Tessl • The management layer for AI agent skills

SkillPublic

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".

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The walkthrough half is exceptionally actionable with a tightly sequenced, validated workflow, but the skill is a 755-line monolith: the entire reference half (tool tables, config schema, uninstall, error recovery) is inlined rather than split into bundle files, and several rules and error strings are repeated. Actionability and workflow clarity are top-tier; conciseness and progressive disclosure are the drag.

Suggestions

Move Part 2 (Available Tools, Configuration Schema, Multi-Instance, Uninstall, Error Recovery) into references/ files (e.g. references/tools.md, references/config-schema.md, references/error-recovery.md) and keep SKILL.md as a concise walkthrough plus a one-level-deep index of those files.

Deduplicate repeated content: the identical Path A install command under 'Before falling back, also try the explicit registry prefix once', the peer-role flag-building rules (stated in STEP 4c, Path B, and STEP 7), and the root-key error text (STEP 4e, STEP 7, and the Multi-Tenant section) each need to appear once.

Trim the STEP 4c peer-role explanation — the prose, the 3-row table, and the legacy-alias notes overlap; a single compact table with the decision rules would preserve clarity at roughly half the tokens.

Dimension	Reasoning	Score
Conciseness	Mostly dense, genuinely novel domain content (no basic-concept padding), but noticeably duplicative: the Path A install command is repeated verbatim, peer-role flag rules are restated in STEP 4c, Path B, and STEP 7, and the root-key error text appears three times. This fits the 'mostly efficient but could be tightened' anchor, not 4, since the repetition plus inlined bulk reference exceeds minor trimming.	3 / 5
Actionability	Fully executable throughout: exact commands per OS, literal JSON output schemas for the wizard and status, a decision matrix keyed to exact error strings ('Root API key detected. Missing: --account-id, --user-id'), and ready-to-send CN/EN message templates. Copy-paste ready and covers the common cases, matching the top anchor.	5 / 5
Workflow Clarity	STEP 0–10 are strictly sequenced with explicit validation checkpoints (STEP 5 connectivity check, STEP 10's 'configured: true and slotActive: true and health.ok: true' success gate) and feedback loops (error-recovery table routing back to specific steps). Risky overrides (--force-slot, --allow-offline) require explicit user consent — matching the top anchor.	5 / 5
Progressive Disclosure	No bundle files exist; roughly 400 lines of tool parameter tables, config schema, uninstall, and error-recovery reference are inlined in SKILL.md where they belong in separate reference files. The Part 1/Part 2 split with 'Read on demand' provides real structure, so this is above the 2 anchor, but it matches the 3 anchor ('content that should be separate is inline') rather than 4 because no actual file-level split exists and the body far exceeds overview size.	3 / 5
	Total	16 / 20 Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it states concrete capabilities comprehensively, gives explicit bilingual trigger phrases, defines scope boundaries, and uses third-person voice. The only weakness is that several generic trigger terms ('set up memory', 'RAG') create minor overlap risk with other memory-related skills.

Dimension	Reasoning	Score
Specificity	The description enumerates the full workflow concretely — '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' — which matches the comprehensive-coverage anchor. It is not 4 because there are no meaningful gaps in the action coverage for this task.	5 / 5
Completeness	It explicitly answers what ('automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session)') and when ('Trigger on: "install OpenViking", ...') with concrete trigger phrases, and adds scope boundaries ('Assumes the OpenViking server is already running; it does NOT install the server').	5 / 5
Trigger Term Quality	Triggers cover natural phrasings across verb and noun synonyms — 'install OpenViking', 'set up memory', 'configure memory plugin', 'add long-term memory', 'semantic memory', 'RAG' — plus Chinese equivalents ('帮我装 OpenViking', '配置记忆插件'). This matches the comprehensive-synonyms anchor rather than the good-but-few-missing 4 anchor.	5 / 5
Distinctiveness Conflict Risk	Product-specific triggers like 'install OpenViking' and '接入 OpenViking' are highly distinct, but generic terms ('set up memory', 'semantic memory', 'RAG') could overlap with other memory or RAG skills — matching the mostly-distinct/minor-overlap anchor. It is not 5 because those generic triggers are not uniquely tied to this skill.	4 / 5
	Total	19 / 20 Passed

Validation

75%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (785 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	12 / 16 Passed

Repository: volcengine/OpenViking
Path: examples/openclaw-plugin/skills/install-openviking-memory/SKILL.md
Revision: 4ab22a4

Reviewed: 7 days ago

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.

install-openviking-memory

Table of Contents

Is this your skill?