Claude Code best practices: verify, explore-plan-implement, manage context
Use Claude Code effectively — give Claude a runnable way to verify its work, use the Explore → Plan → Implement workflow, write scoped prompts, keep CLAUDE.md lean, manage context, use subagents
- What
- Use Claude Code effectively — give Claude a runnable way to verify its work, use the Explore → Plan → Implement workflow, write scoped prompts, keep CLAUDE.md lean, manage context, use subagents
- Cost
- Free
- Needs
- Claude Code installed — the skill is guidance the agent follows, not software to install
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @dboeckli's Claude Code best-practice guide (built from Anthropic's official best-practices documentation): the single governing constraint is that Claude's context window fills up fast and performance degrades as it fills — everything flows from that. Step 1, always give Claude a runnable way to verify its work (test suite, build exit code, linter, diff script) and ask for evidence, not assertions. Step 2, use the Explore → Plan → Implement workflow for non-trivial tasks — enter plan mode, let Claude read the codebase, draft the plan, then implement. Step 3, write specific, scoped prompts (@filename, symptoms not guesses, existing patterns). Step 4, keep CLAUDE.md short and actionable — include only what Claude cannot infer ("would removing this cause mistakes?"). Step 5, manage context aggressively (/clear between tasks, /compact with a hint, /rewind, /btw; after two failed corrections, clear and write a better prompt). Step 6, use subagents for investigation and review in a fresh context. Plus non-interactive mode, fan-out loops, parallel sessions with git worktrees, and a common failure patterns reference. Honest caveats: methodology only — you need Claude Code installed to apply it; the full CLI command reference lives in the repo's references/commands.md. MIT licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Claude Code best practices is a free guide from @dboeckli built from Anthropic's official documentation, governed by one constraint: the context window fills fast and performance degrades as it fills. It teaches giving Claude a runnable way to verify work, the Explore, Plan and Implement workflow, scoped prompts, a lean CLAUDE.md, aggressive context management, and subagents for investigation and review.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit ab99d0cStep 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: Claude Code installed — the skill is guidance the agent follows, not software to install Install "Claude Code best practices: verify, explore-plan-implement, manage context" for me. It teaches my agent @dboeckli's Claude Code best practices (built from Anthropic's official docs): always give Claude a runnable verification (tests, build, linter) and ask for evidence; use Explore → Plan → Implement for non-trivial tasks; write specific scoped prompts; keep CLAUDE.md short (only what Claude can't infer); manage context aggressively (/clear, /compact, /rewind); use subagents for investigation and review; automate with non-interactive mode and parallel sessions. MIT-licensed. Repository: https://raw.githubusercontent.com/dboeckli/ai-agent-skills/ab99d0c7b12ebf0a63c76c82ff3337d9b5af1199/.claude/skills/cc-best-practices/SKILL.md Pinned version: install the code at commit ab99d0c7b12ebf0a63c76c82ff3337d9b5af1199 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "cc-best-practices". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. nothing else — it's a methodology; apply it whenever the user asks how to get the most out of Claude Code). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- ab99d0c · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.