calibrate Voice
Run an empirical calibration round: regenerate the 8-brief matrix, measure, collect owner ratings, codify ever
Claude Auto Handoff
Claude Code mod: hand a long session off to a fresh one with a structured brief, instead of auto-compacting
Phone A Team
Iterative refinement — delegates tasks to backend(s) via agent teams, reviews, iterates up to MAX_ROUNDS round
Coder Eval Create Plan
Create a structured, phased implementation plan for a feature or change in the coder_eval codebase, executable
Pre Ship Adversary
Before committing a non-trivial change, spend 2-3 minutes attacking the change yourself — scope creep, failure
Related Agents
Ticket Reviewer
Independently reviews one finished ticket by following the review-ticket skill. Read only: it cannot edit, wri
Design Designer
Creative UI/UX designer on a design sprint team. Produces design proposals across three rounds of increasing c
Debate Orchestrator
Orchestrate multi-round debates between AI tools. Manages proposer/challenger rounds, builds cross-tool prompt