Skip to content
TakoAPI
Back to skills

adversarial-coach

by killerapp

Personal Development
1.4kDownloads reported by clawskills.sh
1Stars
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Adversarial implementation review based on Block's g3.

Description

What This Skill Does

A dialectical review loop where an adversarial coach independently validates implementation completeness against a requirements file. Based on Block's g3 research, it separates the implementing agent from the reviewer to catch gaps the implementer would rationalize away. Returns either IMPLEMENTATION_APPROVED or a concrete list of missing items.

Unlike self-review, the coach discards prior context and evaluates code against requirements as written, catching gaps the implementing agent would overlook or excuse.

When to Use It

  • Catching missing auth endpoints before code review
  • Verifying a spec is fully implemented after a coding session
  • Looping on fixes until all requirements are met
  • Reviewing JWT/bcrypt security gaps in auth implementations
  • Validating edge case test coverage against a written spec

Example Workflow

INPUT

User asks: /coach SPEC.md

AGENT
  1. 1

    Locate and parse SPEC.md to extract all requirements

  2. 2

    Review the current implementation independently, ignoring prior conversation context

  3. 3

    Check each requirement for implementation status, compilation, tests, and security gaps

  4. 4

    Return compliance report with IMMEDIATE ACTIONS NEEDED listing specific files and fixes

  5. 5

    After user applies fixes, re-run review until IMPLEMENTATION_APPROVED is issued

OUTPUT

IMPLEMENTATION_APPROVED with each requirement verified and test count confirmed

Installation

clawhub install killerapp/adversarial-coach

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links