agentleFS
dmzoneilldmzoneill/skills/memory-init/SKILL.md

memory-init

Skill2 starsChanged 19 days agoApache-2.0View on GitHub

Initialize or reset memory files to clean state. Use for fresh start, new project/sprint, or new machine. Preserves learned patterns by default. Use when user says "initialize memory", "reset memory", or "memory init".

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If confirm not true: output error and usage, stop

    line 22
  2. Distinctive:

    Keep last 10 backups, delete older

    line 29
  3. Very specific:

    Write patterns_backup back to learned/patterns.yaml

    line 49

“Common” is measured: kept by at least 6 in 10 of the 7 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

Memory Init - Reset Memory to Clean State

Backs up and resets state files. Optionally resets learned patterns and runbooks.

Inputs

InputTypeRequiredPurpose
confirmboolyesMust be true (safety)
reset_learnedboolfalseAlso reset patterns, runbooks, preferences
preserve_patternsbooltrueKeep error patterns when resetting learned

Workflow

1. Check Confirmation

  • If confirm not true: output error and usage, stop
  • "Must set confirm=true to proceed. This will clear your memory state."

2. Backup Before Init

  • Create memory/backups/YYYYMMDD_HHMMSS/
  • Copy: state/current_work, state/environments, learned/patterns, learned/tool_fixes, learned/tool_failures, learned/runbooks, learned/service_quirks, learned/teammate_preferences
  • Keep last 10 backups, delete older

3. Backup Patterns (if preserve_patterns)

  • Save learned/patterns.yaml content before reset

4. Reset State Files

  • current_work: active_issues=[], open_mrs=[], follow_ups=[], notes="Memory initialized"
  • environments: Template with stage, production, konflux (status unknown), ephemeral_namespaces=[]

5. Reset Learned (if reset_learned)

  • patterns: Clear unless preserve_patterns
  • runbooks: Empty with commit_format, branch_format from config
  • teammate_preferences: Empty
  • service_quirks: Empty

6. Restore Patterns (if reset_learned and preserve_patterns)

  • Write patterns_backup back to learned/patterns.yaml

7. Log Init

  • memory_session_log("Memory initialized", "reset_learned: X, preserve_patterns: Y")

8. Output Format

## ✅ Memory Initialized

### 💾 Backup Created

**Location:** memory/backups/YYYYMMDD_HHMMSS/
**Files backed up:** N

### State Files Reset

- ✅ state/current_work.yaml
- ✅ state/environments.yaml

### Learned Files Reset (if reset_learned)

- ✅ learned/runbooks.yaml
- ✅ learned/teammate_preferences.yaml
- ✅ learned/service_quirks.yaml
- ℹ️ learned/patterns.yaml - Preserved (if preserve_patterns)

---

Ready for a fresh start! Use /coffee to begin your day.

Key Details

  • Chains to: memory_view, bootstrap_knowledge
  • Requires: confirm: true - never proceed without it
  • Backup location: memory/backups/<timestamp>/

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.