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-sdlc-playbook.md
View on GitHub---
slug: cc-art-sdlc-playbook
title: The AI-native SDLC playbook
publisher: Anthropic
url: https://claude.com/resources/articles/the-ai-native-sdlc-playbook
fetchedAt: 2026-11-11
lastVerifiedAt: 2026-11-11
linkStatus: ok
finalUrl:
---
# The AI-native SDLC playbook
## Summary
- An organizational playbook for an AI-native development lifecycle across plan, design, build, test, deploy and maintain stages, with intent.md, spec.md and plan.md artifacts.
- Build stage: start sessions in plan mode, interrogate the plan and commit it as plan.md before implementation.
- Generate `CLAUDE.md` with `/init`, cut it to what a new joiner needs, keep it short, and add a correction whenever Claude repeats a mistake.
- Skills carry policies that must be applied consistently; hooks back them where a rule must always hold, e.g. formatting and linting after edits.
- Run two or three parallel sessions in separate worktrees to start, adding more only while review keeps up; turn repeated jobs into subagents.
- Test stage: always give Claude a feedback loop (tests, build, screenshots), list commands with healthy output, and write failing tests first for bugs.
- A verifier subagent with a fresh context window can give the final verdict without the assumptions that produced the code.
- Run agent evals in CI when `CLAUDE.md`, skills or hooks change; review PRs with Claude, and feed repeated review findings back into `CLAUDE.md`.
- Much of the playbook (stage gates, governance, metrics, release approval) targets teams rather than individual developers.
## Cited quotes
- "is one way to package the final check by running a fresh context window once the session believes the work is done." (verify-fresh-context-review)
- "Run the formatter and linter after file edits so drift never accumulates" (verify-lint-hook)
- "When Claude makes a mistake twice, the correction goes into CLAUDE.md." (doc-update-on-repeat)
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 |