defragmenting-memory

Included with Lifetime

$97 forever

Decomposes and reorganizes agent memory files into focused, single-purpose components. Use when memory has large multi-topic blocks, redundancy, or poor organization. Trigger phrases: "defrag memory", "reorganize memory", "clean up memory files", "split memory blocks".

AI Agents

What this skill does


# Memory Defragmentation

> **Requires context-repo extension** with memory at `.pi/memory/`

Splits large, multi-purpose memory blocks into focused single-purpose files
with hierarchical `/` naming.

## When to Use

- Memory blocks have redundant information
- Files mix multiple unrelated topics
- Memory lacks structure (walls of text)
- After major project milestones
- Every 50-100 conversation turns

## Workflow

### Step 1: Backup (MANDATORY)

Use the `memory_backup` tool before proceeding. This is your safety net.

### Step 2: Analyze Current Memory

```bash
find .pi/memory -name '*.md' | while read f; do
  echo "=== $f ($(wc -l < "$f") lines) ==="
  head -5 "$f"
  echo
done
```

For each file, determine:

- Does it serve 2+ distinct purposes? → needs splitting
- Is it >40 lines? → candidate for splitting
- Does it overlap with another file? → consolidate

### Step 3: Decompose

Split multi-purpose blocks into focused files using hierarchical naming:

**Before:**

```
system/project.md  (80 lines mixing overview, tooling, conventions, gotchas)
```

**After:**

```
system/project/overview.md
system/project/tooling.md
system/project/conventions.md
system/project/gotchas.md
```

Use `memory_write` for each new file, then delete the original:

```bash
rm .pi/memory/system/project.md
```

### Step 4: Clean Up

For each file (new and existing):

- Add markdown structure (headers, bullets)
- Remove redundancy across files
- Remove speculation ("probably", "maybe")
- Keep only actionable, concrete information
- Resolve contradictions

### Step 5: Commit

```
memory_commit({ message: "refactor: defragment memory — split N files into M focused blocks" })
```

### Step 6: Report

Provide a summary:

- Files created (new decomposed blocks)
- Files modified (what changed)
- Files deleted (if any, explain why)
- Before/after file counts and line counts

## Evaluation Criteria

1. **DECOMPOSITION** — Each file has ONE clear purpose described by its filename
2. **STRUCTURE** — Headers, bullets, scannable at a glance
3. **CONCISENESS** — No redundancy, no speculation, only unique value
4. **CLARITY** — Contradictions resolved, plain language, actionable
5. **ORGANIZATION** — General to specific within files, important first

## Naming Rules

- Use `/` hierarchy: `project/tooling/testing.md` (not `project-tooling-testing.md`)
- 2-3 levels of nesting
- ~40 lines max per file
- Descriptive frontmatter descriptions

## What to Preserve

- User preferences (sacred — never delete)
- Project conventions discovered through experience
- Important context for future sessions
- Learnings from past mistakes

## Rollback

If something goes wrong:

```
/memory-backups     # list available backups
/memory-restore <backup-name>
```

Files: 1

Size: 3.0 KB

Complexity: 8/100

Category: AI Agents

Source: https://github.com/edmundmiller/dotfiles/tree/main/packages/pi-packages/pi-context-repo/skills/defragmenting-memory

Related in AI Agents

skill-development

Included

Comprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.

AI Agentsscripts

reprompter

Included

Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.

AI Agentsscripts

adaptive-compaction

Included

Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.

AI Agentsscripts

agent-skill-creator

Included

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.

AI Agentsscripts

llm-wiki

Included

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.

AI Agentsscripts

skill-master

Included

Agent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.

AI Agentsscripts