Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Memory Loop

ASecurity

Update project memory after completing a task, making a key decision, discovering a gotcha, or changing active goals. Use this skill at the end of any meaningful unit of work to write structured entries into .claude/memory/MEMORY.md following the project schema. Also use when the user asks to save memory, update memory, or record what was done.

30 stars
0 votes
0 copies
1 views
Added 6/11/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 6/11/2026

$npx -y skills add yucai0302/memory-loop --skill memory-loop --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Memory Loop?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Memory Loop
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yucai0302-memory-loop/badge)](https://www.skillsdirectory.com/skills/yucai0302-memory-loop)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: memory-loop
description: "Update project memory after completing a task, making a key decision, discovering a gotcha, or changing active goals. Use this skill at the end of any meaningful unit of work to write structured entries into .claude/memory/MEMORY.md following the project schema. Also use when the user asks to save memory, update memory, or record what was done."
---

# memory-loop — Write Protocol

You are writing structured entries into `.claude/memory/MEMORY.md`.
This file is the project's persistent memory. It survives between sessions.
Write accurately and concisely. Future agents (and you in a future session) will rely on this.

## Step 1 — Read the current schema

Read `.claude/memory/schema.yaml` to understand which sections exist, their format strings, and their `max_items` limits.

## Step 2 — Read the current MEMORY.md

Read `.claude/memory/MEMORY.md` to see what is already there.

## Step 3 — Determine what needs updating

Based on what just happened in this session, identify which sections need new entries:

| Trigger | Section to update |
|---|---|
| Task finished | **Completed** (add entry) + **Active Goals** (remove the done goal) |
| Technical decision made | **Decisions** (add entry) |
| Bug / constraint / trap discovered | **Gotchas** (add entry) |
| New work started | **Active Goals** (add entry) |
| Project overview changed | **Project Context** (rewrite) |

Only update sections that are actually affected. Do not rewrite unchanged sections.

## Step 4 — Apply format and max_items rules

- Use the exact format string from the schema for each section.
- After adding a new entry, if the section now has more than `max_items` entries, remove the oldest one(s) to stay within the limit.
- Never delete **Decisions** or **Gotchas** entries during a regular write — those are only pruned during compression.

## Step 5 — Write the file

Write the updated MEMORY.md back to disk.
Preserve the file header comment block at the top.
Do not change sections you did not touch.

## Step 6 — Confirm

Report briefly what you wrote:
> "Memory updated: added 1 Completed entry, removed Active Goal 'X'."

---

## Format reference (defaults — actual values come from schema.yaml)

```
## Active Goals
- [goal description] | started: YYYY-MM-DD

## Decisions
- YYYY-MM-DD | chose X over Y | reason: Z

## Gotchas
- [module] problem description → workaround / rule

## Completed
- YYYY-MM-DD | task description | outcome
```

Attribution

yucai0302yucai0302
View sourceSee grades on GitHubMore from yucai0302 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →