SKILLEMALL.ai
GitHub ↗ RU Sign in

BB mem9

Persistent cloud memory for OpenClaw agents. Use when users say: - "install mem9" - "setup memory" - "add memory plugin" - "openclaw memory" - "mem9 onboarding" - "memory not working" - "import memories" - "upload sessions"

LeoYeAI/openclaw-master-skills Agent Skills author: LeoYeAI MIT 2 files body ≈ 5 766 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Persistent cloud memory for OpenClaw agents.

As a process B 67/100 · Nearly there — weak spots: result and completion, inputs and preconditions, consistency

ProcedureAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
76/100
safety, quality, tests
Safety 60%
75
Quality 40%
78
Run on models
none yet
Process rating
B
67/100
Nearly there
Inputs and preconditions w 11
0
Result and completion w 14
40
Consistency w 8
40
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 5

✓ No critical or high findings

Medium and low: 5
  • medium Exfiltration net-credential-use SKILL.md:517
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "X-API-Key: $API_KEY" "$API/memories?q=postgres&limit=5"
  • medium Exfiltration net-credential-use SKILL.md:518
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "X-API-Key: $API_KEY" "$API/memories?tags=tech&source=agent-1"
  • medium Exfiltration net-credential-use SKILL.md:524
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "X-API-Key: $API_KEY" "$API/memories/{id}"
  • medium Exfiltration net-credential-use SKILL.md:525
    Credential used in a network call (verify the destination is the intended service)
    curl -sX PUT "$API/memories/{id}" -H "Content-Type: application/json" -H "X-API-Key: $API_KEY" -d '{"content":"updated"}'
  • medium Exfiltration net-credential-use SKILL.md:526
    Credential used in a network call (verify the destination is the intended service)
    curl -sX DELETE "$API/memories/{id}" -H "X-API-Key: $API_KEY"

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5766 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "keywords"
  • note edit-residue the text marks something as outdated (lines 27, 154, 159, 169, 379, 451): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 67/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Result and completion. Does not say what the result is
  • 40Consistency. Frontmatter name (mem9) differs from the folder (mem9-ai)
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 70Execution cost. Instruction body is 5766 tokens
  • 100Steps. 71 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 10 branches, has a failure section
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • low 16 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 8 example trigger phrases
  • +3Description length 224: enough signal without eating the budget
  • +4Structure: 28 headings
  • +3Step-by-step instructions: 71 items
  • +4Has examples (21 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.