Install
$ agentstack add skill-robabby-claude-skills-remember ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Remember
Store content in the Obsidian memory system as a browseable Markdown file.
Workflow
- Parse the content to remember from $ARGUMENTS
- If no arguments provided, ask what should be remembered
- Determine memory type based on content:
episodic: Events, experiences, things that happened ("We decided...", "The session where...")semantic: Facts, knowledge, definitions ("The API uses...", "Vault path is...")procedural: How to do things, patterns, processes ("To deploy, run...", "Pattern for X...")strategic: Plans, decisions, approaches ("We chose X because...", "Next steps...")
- Assess importance (0.0 to 1.0):
- 0.9-1.0: Critical decisions, core project context
- 0.7-0.8: Important patterns, significant learnings
- 0.5-0.6: Useful context, moderate relevance
- 0.3-0.4: Minor details, low priority
- Extract concepts (keywords for search):
- Terms someone might search for to find this memory
- Project names, technologies, people, patterns
- Example: ["metatron", "three.js", "deployment"]
- Generate filename:
YYYY-MM-DD - Brief Title.md
- Use today's date
- Create a brief descriptive title (3-6 words)
- Create the memory file in the appropriate folder:
/Areas/AI/Memory/Episodic//Areas/AI/Memory/Semantic//Areas/AI/Memory/Procedural//Areas/AI/Memory/Strategic/
- Confirm what was stored
File Template
---
created: {today's date}
type: {episodic|semantic|procedural|strategic}
importance: {0.0-1.0}
concepts: [{list, of, keywords}]
source: explicit
---
# {Title}
{Content - expanded with context}
## Context
{Why this matters, when it applies}
Examples
User: /remember We decided to use commands instead of skills for Hexis integration to avoid the collision bug
-> Create Areas/AI/Memory/Strategic/2026-01-04 - Commands Over Skills Decision.md -> type: strategic, importance: 0.85, concepts: [hexis, commands, skills, architecture]
User: /remember Rob's PKM vault path is /Users/rob/Documents/PKM
-> Create Areas/AI/Memory/Semantic/2026-01-04 - PKM Vault Path.md -> type: semantic, importance: 0.7, concepts: [pkm, vault, path, obsidian]
User: /remember To fix React hydration errors, use useState + useEffect instead of useMemo with random values
-> Create Areas/AI/Memory/Procedural/2026-01-04 - React Hydration Fix Pattern.md -> type: procedural, importance: 0.75, concepts: [react, hydration, ssr, usememo, useeffect]
Response Format
"Remembered: [title] (type: X, importance: Y) Saved to: Areas/AI/Memory/{Type}/{filename}"
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: robabby
- Source: robabby/claude-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.