Learn from Conversation

Supported Assistants

CLAUDE.md

GEMINI.md

AGENTS.md

.cursorrules

.cursor/rules/*.mdc

.github/copilot-instructions.md

.windsurf/rules/rules.md

.continuerc.json

Process

1. Detect and Assess Configurations

for f in CLAUDE.md GEMINI.md AGENTS.md .cursorrules .github/copilot-instructions.md \
  .windsurf/rules/rules.md .continuerc.json; do
  [ -f "$f" ] && wc -l "$f"
done
find .cursor/rules -name "*.mdc" -exec wc -l {} \; 2>/dev/null

Size Thresholds

Discover Existing Skills

find . -name "SKILL.md" -type f 2>/dev/null | grep -v node_modules | \
  xargs grep -l "^name:" | while read -r f; do
  grep -m1 "^name:" "$f" | sed 's/name: //'
done

2. Analyze Conversation

• Corrections: Commands retried, assumptions proven wrong, missing prerequisites
• Discoveries: Undocumented patterns, integration quirks, environment requirements
• Improvements: Steps that should be automated or validated earlier

3. Categorize and Route Each Learning

project-setup

environment-setup

Routing Decision Tree

1. Is this a multi-step automated workflow (>5 steps)?
   • YES → Create new skill (proceed to Step 5, Route C)
   • NO → Continue
2. Does an existing skill cover this topic?
   • YES → Update that skill
   • NO → Continue
3. Is the target config file oversized (>500 lines)?
   • YES → Create new skill OR offer refactoring (see Step 4)
   • NO → Continue
4. Is this learning situation-specific (applies to narrow context)?
   • YES → Create new skill with

     globs

     or context constraints
   • NO → Add to config file

Size-Based Rules

Skill Relevance Matching

description

4. Present and Confirm

**[Category]**: [Brief description]
- Source: [What happened in conversation]
- Proposed change: [Exact text or file to add]
- Destination: [Config file] ([current] → [projected] lines)

Handle Size Threshold

Adding this learning would bring [filename] to [X] lines (threshold: [Y]).

Options:
1. Add learning anyway (not recommended)
2. [Refactor](references/refactoring.md) existing content to skills first, then add
3. Create a new skill for this learning instead
4. Skip this config file

5. Apply Changes

Route A: Add to Config File

• Find appropriate section, preserve existing structure
• Append to relevant section or create new section if needed

• Legacy

  .cursorrules

  : Treat like markdown, append content
• Modern

  .cursor/rules/*.mdc

  : See references/format-cursor-mdc.md

.continuerc.json

• Update

  customInstructions

  field, preserving existing content
• See references/format-continue.md

Route B: Update Existing Skill

1. Read the skill file:

   skills/[name]/SKILL.md

2. Find appropriate section or create new one
3. Append learning, maintaining the skill's existing structure
4. If skill has references, consider adding to reference file instead

## [New Section or append to existing]

[Learning content formatted as guidance or workflow step]

Route C: Create New Skill

skills/[name]/SKILL.md

---
name: [learning-topic]
description: [What this handles and when to use it - triggers belong here, not in body]
---

# [Learning Topic]

[Learning content structured as workflow]

## Process

### 1. [First Step]
[Details]

6. Verify Changes

✓ Added to [file path]:
  [Section name]
  > [First 2-3 lines of added content...]

7. Summarize

• Config files modified (with full paths)
• Sections updated in each file
• Any skills created

Examples

add-component

Edge Cases

Guidelines