Agent skill
md-improve
Improves CLAUDE.md by analyzing conversation patterns. Use when Claude keeps repeating a mistake, when teaching a new preference, or when consolidating guidance from repeated instructions. Captures recurring corrections and style preferences into project instructions.
Install this agent skill to your Project
npx add-skill https://github.com/philoserf/claude-code-setup/tree/main/skills/md-improve
SKILL.md
Improve Instructions
Analyze conversation patterns to identify improvements for CLAUDE.md instruction files.
Objective
Review how the conversation has gone to find opportunities where better instructions would have helped Claude perform more effectively.
When to Use
- Claude keeps making the same mistake despite corrections
- You've stated a preference 2+ times and it's not sticking
- A workflow or tool preference should be codified
- You want to consolidate scattered guidance into CLAUDE.md
When NOT to Use
- For initial CLAUDE.md creation or template-based audits — use
md-audit - For full session retrospectives with code/architecture insights — use
session-review - For one-off corrections that won't recur — just tell Claude directly
Process
Phase 1: Analyze Conversation
Review the conversation history for:
- Repeated corrections - "No, I meant..." or "Remember to..."
- Manual guidance - Workflows explained step-by-step that could be documented
- Preference statements - "I prefer X" or "Always use Y"
- Misunderstandings - Where Claude made wrong assumptions
- Undocumented patterns - Tools or workflows used frequently
Track each potential improvement identified.
Phase 2: Review Current State
Read the relevant CLAUDE.md file(s):
~/.claude/CLAUDE.mdfor global instructions- Project-level
CLAUDE.mdfor project-specific instructions
Understand what's already documented to avoid duplication and identify gaps.
Phase 3: Propose Improvements
Present findings to the user using AskUserQuestion:
For each improvement, explain:
- Issue: What pattern was observed
- Proposal: Specific text to add or change
- Rationale: Why this would help
Group related improvements and let the user select which to implement.
Phase 4: Implement
For each approved improvement:
- Use Edit to modify the appropriate CLAUDE.md
- Place new content in the logical section
- Maintain existing formatting and style
Summarize all changes made.
Guidelines
- Ground suggestions in actual conversation patterns, not hypotheticals
- Prefer specific, actionable instructions over vague guidance
- Keep instructions concise - Claude is smart, it doesn't need over-explanation
- Preserve the user's existing voice and style
- Don't add instructions for one-off situations
Phase 5: Verify
After all edits:
- Read back the modified CLAUDE.md section(s) to confirm changes match approvals
- Run
bunx prettier --checkon modified files to ensure formatting is clean - Show a summary diff of what changed
Output
End with a summary of:
- Changes made to CLAUDE.md
- Patterns identified but not yet addressed (for future consideration)
Reference Files
Detailed analysis patterns and examples:
- analysis-guide.md — Correction patterns, preference signals, workflow patterns, anti-patterns
- examples.md — Before/after examples of instruction improvements
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
pre-release
Validates a project is ready to tag and ship. Use when tagging a release, cutting a version, shipping a package, or asking "are we ready to release?" Checks repo hygiene, CI status, docs, version sync, and build verification. Optimized for Obsidian plugins with fallback detection for other project types.
local-issues
Reviews a codebase for bugs, design issues, and code cleanliness problems with specific file paths and line numbers. Use when auditing code quality, finding bugs, doing a code review, finding problems, or reviewing a project for issues. Creates issue files in `.issues/` directory.
skill-improve
Generates prioritized improvement recommendations for Claude Code skills. Use when improving skills, enhancing customizations, or wanting actionable feedback on how to make a skill better. Provides impact/effort prioritization with specific fix suggestions.
release
Executes the final release workflow for Obsidian plugins after pre-release checks pass. Use when tagging a release, publishing a version, or shipping an Obsidian plugin. Bumps version via bun run script, creates git tag, pushes to trigger GitHub Actions, and updates GitHub release notes from CHANGELOG.md.
skill-quality
Scores Claude Code skills (1-5) across 6 weighted quality dimensions aligned with official Anthropic docs. Use when evaluating skill quality, rating skills, scoring customizations, comparing skill effectiveness, or checking if a skill follows best practices. Produces per-dimension scores with evidence, weighted totals, quality tier classification, and actionable improvement recommendations.
obsidian-cli
Interacts with Obsidian vaults using the Obsidian CLI to read, create, and manage notes, tasks, properties, tags, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, add to daily note, find notes about a topic, check tasks, append to a note, query the vault, list tags, list files, manage bookmarks, check sync status, view file history, use templates, query bases, run QuickAdd, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.
Didn't find tool you were looking for?