knowledge-graph

Three-Layer Memory System — automatic fact extraction, entity-based knowledge graph, and weekly synthesis. Manages life/areas/ entities with atomic facts and living summaries.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./clawdbot/knowledge-graph/SKILL.md

Quality

Content

76%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 skill body is a lean, well-structured, actionable instruction set with a precise data model and numbered workflows. Its main weakness is the lack of explicit validation/feedback loops in the batch Weekly Synthesis workflow, which caps workflow clarity.

Suggestions

Add an explicit validation step to Weekly Synthesis (e.g., 'After rewriting, re-read summary.md and confirm every active fact is reflected and no superseded fact remains'), with a fix-and-retry loop.

Insert a duplicate-check checkpoint directly into the Fact Extraction workflow steps rather than only in the Fact Rules list.

Consider splitting the JSON schema / data model into a short reference file if the skill grows, to keep SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized with tight sections (Data Model, Fact Rules, Workflows, Safety Boundaries); it assumes Claude's competence and avoids explaining concepts Claude already knows, with every list earning its place.	5 / 5
Actionability	Provides concrete, actionable guidance — exact directory layout, a full JSON schema with typed fields, a runnable mkdir command, and step-by-step workflows — but as an instruction-only skill it has minor gaps (no extraction code), keeping it just short of fully copy-paste ready.	4 / 5
Workflow Clarity	The three workflows are clearly numbered and sequenced, but Weekly Synthesis is a batch/destructive operation (rewriting summary.md across multiple entities) with no explicit validate→fix→retry feedback loop, which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Content is well-structured into clearly headed sections with no nested references and no content that clearly belongs in a separate file, though at ~107 lines it slightly exceeds the under-50-line simple-skill exception that would allow a 5.	4 / 5
	Total	16 / 20 Passed

Description

58%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 clearly conveys what the skill does across its three layers and names concrete capabilities, but it omits any explicit 'when to use' trigger guidance and leans on some non-natural jargon. Adding a 'Use when...' clause with natural user phrases would raise both completeness and trigger-term quality.

Suggestions

Add a 'Use when...' clause naming natural triggers (e.g., 'Use when the user asks to remember, recall, or summarize facts about people, companies, or projects').

Replace or supplement jargon like 'Three-Layer Memory System' and 'living summaries' with terms users actually say.

Include common synonyms/file cues (e.g., 'knowledge graph', 'entity memory', 'facts.jsonl') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete capabilities — 'automatic fact extraction, entity-based knowledge graph, and weekly synthesis' and 'Manages life/areas/ entities with atomic facts and living summaries' — listing multiple specific actions, though slightly abstract rather than fully comprehensive.	4 / 5
Completeness	The 'what' is clearly stated (extraction, graph, synthesis, entity management), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Relevant keywords like 'fact extraction', 'knowledge graph', and 'summaries' appear, but jargon such as 'Three-Layer Memory System' and 'living summaries' is not natural user speech and common synonyms ('remember', 'recall', 'what do we know about') are missing.	3 / 5
Distinctiveness Conflict Risk	The entity-based knowledge-graph model with 'life/areas/ entities' and 'atomic facts' is a fairly distinct niche with only minor overlap risk against generic memory or note-taking skills.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jdrhyne/agent-skills
Path: clawdbot/knowledge-graph/SKILL.md
Commit: 439cd3a

Reviewed: 8 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.