agentleFS
NoaiRoxNoaiRox/specialist-agent/skills/remember/SKILL.md

remember

Skill2 starsChanged 9 months agoMITView on GitHub

Use when making a decision, choosing a convention, or learning a lesson that should persist across sessions.

69 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use agent-context-isolation, agentica-infrastructure and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 61 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Extract key info: - Don't store raw text

    line 155
  2. Distinctive:

    No duplicates: - Update existing if same topic

    line 157
  3. Distinctive:

    No secrets: - Never store credentials

    line 158

“Common” is measured: kept by at least 6 in 10 of the 61 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/remember - Save to Session Memory

Save decisions, preferences, and lessons that persist across sessions.

Input: $ARGUMENTS

Workflow

Step 1: Parse Input

Detect type of memory:

  • Decision: "Use X instead of Y because Z"
  • Preference: "Always use single quotes"
  • Pattern avoid: "Never use any types"
  • Pattern prefer: "Prefer composition over inheritance"
  • Lesson: "API changed and broke app. Solution: version contracts"

Step 2: Load Existing Memory

const memoryFile = '.claude/session-memory.json';
let memory = {};

if (exists(memoryFile)) {
  memory = JSON.parse(read(memoryFile));
} else {
  memory = {
    version: "1.0",
    projectId: getProjectName(),
    created: new Date().toISOString(),
    decisions: [],
    preferences: {},
    context: {},
    patterns: { avoided: [], preferred: [] },
    lessons: []
  };
}

Step 3: Add to Memory

For Decisions:

{
  "id": "d001",
  "date": "2024-01-15",
  "topic": "[extracted topic]",
  "decision": "[what was decided]",
  "reason": "[why]",
  "agent": "[current agent or 'user']"
}

For Preferences:

{
  "preferences": {
    "[category]": {
      "[key]": "[value]"
    }
  }
}

For Patterns:

{
  "patterns": {
    "avoided": ["[pattern]"],
    "preferred": ["[pattern]"]
  }
}

For Lessons:

{
  "lessons": [{
    "date": "2024-01-15",
    "issue": "[what happened]",
    "solution": "[how to fix]",
    "preventionRule": "[how to prevent]"
  }]
}

Step 4: Save Memory

memory.updated = new Date().toISOString();
write(memoryFile, JSON.stringify(memory, null, 2));

Output

──── /remember ────

✓ Saved to session memory

Type: [Decision | Preference | Pattern | Lesson]
Topic: [topic]
Content: [what was saved]

This will be recalled in future sessions.

Memory file: .claude/session-memory.json
Total memories: [N] decisions, [N] preferences, [N] patterns, [N] lessons

Examples

Remember a Decision

/remember Use Zustand for state management because it's simpler than Redux

Output:

✓ Saved to session memory

Type: Decision
Topic: State Management
Content: Use Zustand instead of Redux
Reason: Simpler

This will be recalled in future sessions.

Remember a Preference

/remember Always use single quotes in this project

Remember to Avoid

/remember Never use any types in TypeScript

Remember a Lesson

/remember The API changed format and broke parsing. Solution: Always create adapters with versioned contracts.

Rules

  1. Extract key info - Don't store raw text
  2. Categorize correctly - Decision vs preference vs pattern
  3. No duplicates - Update existing if same topic
  4. No secrets - Never store credentials

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.