borghei/Claude-Skills / engineering/claude-code-mastery
claude-code-mastery
FlaggedOptimizes CLAUDE.md files, scaffolds skills and subagents, wires hooks and measures context budget for Claude Code. Use when writing or trimming a CLAUDE.md, creating a skill, subagent or hook, or auditing token usage.
Claude Code Mastery
Expert skill for Claude Code CLI -- CLAUDE.md optimization, skill authoring, subagent creation, hooks automation, and context engineering.
Core Capabilities
- CLAUDE.md optimization — audit, restructure, compress, and hierarchize config files for token efficiency.
- Skill authoring — scaffold and write discoverable skill packages with correct layout and frontmatter.
- Subagent creation — write
.claude/agents/<name>.mdfiles with atoolsallowlist and a Markdown-body system prompt. - Hooks automation — wire
PreToolUse/PostToolUse/Stoplifecycle scripts via.claude/settings.json. - Context engineering — measure and manage the context-window token budget across a codebase.
When to Use
- Authoring, structuring, or optimizing a CLAUDE.md file for any project.
- Scaffolding a new skill package or creating a Claude Code subagent.
- Configuring hooks for automated quality, security, or workflow steps.
- Auditing and reducing context-window consumption.
Clarify First
Before scaffolding or optimizing, settle the inputs below. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.
- Which task: scaffold a new skill, optimize a CLAUDE.md, create a subagent, or analyze context budget (selects
skill_scaffolder.pyvsclaudemd_optimizer.pyvscontext_analyzer.py). - Target identity: for a new skill: its name, domain, and one-line description; for optimization: the file or project path (the inputs the scripts require).
- Token budget: the target ceiling (sets
--token-limitand what counts as over-budget).
Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top.
Workflow
# Score a CLAUDE.md for structure, token cost and redundancy (default budget 6000 tokens)
python scripts/claudemd_optimizer.py CLAUDE.md --token-limit 4000
# Estimate how much of the context window a project's files would take, by category
python scripts/context_analyzer.py . --max-depth 4 --context-window 200000
# Scaffold a skill package into an existing parent directory
python scripts/skill_scaffolder.py my-skill -d engineering -o /tmp --description "Scores API specs for breaking changes"
All three accept --json. Full flags and output fields: references/tool-reference.md.
claudemd_optimizer.pyreports a 0–100 score, the token estimate against--token-limit, duplicated or vague sections, and concrete cuts.context_analyzer.pydefaults to a 200K window as a conservative floor. Pass the real window of the model you run, or the percentages will overstate the pressure.skill_scaffolder.pycreates<-o DIR>/<skill-name>/withSKILL.md,scripts/,references/andassets/.-o(--output) is the parent directory, which must already exist; it defaults to the current directory, so pass-oto keep the scaffold out of the repo you are standing in. If the description has no "Use when" clause it appends a placeholder so you fill in the triggers before shipping.
Exit codes (all three): 0 report or scaffold written; 2 missing file or path, output directory that does not exist, or a skill folder that already exists. They are advisory, not gates: an over-budget CLAUDE.md still exits 0.
Done when: the CLAUDE.md fits its budget and every line is something the model could not infer from the code; a new skill's description says what it does and when to use it in under 240 characters; a hook has been triggered once on purpose and blocked or passed as intended.
Anti-Patterns
CLAUDE.md as a wiki
Mistake: Pasting architecture essays, full style guides and onboarding notes into CLAUDE.md. Why it happens: It is the one file the agent always reads, so everything lands there. Instead: Keep commands, conventions and traps the code does not reveal; link to longer docs and let the agent read them when needed. Every line costs tokens on every turn.
Hooks that fail open
Mistake: A PreToolUse guard that exits 1 on a violation and assumes the tool call was blocked. Why it happens: Exit 1 means "error" in most CLIs. Instead: A PreToolUse hook blocks only on exit 2 (stderr goes back to the model). Test the hook against a real violating command before relying on it. See references/hooks-cookbook.md.
Subagents with every tool
Mistake: A review subagent with no tools allowlist, so it can edit files and run shell commands.
Why it happens: Omitting tools is the shortest working file.
Instead: Give each subagent the smallest tool list its job needs; a reviewer gets read and search tools only.
Files
scripts/claudemd_optimizer.py,scripts/context_analyzer.py,scripts/skill_scaffolder.py— the three CLIs above.assets/skill-template.md,assets/agent-template.md— starting files for a skill and a subagent.references/— playbooks, quick reference, tool reference, skill authoring, subagent patterns, hooks cookbook.
References
Load the reference that matches the task — keep this file lean and pull detail on demand:
- references/workflows.md — the five numbered playbooks: optimize a CLAUDE.md, author a skill, create a subagent, configure hooks, and manage the context budget. Read when executing any of those tasks step-by-step.
- references/quick-reference.md — slash commands, permission modes, CLAUDE.md loading order, MCP servers, the troubleshooting table, and success criteria. Read for at-a-glance lookups or when debugging configuration.
- references/tool-reference.md — full parameter tables and output formats for the three Python tools. Read when scripting the tools or interpreting their JSON output.
- references/skill-authoring-guide.md — comprehensive reference for writing effective skills, from YAML frontmatter to structure. Read when authoring a skill in depth.
- references/subagent-patterns.md — guide to creating and using subagents for parallel work and scoped tasks. Read when designing a subagent.
- references/hooks-cookbook.md — practical hook recipes for code quality, security enforcement, and workflow automation. Read when building hooks.
Templates: assets/skill-template.md, assets/agent-template.md
Scope & Limitations
This skill covers:
- Authoring, structuring, and optimizing CLAUDE.md files for any project
- Scaffolding new skill packages with correct directory layout and frontmatter
- Creating and configuring Claude Code subagents with scoped tool access
- Analyzing and managing context window token budgets across a codebase
This skill does NOT cover:
- Writing application source code or implementing business logic (see senior-fullstack, senior-backend)
- MCP server development or custom transport protocols (see mcp-server-builder)
- Advanced prompt engineering techniques for LLM applications (see senior-prompt-engineer)
- CI/CD pipeline configuration or deployment automation (see senior-devops, ci-cd-pipeline-builder)
See Also
- context-engine — compression and prioritisation once you know the budget.
- doc-drift-detector — find where CLAUDE.md no longer matches the code.
- code-reviewer — review logic for a code-review subagent.
- senior-prompt-engineer — wording for skill descriptions and agent prompts.
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: 466k | 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: 466k | 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: 466k | 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: 192k | Updated | Claude CodeCodex | Verified | Install |