Adonis0123/adonis-skills / skills/agent-practice-audit
agent-practice-audit
FlaggedScore how someone uses coding agents (Claude Code, Codex, Grok and WorkBuddy session logs, instruction files, hooks, permissions, Codex config) against practices quoted from official vendor docs, and write a local HTML report with coverage, trend and suggestions; also refresh or verify that practice list from official docs with multi-model consensus. Use when the user asks how far their agent usage is from official practice, wants an agent usage check-up or grade, or wants the practice list refreshed, its links checked, or either run on a schedule. Chinese triggers: Agent 用法体检、对照官方最佳实践、我的 agent 用得对不对、给 agent 用法打分、更新最佳实践清单. Not for whether a tool, MCP or skill is worth keeping (dev-environment-roi-audit), for writing or reviewing one CLAUDE.md or AGENTS.md, for general best-practice questions, or for Cursor or Gemini CLI logs, which it does not read. Never edits the user's config.
references/sources/cc-art-verification-loops.md
View on GitHub---
slug: cc-art-verification-loops
title: Building verification loops in Claude Code with skills
publisher: Anthropic
url: https://claude.com/resources/articles/building-verification-loops-in-claude-code-with-skills
fetchedAt: 2026-11-11
lastVerifiedAt: 2026-11-11
linkStatus: ok
finalUrl:
---
# Building verification loops in Claude Code with skills
## Summary
- Frames agentic work as a loop of gathering context, acting and verifying, and argues the verify step should be encoded rather than left to the human.
- Built-in aids include the `/verify` skill, toolchain errors, managed Code Review, GitHub Actions jobs and spec validation.
- Listing exact build and test commands in `CLAUDE.md` saves Claude from guessing them.
- Any check you repeatedly enforce by hand, deterministic or not, is a candidate for a custom verification skill.
- Skills can be drafted with the skill-creator plugin interviewing you, or hand-written under `.claude/skills/`.
- A check can run standalone, be embedded in the skill that produces the artifact, be chained after another skill, or run on every PR.
- Chaining turns a habit into a contract but costs tokens, so test chains before using them widely.
- Suggested start: pick the most frequent manual follow-up, try `/verify`, write the procedure in plain English, make it a skill and confirm it runs.
## Cited quotes
- "Anything you keep having to enforce by hand as a manual check qualifies for capture as a loop." (verify-checks-as-skills)
- "A good practice is to list your exact build and test commands in CLAUDE.md so Claude doesn't have to infer them." (doc-test-commands)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |