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-common-workflows.md
View on GitHub---
slug: cc-common-workflows
title: Common workflows
publisher: Anthropic
url: https://code.claude.com/docs/en/common-workflows
fetchedAt: 2026-10-31
lastVerifiedAt: 2026-11-11
linkStatus: ok
finalUrl:
---
# Common workflows
## Summary
- The page gives short prompt recipes for exploring a codebase, fixing bugs, refactoring, writing tests, opening pull requests and documentation.
- For bugs, share the reproduce command and error output; for refactors, work in small testable steps and run tests afterward.
- Use `@` references to pull files, directories or MCP resources into context; `PreToolUse` hooks do not run for them, so use deny rules for sensitive paths.
- Resume earlier work with `claude --continue` or `/resume` rather than re-explaining context.
- Run `claude --worktree <name>` for isolated parallel sessions on separate branches so edits do not collide.
- Plan mode lets Claude read and propose without editing until you approve.
- Hand large exploration to a subagent so the main context receives only the findings.
- Non-interactive `claude -p` fits CI, pre-commit hooks and batch jobs, with stdin and stdout behaving like other Unix tools.
- Scheduled work can run in the cloud, in the desktop app, in GitHub Actions or via `/loop`; prompts should state success criteria because the run cannot ask questions.
- Images can be pasted or referenced to explain errors, designs and schemas.
## Cited quotes
- "Delegate the exploration so only the findings come back." (ctx-subagent-offload)
- "Claude reads files and proposes a plan but makes no edits until you approve." (plan-mode-first)
- "Run Claude non-interactively for CI, pre-commit hooks, or batch processing." (auto-headless)
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: 471k | 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: 471k | 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: 471k | 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 |