prompt-improvement

Description

Meta-skill for improving and optimizing prompts using Anthropic's prompt engineering best practices. Provides the 4-step improvement workflow (example identification, initial draft, chain of thought refinement, example enhancement), keyword registries for documentation lookup, and decision trees for improvement strategies. Use when improving prompts, optimizing for accuracy, adding chain of thought reasoning, structuring with XML tags, enhancing examples, or iterating on prompt quality. Delegates to docs-management skill for official prompt engineering documentation.

Tool Access

5 tools

Limited to specific tools

Supporting Files

16 files

Additional assets for this skill

Tool Access

This skill is limited to using the following tools:

ReadGlobGrepSkillBash

Supporting Assets

references/examples/advanced-transformations.md

references/examples/basic-transformations.md

references/examples/domain-specific.md

references/metadata/keyword-registry.md

references/metadata/tag-reference.md

references/patterns/cot-patterns.md

references/patterns/example-enrichment-patterns.md

references/patterns/prefill-patterns.md

references/patterns/system-prompt-patterns.md

references/patterns/xml-tagging-patterns.md

references/troubleshooting/common-issues.md

references/troubleshooting/debugging-guide.md

references/troubleshooting/tradeoffs-guide.md

references/workflows/improvement-workflow.md

references/workflows/iterative-refinement.md

references/workflows/test-case-generation.md

Links

GitHub Stats

0 forks

Updated 7 hours ago

Related Skills

Agent Development

45.7K

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

From plugin-dev

Command Development

45.7K

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

From plugin-dev

Hook Development

45.7K

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

From plugin-dev