Full — Development skill for Claude Code
Full review - all 10 angles plus the adversarial verify pass.
How to install Full
Installs to ~/.claude/skills/demchaav-deep-review-full/SKILL.md
mkdir -p ~/.claude/skills/demchaav-deep-review-full && curl -fsSL https://raw.githubusercontent.com/DemchaAV/deep-review/HEAD/commands/full.md -o ~/.claude/skills/demchaav-deep-review-full/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Full does
description: Full review - all 10 angles plus the adversarial verify pass. argument-hint: "[target] [what you want looked at]" allowed-tools: Bash, Read, Write, Grep, Glob, Agent, Skill, ReportFindings
Run a deep review with `--effort deep` fixed. Arguments: `$ARGUMENTS`
Follow the protocol in the `deep-review:deep-review` skill exactly, start to finish, and read `$ARGUMENTS` by its **Reading the arguments** section. Load the skill with the Skill tool if it is not already in context.
Alternatives in Development
- Zeroshot — Runs coding agents as a graph: one agent implements, independent agents review, failures go to repair, and not 1.9k ★
- Quick Eval — Quick job evaluation 473 ★
- Verify Theme — Run the full Graphite quality gate (drift, tokens, contrast, YAML) and report pass/fail 452 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Critique Adversarial
/critique-adversarial — Hostile cut-editor for articles. Reads the full piece first, maps the thesis spine, th
Feature Forge
A full feature lifecycle for coding agents: crucible, brief, wireframe, architecture, plan, TDD build loop, ad
Rolepod Stats
Show rolepod evidence stats for this project — tier routes, verify/review verdicts, strong-dispatch overrides,
Reviewer Verify
You are the adversarial verifier for the candidate pull-request findings raised against one file. Your only jo
Opc
OPC — One Person Company. A full team in a single Claude Code skill. Adaptive agent orchestrator with 11 built
Anti Subagent
FUCK SUBAGENTS. Multi-agent architecture built with autonomous full agents instead of native subagents. Superv
Related Agents
Dashclaw Gate Runner
Runs the DashClaw verification gates (lint, full vitest suite, build, contract checks) and returns ONLY the fa
Debate Judge
L0.97 Adversarial Verification — reads all 3 rounds of prosecution and defense transcripts plus the original d
Loop Reviewer Verify
full-loop S6 검수 2 — 기능 실증(BASH 실행·재현 기반). AC의 검증 방법을 실제로 실행해 출력으로 판정한다. 증거 없는 PASS 금지.