CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

surrealdb-agent-memory-docs

Look up official SurrealDB Agent Memory (formerly Spectron) documentation from surrealdb.com as markdown: quickstarts, mental model, ingest, sessions, recall, reasoning, SDKs, framework integrations, MCP server, REST API, CLI, and configuration. Use when building with or answering questions about SurrealDB Agent Memory. Read-only; sends only search terms and doc paths.

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An excellent single-file docs-lookup skill: dense and actionable with copy-paste curl/ssh commands, a genuinely non-obvious naming caveat, a well-organized section map, and a safety-oriented Rules section that includes prompt-injection defense and data-minimization guidance. Structure, error-recovery fallbacks, and token efficiency are all consistent with the top anchors.

DimensionReasoningScore

Conciseness

Every section carries non-obvious, load-bearing information — the partial Spectron rename ("Some pages still say \"Spectron\", so search for both names"), the section-map table, the SSH path-to-URL conversion rules, the host key, and the timeout pitfall — with no explanations of concepts Claude already knows. The four conversion examples each demonstrate a distinct transformation (nested index/, plain reference, index hub, root), so none is redundant; this matches the lean/efficient anchor rather than the 'minor trims' anchor.

5 / 5

Actionability

Guidance is copy-paste ready: "curl -s https://surrealdb.com/docs/agent-memory.md", three concrete ssh commands ("ls -R", "grep -rl 'recall'", "cat .../recall.mdx"), and a deterministic path-to-URL conversion spec with worked examples. Specific examples cover the common cases (hub fetch, topic fetch, search, read), matching the fully-executable anchor.

5 / 5

Workflow Clarity

This is a simple single-purpose skill whose action (fetch markdown docs) is unambiguous, with a clear entry sequence ("Start here" points 1 and 2, then the section map) and explicit error recovery ("If it differs, or SSH is unavailable, use HTTPS") plus a failure-prevention guard ("An unscoped grep -r can hit the 10s exec timeout"). It is read-only with no destructive or batch operations, so no validation cap applies, and the simple-skill exception holds.

5 / 5

Progressive Disclosure

The body is a clear overview with a well-signaled, one-level-deep section map ("All paths are relative to https://surrealdb.com/docs/agent-memory/. Append .md"), externalizing all detail to the live doc pages instead of inlining it; hub and index entry points ("Section hubs are integrations.md, cookbooks.md, and reference.md", llms.txt) aid navigation. No bundle files exist and none are needed, and nothing that belongs in separate files is inlined.

5 / 5

Total

20

/

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: it states exactly what it does (fetch official docs as markdown from surrealdb.com), scopes the topic coverage comprehensively, includes an explicit 'Use when...' trigger with the key product synonym, and adds a useful read-only/data-minimization qualifier. The only minor gap is that it describes a single lookup action rather than multiple distinct actions.

DimensionReasoningScore

Specificity

"Look up official SurrealDB Agent Memory (formerly Spectron) documentation from surrealdb.com as markdown" names one concrete action with its source and delivery format, and the colon list ("quickstarts, mental model, ingest, sessions, recall, reasoning, SDKs, framework integrations, MCP server, REST API, CLI, and configuration") comprehensively scopes the domain, plus the behavioral constraint "Read-only; sends only search terms and doc paths". It falls between the 3 anchor (only 1-2 actions, not comprehensive) and the 5 anchor (multiple distinct concrete actions): coverage is comprehensive but there is only a single action, so it is noticeably above the midpoint.

4 / 5

Completeness

It explicitly answers what ("Look up official ... documentation ... as markdown" with a full topic inventory) and when ("Use when building with or answering questions about SurrealDB Agent Memory") with concrete trigger phrasing. This clearly matches the 5 anchor rather than the 4 anchor, whose 'when' clause is less explicit.

5 / 5

Trigger Term Quality

"SurrealDB Agent Memory (formerly Spectron)" captures the essential synonym, and natural topic terms users would say — "recall", "ingest", "sessions", "MCP server", "REST API", "CLI", "SDKs" — are all present. This matches the comprehensive-coverage anchor; it is not a 4 because no natural variation or synonym for this domain is obviously missing.

5 / 5

Distinctiveness Conflict Risk

The named product ("SurrealDB Agent Memory", with the "formerly Spectron" alias) carves out a clear niche; it would only trigger for this specific product's docs and has minimal overlap with any other skill. Clear match to the 5 anchor.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

boranfurkan/discordlancer

Path

.claude/skills/surrealdb-agent-memory-docs/SKILL.md

Reviewed

Table of Contents

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.