Name: openviking-memory
Rating: 69.6 (1 reviews)
Author: volcengine

openviking-memory

Work with OpenViking, the persistent context database behind this agent's memory. Use it whenever the user refers to earlier sessions or shared history ("like last time", "what did we decide"), asks to remember or forget something, shares files, URLs, or repos worth keeping, or when the task needs context this session does not have — even if nobody says the word "memory". Also use it when the user asks where memories are stored: per project, per folder, or shared between repositories. Covers choosing between context search, find, list search, and grep, reading viking:// URIs, and when (not) to write.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is openviking-memory in volcengine/OpenViking

Quality

Content

75%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.

A lean, well-structured operational skill that gives concrete tool-selection guidance, a clear session lifecycle, and proper safeguards around destructive operations. It defers detail appropriately to a sibling skill and external docs rather than inlining them.

Suggestions

Add one or two concrete MCP tool-call invocation examples (e.g. a search mode='context' call) to close the actionability gap.

Tighten the explanatory asides in the lifecycle and writing sections to push conciseness toward fully lean.

Consider an explicit validate/retry note for add_resource's async ingestion so the workflow feedback loop is complete rather than just 'report ingestion started'.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no explaining what databases, grep, or URIs are) and stays operational, but a few explanatory asides like 'retrieval quality degrades as the store fills with noise' and 'this is why you rarely need remember' could be trimmed slightly.	4 / 5
Actionability	Provides concrete tool-by-tool selection guidance, a copy-paste-ready JSON config block, a named env var (OPENVIKING_PEER_ID), and an exact config path, but includes no actual MCP tool-call invocation syntax, which is a minor gap for an instruction-style skill.	4 / 5
Workflow Clarity	The Start/During/Data-in/End lifecycle is a clear sequenced process with checkpoints (check injected context before searching; expand hits with read before relying), and the destructive 'forget' op carries an explicit confirm-with-user + exact-URI safeguard, though there is no full validate-fix-retry feedback loop.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with one-level-deep, well-signaled deferrals (Experiences -> ov-experience-memory skill; CLI -> external docs URLs); no bundle files exist, and the single-file structure is appropriately split, with only minor organization headroom.	4 / 5
	Total	16 / 20 Passed

Description

95%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, third-person description that clearly answers both what and when, with rich natural trigger phrases and a distinct niche. Voice is appropriately third person; only minor specificity gaps around the write-side tool names prevent a perfect specificity score.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — 'choosing between context search, find, list search, and grep', 'reading viking:// URIs', and 'when (not) to write' — but stops short of naming the write-side tools (remember/add_resource/forget), leaving minor coverage gaps.	4 / 5
Completeness	Explicitly states what the skill does ('persistent context database behind this agent's memory', retrieval-tool selection, URI reading, when to write) and when to use it via a concrete 'Use it whenever...' clause with multiple trigger scenarios.	5 / 5
Trigger Term Quality	Includes natural user-speech quotes ('like last time', 'what did we decide') plus synonyms for remembering/forgetting and storage-scope phrasings ('per project, per folder'), giving comprehensive coverage of terms users would actually say.	5 / 5
Distinctiveness Conflict Risk	The 'persistent context database behind this agent's memory' framing plus memory-centric trigger phrases carve a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: volcengine/OpenViking
Path: examples/codex-memory-plugin/skills/openviking-memory/SKILL.md
Commit: 2251aa1

Reviewed: 3 days ago

Table of Contents

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.