菜单
Truth scoring, code-quality verification, and automatic rollback with a high accuracy threshold. Use when validating agent output before it ships, gating changes on quality, or adding a verify-and-rollback safety loop.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Compile a goal into a durable, file-backed agent loop — a .loop/<name>/ charter any coding agent (Claude Code, Codex, Gemini, Grok) can execute unattended. Use when the user wants to "build a loop", "design a loop", "run X continuously/24-7", "make an agent keep working on Y", automate recurring work, or convert a big backlog into autonomous iteration. Produces LOOP.md + state.json + backlog.md, ready for loop-runner.
Operate a fleet of durable agent loops under .loop/ — schedule which loop runs next, assign agents to roles (maker vs checker), enforce promotion gates from propose-only to write access, allocate budgets, detect stalled or dead loops, and roll up fleet status into one report. Use when asked to "run the loops", "orchestrate the loops", "loop status", "which loop next", "promote the loop", or to manage 24/7 loop operations across Claude Code, Codex, Gemini, and Grok.
Execute exactly one disciplined iteration of a designed loop from .loop/<name>/ (LOOP.md charter + state.json + journal.md). Use when asked to "run the loop", "run one iteration of <loop>", "continue the <name> loop", or when invoked on a cadence (cron, /loop, while-loop) against a loop directory. Works identically under Claude Code, Codex, Gemini CLI, or any coding agent — state lives in files, not in this conversation.
Generate high-quality AI Architect newsletters with latest AI news, research integration, and visual design. Use when creating newsletters, researching AI developments, synthesizing AI news for architects, or distributing intelligence reports. Covers AI model releases, research papers, tool launches, architecture patterns, production systems, and enterprise AI trends. Integrates with FrankX research hub and supports both daily briefs and weekly deep-dives.
Design and generate premium book covers using NB2 (Nano Banana 2 / Gemini 3.1 Flash Image) with deep thinking about book tension, emotion, and genre. Pulls from top book cover design principles (Chip Kidd, Peter Mendelsund, Coralie Bickford-Smith). Auto-activates when user requests book cover, cover art, cover design, or mentions generating a cover for a book project.
Build autonomous AI agents with the Claude Agent SDK — computer use, tool calling, MCP integration, and production best practices for Anthropic models. Use when writing agent code against the Claude/Anthropic SDK, wiring tools or MCP servers, or hardening an agent for production.
| name | verification-quality |
| description | Truth scoring, code-quality verification, and automatic rollback with a high accuracy threshold. Use when validating agent output before it ships, gating changes on quality, or adding a verify-and-rollback safety loop. |
| version | 2.0.0 |
| category | quality-assurance |
| tags | ["verification","truth-scoring","quality","rollback","metrics","ci-cd"] |
This skill provides a comprehensive verification and quality assurance system that ensures code quality and correctness through:
npx claude-flow@alpha)# View current truth scores
npx claude-flow@alpha truth
# Run verification check
npx claude-flow@alpha verify check
# Verify specific file with custom threshold
npx claude-flow@alpha verify check --file src/app.js --threshold 0.98
# Rollback last failed verification
npx claude-flow@alpha verify rollback --last-good
The full detail lives in references/ and loads only when needed:
references/guide.md — truth scoring, verification checks, rollback, reports, dashboard, configuration & advanced workflows.Verification Speed:
Rollback Speed:
Dashboard Performance:
Low Truth Scores:
# Get detailed breakdown
npx claude-flow@alpha truth --verbose --threshold 0.0
# Check specific criteria
npx claude-flow@alpha verify check --verbose
# View agent-specific issues
npx claude-flow@alpha truth --agent <agent-name> --format json
Rollback Failures:
# Check git status
git status
# View rollback history
npx claude-flow@alpha verify rollback --history
# Manual rollback
git reset --hard HEAD~1
Verification Timeouts:
# Increase timeout
npx claude-flow@alpha verify check --timeout 60s
# Verify in batches
npx claude-flow@alpha verify batch --batch-size 10
Verification commands return standard exit codes:
0: Verification passed (score ≥ threshold)1: Verification failed (score < threshold)2: Error during verification (invalid input, system error)npx claude-flow@alpha pair - Collaborative development with verificationnpx claude-flow@alpha train - Training with verification feedbacknpx claude-flow@alpha swarm - Multi-agent coordination with quality checksnpx claude-flow@alpha report - Generate comprehensive project reports/docs/truth-scoring.md/docs/verification-criteria.md/examples/verification//docs/api/verification.md