SKILLEMALL.ai
GitHub ↗ RU Sign in

CB install-openviking-memory

Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin manager (ov-install as backup), wizard-based configuration, slot activation, gateway restart, verification, multi-tenant root keys, multi-instance and uninstall. The user needs no CLI knowledge — the agent runs everything and only asks for a few values. Assumes the OpenViking server is already running; it does NOT install the server. Trigger on: "install OpenViking", "set up memory", "configure memory plugin", "add long-term memory", "semantic memory", "RAG", "帮我装 OpenViking", "配置记忆插件", "安装记忆功能", "接入 OpenViking".

Not recommendedcritical or high security findings
volcengine/OpenViking Agent Skills author: volcengine AGPL-3.0 1 file body ≈ 9 279 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation.

As a process B 67/100 · Nearly there — weak spots: result and completion, execution cost, running it twice

IntegrationAI and agentstype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
C
79/100
safety, quality, tests
Safety 60%
82
Quality 40%
74
Run on models
none yet
Process rating
B
67/100
Nearly there
Result and completion w 14
0
Running it twice w 4
30
Execution cost w 6
40
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Concealment
If you install

The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.

For the author

Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. 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 · 1

  • high Concealment en-hide-from-user SKILL.md:159
    Instruction to hide actions from the user
    OpenViking initializes the managed `peers/` container for every user. Do not tell the user that `none` removes that container: it only avoids a concrete peer memory subtree. With `assistant` or `sende

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 9279 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 128, 133, 261, 290, 578, 594): 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

  • 0Result and completion. Does not say what the result is
  • 30Running it twice. 56 mutating operations with no state check
  • 40Execution cost. Instruction body is 9279 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 73 steps, 1 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 19 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 20 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (18 tags): a typed call is more reliable

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)
  • +3Description length 833: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 9 example trigger phrases
  • +4Structure: 52 headings
  • +3Step-by-step instructions: 73 items
  • +4Has examples (23 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.