/learn
Manually record an insight, correction, preference, or rule that the agent should remember for future tasks.
$ npx -y skills add CoWork-OS/CoWork-OS --skill learn --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/learn
Context preview
The summary Claude sees to decide when to auto-load this skill.
Manually record an insight, correction, preference, or rule that the agent should remember for future tasks.
SKILL.md
learn.SKILL.mdname: learn
description: "Manually record an insight, correction, preference, or rule that the agent should remember for future tasks."
Learn
Purpose
Manually record an insight, correction, preference, or rule that the agent should remember for future tasks.
Routing
- Use when: Use when the user explicitly wants to teach the agent something, record a preference, save a correction, or store a rule for future tasks.
- Do not use when: Don't use for general conversation, one-time instructions that don't need to be remembered, or when the user is just chatting.
- Outputs: Persisted learning in memory system and .cowork/MEMORY.md file.
- Success criteria: Learning is stored in memory and written to .cowork/MEMORY.md with confirmation to the user.
Trigger Examples
Positive
- Use the learn skill for this request.
- Help me with learn.
- Use when the user explicitly wants to teach the agent something, record a preference, save a correction, or store a rule for future tasks.
- Learn: provide an actionable result.
Negative
- Don't use for general conversation, one-time instructions that don't need to be remembered, or when the user is just chatting.
- Do not use learn for unrelated requests.
- This request is outside learn scope.
- This is conceptual discussion only; no tool workflow is needed.
Parameters
| Name | Type | Required | Description | |---|---|---|---| | what | string | Yes | The insight, correction, preference, or rule to remember | | category | select | No | Type of learning |
Runtime Prompt
- Current runtime prompt length: 1153 characters.
- Runtime prompt is defined directly in `../learn.json`.
Read more
name: learn description: "Manually record an insight, correction, preference, or rule that the agent should remember for future tasks."
Learn
Purpose
Manually record an insight, correction, preference, or rule that the agent should remember for future tasks.
Routing
- Use when: Use when the user explicitly wants to teach the agent something, record a preference, save a correction, or store a rule for future tasks.
- Do not use when: Don't use for general conversation, one-time instructions that don't need to be remembered, or when the user is just chatting.
- Outputs: Persisted learning in memory system and .cowork/MEMORY.md file.
- Success criteria: Learning is stored in memory and written to .cowork/MEMORY.md with confirmation to the user.
Trigger Examples
Positive
- Use the learn skill for this request.
- Help me with learn.
- Use when the user explicitly wants to teach the agent something, record a preference, save a correction, or store a rule for future tasks.
- Learn: provide an actionable result.
Negative
- Don't use for general conversation, one-time instructions that don't need to be remembered, or when the user is just chatting.
- Do not use learn for unrelated requests.
- This request is outside learn scope.
- This is conceptual discussion only; no tool workflow is needed.
Parameters
| Name | Type | Required | Description | |---|---|---|---| | what | string | Yes | The insight, correction, preference, or rule to remember | | category | select | No | Type of learning |
Runtime Prompt
- Current runtime prompt length: 1153 characters.
- Runtime prompt is defined directly in `../learn.json`.
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.
Repo: CoWork-OS/CoWork-OS
Other skills on cowork-os.
- /attack-path-analysis
Use when Codex is already in the attack-path-analysis phase of a security scan or the user explicitly asks to trace a security finding from source to sink and calibrate severity. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.
Open skill - /deep-security-scan
Use when the user asks for a deep, exhaustive, multi-pass, or variance-reducing repository-wide Codex Security scan. Run repeated independent repository-wide discovery passes with worker-specific threat models, semantically merge candidates, synthesize one canonical validation
Open skill - /finding-discovery
Use when Codex is already in the finding-discovery phase of a security scan or the user explicitly asks to discover candidate security findings in a repository or code change. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.
Open skill - /fix-finding
Use when the user explicitly asks to fix and verify a validated or plausible security finding. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.
Open skill - /security-diff-scan
Use when the user asks for a security review of a pull request, commit, branch diff, working-tree patch, or other Git-backed change set.
Open skill - /security-scan
Use when the user asks for a repository-wide or scoped-path security scan.
Open skill