Skip to content
Agentmart
Submit a tool

learn

Teach Campy a new pattern, procedure, or lesson.

Skill by engramist

IndexedApache-2.0
Write a review

Chalk Labs

Need help deploying learn?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/engramist-learn

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Teach Campy a new pattern, procedure, or lesson. Use after resolving a tricky issue, discovering a recurring pattern, establishing a new procedure, or when the user says "remember this" or "learn this."

Use cases: data

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/learn

What's inside

Skill name
learn
Description
Teach Campy a new pattern, procedure, or lesson. Use after resolving a tricky issue, discovering a recurring pattern, establishing a new procedure, or when the user says "remember this" or "learn this."
License
Apache-2.0
Instructions
76 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Campy Learn

Encode a new piece of knowledge into Campy's graph.

## When to Use

- You just resolved a tricky bug and want to remember the fix
- You discovered a recurring pattern (errors, workflows, timing)
- The user established a new procedure they want remembered
- The user explicitly says "remember this" or "don't forget"

## Process

1. Ask the user (or determine from context):
   - **What happened?** The situation or problem.
   - **What was the solution?** The fix, procedure, or decision.
   - **What triggers this?** When should this knowledge surface again?
     (error message, action pattern, time interval, domain area)

2. Determine the knowledge type:
   - **Lesson** — something learned from experience
     Call `upsert_lesson` with:
     - lesson_text: the lesson content
     - lesson_type: one of mistake|edge-case|optimization|architecture-principle
     - tags: relevant keywords

   - **Procedure** — a step-by-step process
     Call `register_plan` with:
     - goal: what the procedure achieves
     - steps: ordered list of steps
     - Include metadata: `{"procedure": true, "trigger": "<pattern>"}`

   - **Decision** — an architectural or design choice
     This is captured automatically by passive ingestion.
     Just make sure the decision is clearly stated in the conversation.

3. Confirm with the user that the knowledge was stored.

4. If the user specified a trigger pattern (e.g., "remind me when I run docker"),
   pass the trigger metadata in the `trigger` parameter of `upsert_lesson`.
   The trigger manifest is recompiled every sweep cycle (~5 minutes).
   After creation, the user can verify with `campy trigger list`.

## Trigger Metadata

When storing a Lesson with a trigger, pass the `trigger` parameter:

```json
{
  "trigger": {
    "pattern": "regex pattern to match tool input/output",
    "hook_type": "PreToolUse or PostToolUse",
    "tool": "Bash or Edit or Write (empty for all)",
    "project_scope": "optional project path (empty for all)"
  }
}
```

Example — remember that docker requires OD env vars:
```json
{
  "text": "OD docker containers require OAUTH_TOKEN and CLUSTER_ENV vars",
  "lesson_type": "edge-case",
  "trigger": {
    "pattern": "docker run|docker build|docker compose",
    "hook_type": "PreToolUse",
    "tool": "Bash"
  }
}
```

The manifest compiler picks this up on the next sweep and the
PreToolUse hook will inject the lesson text before any matching
Bash command runs.

From engramist/hippocampy, Apache-2.0.

More from engramist/hippocampy

Signals

Stars
0
Forks
0
Open issues
1
Last commit (this folder)
May 26, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from engramist

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get learn running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying learn?

CallGet help
Cite this page

learn skill. Agent Mart. https://agentmart.dev/skills/engramist-learn (last updated 2026-10-24)