Manage Memory

Organize, extract, prune, and verify Claude Code persistent memory files. Covers MEMORY.md as a concise index, topic extraction to dedicated files, staleness detection, accuracy verification against project state, and the 200-line truncation constraint. Use when MEMORY.md is approaching the 200-line limit, after a session produces durable insights worth preserving, when a topic section has grown beyond 10-15 lines and should be extracted, or when project state has changed and memory entries may be stale.

45 stars 4 forksProductivity & Notes

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add pjt222/agent-almanac --skill manage-memory
Manual install
git clone --depth 1 https://github.com/pjt222/agent-almanac.git /tmp/agent-almanac
mkdir -p ~/.claude/skills
cp -r /tmp/agent-almanac/i18n/caveman-lite/skills/manage-memory ~/.claude/skills/manage-memory

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Manage Memory

Maintain Claude Code's persistent memory directory so it stays accurate, concise, and useful across sessions. MEMORY.md is loaded into the system prompt on every conversation — lines after 200 are truncated, so this file must be a lean index pointing to topic files for detail.

## When to Use

- MEMORY.md is approaching the 200-line truncation threshold
- A session produced durable insights worth preserving (new patterns, architecture decisions, debugging solutions)
- A topic section in MEMORY.md has grown beyond 10-15 lines and should be extracted
- Project state has changed (renamed files, new domains, updated counts) and memory entries may be stale
- Starting a new area of work and checking whether relevant memory already exists
- Periodic maintenance between sessions to keep the memory directory healthy

## Inputs

- **Required**: Access to the memory directory (typically `~/.claude/projects/<project-path>/memory/`)
- **Optional**: Specific trigger (e.g., "MEMORY.md is too long," "just finished a major refactor")
- **Optional**: Topic to add, update, or extract

## Procedure

### Step 1: Assess Current State

Read MEMORY.md and list all files in the memory directory:

```bash
wc -l <memory-dir>/MEMORY.md
ls -la <memory-dir>/
```

Check the line count against the 200-line limit. Inventory existing topic files.

**Got:** Clear picture of total lines, number of topic files, and which sections exist in MEMORY.md.
Read the full skill on GitHub

Details

Skill name
manage-memory
Path
i18n/caveman-lite/skills/manage-memory/SKILL.md
License
MIT
Repo updated
18 November 2026

FAQ

What does the Manage Memory skill do?

Organize, extract, prune, and verify Claude Code persistent memory files. Covers MEMORY.md as a concise index, topic extraction to dedicated files, staleness detection, accuracy verification against project state, and the 200-line truncation constraint. Use when MEMORY.md is approaching the 200-line limit, after a session produces durable insights worth preserving, when a topic section has grown beyond 10-15 lines and should be extracted, or when project state has changed and memory entries may be stale.

How do I install the Manage Memory skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add pjt222/agent-almanac --skill manage-memory. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Manage Memory popular?

It lives in pjt222/agent-almanac, which has 45 GitHub stars and 4 forks, and is included in 1 curated skill list.

Related skills

Adapt Architecture

45

pjt222/agent-almanac

Execute structural metamorphosis using strangler fig migration, chrysalis phases, and interface preservation. Covers transformation planning, parallel running, progressive cutover, rollback design, and post-metamorphosis stabilization for system architecture evolution. Use when assess-form has classified the system as READY for transformation, when migrating from monolith to microservices, when replacing a core subsystem while dependents continue operating, or when any architectural change must be gradual rather than big-bang.

Software DevelopmentIn 1 list

Adaptic

45

pjt222/agent-almanac

Master skill composing the 5-step synoptic cycle for panoramic synthesis across multiple domains. Orchestrates meditate, expand-awareness, observe, awareness, integrate-gestalt, and express-insight into a coherent process that produces unified understanding rather than sequential compromise. Use when a problem genuinely spans 3+ domains and the interactions between domains matter more than depth in any one, when sequential analysis feels like compromise rather than integration, or before major architectural decisions affecting multiple stakeholders.

OtherIn 1 list

Add Puzzle Type

45

pjt222/agent-almanac

Scaffold a new puzzle type across all 10+ pipeline integration points in jigsawR. Creates the core puzzle module, wires it into the unified pipeline (generation, positioning, rendering, adjacency), adds ggpuzzle geom/stat layers, updates DESCRIPTION and config.yml, extends the Shiny app, and creates a comprehensive test suite. Use when adding a completely new puzzle type to the package or following the 10-point integration checklist to ensure nothing is missed end-to-end.

Testing & QAIn 1 list

Matter Briefing

43

AlsKozlov/ru-legal

One-pager status brief по конкретному matter'у — posture, risk, recent changes, next deadline, exposure, open questions. Flag'ает stale если updates не было > 30 дней. Используй когда пользователь говорит "brief по делу X", "what's status of matter Y", "обнови меня по делу Z", или perед meeting'ом с CEO / Board / outside counsel.

Productivity & Notes

Listen

45

pjt222/agent-almanac

Deep receptive attention to extract intent beyond literal words. Maps active listening from counseling psychology to AI reasoning: clearing assumptions, attending to full signal, parsing multiple layers (literal, procedural, emotional, contextual, constraint, meta), reflecting understanding, noticing what is unsaid, and integrating the whole picture. Use when a user's request feels ambiguous, when context suggests something different from the literal words, when previous responses have missed the mark, or before beginning a large task where misunderstanding intent would waste significant effor

Productivity & NotesIn 1 list

Meditate

45

pjt222/agent-almanac

AI meta-cognitive meditation for observing reasoning patterns, clearing context noise, and developing single-pointed task focus. Maps shamatha to task concentration, vipassana to reasoning pattern observation, and distraction handling to scope-creep and assumption management. Use when transitioning between unrelated tasks, when reasoning feels scattered or jumpy, before a task requiring deep sustained attention, after a difficult interaction that may color subsequent work, or when reasoning feels biased by assumptions rather than evidence.

Productivity & NotesIn 1 list

Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.