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

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 well-structured, operational skill body that assumes Claude's competence and gives concrete tool-by-tool guidance plus a copy-paste config example and a clear session lifecycle with validation checkpoints. It sits at 4 across dimensions: solid but with minor room to tighten prose, add fuller tool-argument examples, and elaborate the retry loop.

Suggestions

Conciseness: tighten the 'Where memories are filed' prose to the operational rule (config keys, peer.id sharing, env-var fallback) and drop explanatory asides about scratch directories.

Actionability: add one short example call showing the argument shape for the primary retrieval tool (e.g. a search mode="context" invocation) so the most common path is copy-paste ready.

Workflow clarity: make the validate->fix->retry pattern explicit for add_resource ingestion (poll/read after the async start) rather than only noting it is asynchronous.

Dimension	Reasoning	Score
Conciseness	Lean and operational with no padded concept explanations Claude already knows, though the 'Where memories are filed' section carries some explanatory prose that could be trimmed slightly. Not a 5 because a few sentences are more explanatory than strictly necessary.	4 / 5
Actionability	Names concrete tools with their roles (search mode="context", find, grep/glob, read/list, remember, add_resource, forget) and gives a copy-paste-ready JSON config example; minor gaps are the absence of full argument examples for the MCP tools, though that is partly inherent to MCP tools.	4 / 5
Workflow Clarity	The 'A session's lifecycle' section gives a clear 4-step sequence with checkpoints ('Check it before searching... skip the tool call', 'Expand promising hits with read before relying on them'), and the destructive forget operation carries an explicit confirm-exact-URI validation, so it is not capped at 3. Missing a fully elaborated validate->fix->retry loop keeps it at 4 rather than 5.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with advanced operations deferred to the ov CLI and external docs URLs, and Experiences pointed out to a separate skill rather than inlined. No bundle files exist to verify, and the structure is good with only minor organization gaps, so 4 rather than 5.	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 description that clearly states the skill's purpose and gives concrete, natural-language triggers including quoted user phrasings and synonyms. Voice is third person throughout. Minor tightening of the action list could push specificity to a 5.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('choosing between context search, find, list search, and grep, reading viking:// URIs, and when (not) to write') but presents them as a coverage summary rather than crisp enumerated actions, leaving minor gaps.	4 / 5
Completeness	Explicitly answers both 'what' (work with the OpenViking persistent context database) and 'when' ('Use it whenever the user refers to earlier sessions...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Rich natural trigger phrases with synonyms and quoted user speech ('like last time', 'what did we decide', 'remember or forget', 'where memories are stored: per project, per folder'), covering the cases users actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche tied to a named system (OpenViking, viking:// URIs, per-project/per-folder memory) with distinct triggers and minimal overlap risk with 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/claude-code-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.