Skip to content

BuilderIO/agent-native / templates/analytics/.builder/skills/learn

Extract key learnings from the current chat thread and save them to docs/learnings.md. Use this skill when the user types "/learn" or asks to save learnings from the conversation.

Learn Skill

When to Use

  • User types /learn in chat
  • User asks to "save this as a learning", "remember this", or "add this to learnings"
  • User corrects you and you want to persist that correction for future sessions

How It Works

  1. Review the full conversation thread
  2. Identify corrections, preferences, data mappings, workflow insights, and gotchas
  3. Save each learning via POST /api/learn
  4. Confirm what was saved

API Endpoint

POST /api/learn

Appends a structured entry to docs/learnings.md.

Structured entry (preferred for individual learnings):

{
  "category": "User Preferences",
  "insight": "Always filter out internal team emails when showing customer-specific activity",
  "source": "User correction during customer dashboard session"
}

Raw markdown (for complex multi-line entries):

{
  "rawMarkdown": "### Customer Data\n\n**Example Corp** org ID: `example-org-id`. Primary contact: jane@example.com."
}

GET /api/learn

Returns the current contents of docs/learnings.md as { content: string }.

Valid Categories

Use one of the existing section headers from docs/learnings.md:

  • Agent Behavior Rules
  • Customer Data
  • User Preferences
  • UI Patterns
  • Dashboard Data Fetching Pattern
  • Reusable Scripts
  • Cross-Referencing Customers Across Services

Use Other if none fit — the learning will be appended at the end of the file.

What to Extract

When reviewing a thread, focus on:

SignalExample
User corrections"No, that metric should use signup not sign_up"
Data source mappings"Example Corp org IDs are X, Y, Z"
Query patterns"Always join on dim_hs_contacts for customer lookups"
Preferences"I prefer stacked bar charts for per-user breakdowns"
Gotchas"The data column is JSON — use JSON_VALUE() to extract"
Workflow insights"Check Grafana before looking at code for incidents"

Skip obvious or trivial observations. Each learning should be actionable — what to do, what not to do, and why.

Example Flow

User types /learn. Agent responds:

  1. Scan the thread for corrections and insights
  2. For each learning found, call POST /api/learn:
    POST /api/learn
    { "category": "Customer Data", "insight": "Example Corp org ID is `example-org-id`", "source": "Thread with Steve" }
    
  3. Summarize what was saved:

    Saved 3 learnings to docs/learnings.md:

    • Customer Data: Example Corp org ID is example-org-id
    • User Preferences: Use dark theme for all exported charts
    • Agent Behavior Rules: Always check Sentry before investigating code for error spikes

Gotchas

  • Always read docs/learnings.md first to avoid duplicating existing entries
  • Keep insights concise — one actionable point per entry
  • Use the structured format (category + insight + source) for most entries; raw markdown only for complex multi-line content
  • The source field is optional but helpful for traceability
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 466kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 196kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 196kUpdated Claude CodeCodexVerifiedInstall