CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ac-knowledge-graph

Manage knowledge graph for autonomous coding. Use when storing relationships, querying connected knowledge, building project understanding, or maintaining semantic memory.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ac-knowledge-graph/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 body is an efficient, honest overview: a compact Quick Start with real code that matches the bundled implementation, and a correct pointer to the script for the full API. Its gaps are the undefined project_dir, the unshown initialize() step, and a slightly redundant Purpose line.

Suggestions

Make the Quick Start fully copy-paste ready: import Path, define project_dir (e.g. graph = KnowledgeGraph(Path("."))) and show the await graph.initialize() call before adding entities.

Show how to consume query results (e.g. what the returned relations/entities look like) so the read path is as actionable as the write path.

Drop the redundant Purpose section or fold it into the intro line to trim the one piece of content that duplicates the description.

DimensionReasoningScore

Conciseness

The body is lean with no concept over-explanation, but the one-line Purpose section ("Maintains a knowledge graph of project concepts, relationships, and learnings for intelligent decision-making") merely restates the description — a minor instance of over-explanation that could be trimmed. Well above anchor 3 since everything else earns its place.

4 / 5

Actionability

The Quick Start shows real, mostly executable code whose async methods (add_entity, add_relation, query) match the actual scripts/knowledge_graph.py implementation. Minor gaps keep it from 5: project_dir is undefined, the initialize() step is never shown, and there is no handling of what query() returns.

4 / 5

Workflow Clarity

As a simple, single-purpose skill the Quick Start presents one unambiguous usage flow, and the code correctly reflects the real API. Not 5 because the undefined project_dir and omitted initialization leave slight ambiguity about the exact sequence to get started.

4 / 5

Progressive Disclosure

The body is under 50 lines with clear sections (Purpose, Quick Start, API Reference) and a single one-level-deep reference to scripts/knowledge_graph.py, which is a real file in the bundle. Per the simple-skill exception, well-organized sections with no need for external references earn the top score.

5 / 5

Total

17

/

20

Passed

Description

62%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.

The description follows the correct structure — third-person what-statement followed by an explicit multi-trigger "Use when" clause — and stays concise. Its main weakness is abstraction: 'Manage' and the listed activities describe a domain rather than concrete capabilities, and trigger terms lack synonym coverage.

Suggestions

Replace the generic verb 'Manage' with concrete capabilities, e.g. 'Create entities, add typed relations, and query connected knowledge in a persistent project knowledge graph.'

Add natural trigger synonyms users would actually say, such as 'entities', 'connections', 'graph memory', or 'project context', to broaden keyword coverage.

Clarify what 'autonomous coding' means in this context or drop it if it is not a trigger users would mention, to sharpen distinctiveness.

DimensionReasoningScore

Specificity

"Manage knowledge graph for autonomous coding" names the domain, and the trigger clause lists "storing relationships, querying connected knowledge, building project understanding" — but these are abstract verbs rather than concrete operations (no mention of creating entities, adding relations, or running queries). It names the domain and a few actions without comprehensive, specific coverage.

3 / 5

Completeness

Both what ("Manage knowledge graph for autonomous coding") and when (explicit "Use when storing relationships, querying connected knowledge, building project understanding, or maintaining semantic memory") are present. Not 5 because the 'what' is generic — 'Manage' gives no concrete capabilities.

4 / 5

Trigger Term Quality

Includes relevant keywords like "knowledge graph", "relationships", and "semantic memory", but misses common variations a user would naturally say such as "entities", "connections", or "graph database". Some relevant keywords without synonym coverage.

3 / 5

Distinctiveness Conflict Risk

"Knowledge graph", "autonomous coding", and "semantic memory" carve a reasonably distinct niche, so it is mostly distinguishable. Not 5 because it could still overlap with general memory/notes/project-context skills and has no fully distinct trigger phrasing like file extensions or unique tool names.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

fernandezbaptiste/Skrillz

Path

skills/ac-knowledge-graph/SKILL.md

Revision

93ed392

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill