/Catalogue/Prompt/thedotmack/thedotmack-claude-mem-what-the

Origin: github

Communityv0.1.0PromptLicense: Apache-2.0 github.com/thedotmack/claude-mem/tree/main/plugin/skills/what-the

what-the

What the? Use when the user wants a plain-English breakdown of something technical — the who, what, where, why, and when.

by thedotmack · updated 10h ago · imported from GitHub

Watch · 0 Send for moderation

Installs0+0/7d

Security score92/100

Retention 14d0%

GitHub stars94.7K

Skill logic

0 tools · +3 prompt lines · 3 steps

Execution graph

SKILL.md

View on GitHub ↗

that sounds mad technical. explain to me the who, what, where, why, and when of this

Discussion

0 comments

No comments yet — start the thread.

/More from thedotmack/claude-mem

thedotmack· 10h agoCommunity

claude-mem-install

Prompts · TypeScript · v0.1.0

Use this when setting up claude-mem on Cursor: local or remote worker, local host-login observer or remote cmem.ai inference.

#ai#ai-agents#ai-memory

thedotmack· 10h agoSandbox

openclaw

Prompts · TypeScript · v0.1.0

This guide walks through setting up the claude-mem plugin on an OpenClaw gateway. By the end, your agents will have persistent memory across sessions via system prompt context injection, and optionally a real-time observation feed streaming to a messaging channel.

#ai#ai-agents#ai-memory

thedotmack· 10h agoCommunity

mem-search

Prompts · TypeScript · v0.1.0

Use this when the user asks to search memory, "did we already solve this?", "how did we do X last time?", or wants work from previous sessions.

#ai#ai-agents#ai-memory

thedotmack· 10h agoCommunity

host-observer

Prompts · TypeScript · v0.1.0

Use this when fulfilling claude-mem observer jobs on Grok Bot: reply only skip_summary or one full observation XML, never prose.

#ai#ai-agents#ai-memory

Security report

Grade: A+

Security audit score92/ 100

Community

Eligible for Verified review

[PASS] Prompt injection resistanceNo override, role-hijack or hidden-instruction patterns in prompt and tool text.
[PASS] Shell command sandboxingNo destructive, privilege-escalating or reverse-shell commands in scripts.
[PASS] Zero secret leakageNo literal API keys or tokens; env values are ${VAR} references.
[PASS] Network egress isolationNo patterns that ship context or credentials to external hosts.
[PASS] Minimal permission scopeDeclared permissions match what the entrypoint needs.
[PASS] Manifest integritySchema, tool names and parameter schemas are provider-compatible.
[PASS] Remote endpoint hygieneRemote servers speak TLS; handshake checks run in the dynamic stage.
[FAIL] Supply chain
mediumDP-04@ package.json
No npm lock file: installs resolve whatever the ranges allow today.
@better-auth/api-key@^1.6.16, better-auth@^1.6.16
[PASS] Sandbox behaviourNo dynamic findings. The runtime sandbox (DY-*) is not enabled yet.

Install

>synapth install thedotmack-claude-mem-what-the --target=claude-code

Or add to terminal

npx degit thedotmack/claude-mem/plugin/skills/what-the .claude/skills/what-the

Copies the skill directory (SKILL.md + scripts) into the project; Claude Code picks it up automatically.

Entry point

system prompt only

Permissions: none

Source repository

In skillsets

Not part of any skillset yet.

Assemble a skillset with it

Source repository

thedotmack/claude-mem

Language: TypeScript
License: Apache-2.0
Forks: 8.4K
Open issues: 296
Last push: 10h ago
Manifest: SKILL.md

ai ai-agents ai-memory anthropic artificial-intelligence chromadb claude claude-agent-sdk