CtrlK
BlogDocsLog inGet started
Tessl Logo

pantheon-ai/graphthulhu

Use and maintain the graphthulhu knowledge graph MCP to store investigations, architectural decisions, plans, and session context in a persistent Obsidian-backed vault; triggers automatically at session start, after analysis or investigations, when recording decisions, and when the user corrects stored knowledge.

99

Quality

99%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Quality

Discovery

100%

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

This is an excellent skill description that hits all the marks. It provides specific capabilities (knowledge graph storage for various content types), uses natural trigger terms users would actually say, explicitly states both automatic triggers and user-initiated scenarios, and has a clear distinctive niche with the named tool and backing store.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'store investigations, architectural decisions, plans, and session context' with clear technical context (Obsidian-backed vault, knowledge graph MCP).

3 / 3

Completeness

Clearly answers both what (maintain knowledge graph for storing investigations, decisions, plans, context) AND when (explicit 'use when' clause with multiple trigger scenarios plus automatic triggers like 'session start', 'after analysis').

3 / 3

Trigger Term Quality

Excellent coverage of natural user phrases: 'remember this', 'save for later', 'take notes', 'persist findings', 'track decisions', 'log results', 'maintain context between sessions', 'store knowledge' - these are terms users would naturally say.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with specific tool name 'graphthulhu', specific backing store 'Obsidian-backed vault', and clear niche around persistent knowledge/context storage that wouldn't conflict with general note-taking or document skills.

3 / 3

Total

12

/

12

Passed

Implementation

100%

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

This is an exemplary skill file that demonstrates excellent token efficiency while providing highly actionable guidance. The clear namespace conventions, explicit anti-patterns with BAD/GOOD examples, and well-structured workflow with validation checkpoints make this immediately usable. The progressive disclosure to reference files is well-executed with clear signaling.

DimensionReasoningScore

Conciseness

The content is lean and efficient, avoiding explanations of concepts Claude already knows. Every section serves a clear purpose with no padding or unnecessary context about what knowledge graphs are or how MCPs work.

3 / 3

Actionability

Provides concrete, executable command sequences with specific tool names and parameters. The Quick Commands section offers copy-paste ready workflows, and the anti-patterns include specific BAD/GOOD examples with actual function calls.

3 / 3

Workflow Clarity

Clear numbered workflow with explicit validation steps (check exists before create, verify before writing, confirm saved before continuing). The anti-patterns section reinforces validation requirements, and corrections workflow explicitly requires confirmation before proceeding.

3 / 3

Progressive Disclosure

Excellent structure with a concise overview, clear namespace table, and well-signaled one-level-deep references to workflow.md and tool-catalogue.md. Content is appropriately split between quick reference here and detailed steps in referenced files.

3 / 3

Total

12

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

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

Warning

Total

10

/

11

Passed

Reviewed

Table of Contents