Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Claude Memory Kit — measured AI agent skill | DecimalAI

rohitg00/claude-memory-kit

SkillScore88Maintained

Persistent memory system for Claude Code. Two-layer architecture (hot cache + knowledge wiki), safety hooks, /close-day end-of-day synthesis. Zero external dependencies.

agent-toolingby rohitg00

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Knowledge Management pack

decimalai skills pull rohitg00-claude-memory-kit

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/rohitg00-claude-memory-kit/SKILL.md

Raw file: /s/rohitg00-claude-memory-kit/SKILL.md ↗ · machine-readable summary at /s/rohitg00-claude-memory-kit.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

24 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 4h ago

Yes — +50% lift-40% tokens0% turns88% of whole cases pass with skill (21/24)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-03	✗→✓	▲ Improved	23%	0%
case-04	✗→✓	▲ Improved	-50%	0%
case-05	✗→✓	▲ Improved	-42%	0%
case-08	✗→✓	▲ Improved	-56%	0%
case-10	✗→✓	▲ Improved	-82%	0%

Showing 5 of 24 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

rohitg00 / awesome-claude-code-toolkit

skills/claude-memory-kit/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Claude Memory Kit

Your Claude agent remembers everything across sessions and projects.

What it does

Persistent memory — MEMORY.md hot cache + knowledge wiki with wikilinks]]
Multi-project support — per-project backlogs and context isolation
Safety hooks — prevent context loss during compression and long sessions
/close-day — one command captures your entire day
/tour — interactive guided walkthrough

Quick Start

bash
git clone https://github.com/awrshift/claude-memory-kit.git my-project
cd my-project
claude

Built from production

700+ sessions across 7 projects. Adapted from Karpathy/Cole Medin's knowledge base pattern, simplified for daily CLI use.

Want to see if rohitg00/claude-memory-kit would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.