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.
51
41%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./clawdbot/knowledge-graph/SKILL.mdQuality
Discovery
17%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 communicates the architectural concept of the skill (three-layer memory system) but relies heavily on internal jargon rather than user-facing language. It lacks an explicit 'Use when...' clause and natural trigger terms that would help Claude select this skill when users ask about remembering things, recalling past conversations, or managing personal knowledge.
Suggestions
Add an explicit 'Use when...' clause with natural trigger terms like 'remember this', 'recall', 'what do you know about [person/topic]', 'save this fact', 'personal notes'.
Replace or supplement technical jargon ('atomic facts', 'entity-based knowledge graph', 'living summaries') with plain-language descriptions of what the skill does for the user, e.g., 'Remembers and organizes personal facts about people, places, and topics across conversations'.
Include common user phrasings that should trigger this skill, such as 'take note of', 'don't forget', 'update my notes on', 'what did I tell you about'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (memory/knowledge management) and some actions (fact extraction, entity-based knowledge graph, weekly synthesis), but these are somewhat abstract rather than concrete user-facing actions. 'Manages life/areas/ entities with atomic facts and living summaries' adds some specificity but remains conceptual. | 2 / 3 |
Completeness | Describes what the system is (a three-layer memory system) but never explicitly states when Claude should use it. There is no 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2, and the 'what' is also somewhat vague, bringing this to a 1. | 1 / 3 |
Trigger Term Quality | Uses technical jargon like 'entity-based knowledge graph', 'atomic facts', 'living summaries', and 'three-layer memory system' that users would not naturally say. Missing natural trigger terms like 'remember', 'recall', 'notes', 'personal information', 'track details'. | 1 / 3 |
Distinctiveness Conflict Risk | The 'life/areas/ entities' path reference and 'three-layer memory system' framing give it some distinctiveness, but 'fact extraction' and 'knowledge graph' could overlap with other knowledge management or note-taking skills. The niche is somewhat clear but not sharply delineated. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, well-structured skill that provides a clear data model and actionable workflows for maintaining an entity-based knowledge graph. Its main strengths are the concrete JSON schema, directory structure, and safety boundaries. Weaknesses include missing validation/feedback loops in workflows and some minor verbosity that could be trimmed.
Suggestions
Add explicit validation checkpoints to workflows, e.g., after fact extraction verify no duplicates exist and after weekly synthesis confirm all contradicted facts are properly superseded.
Trim the 'When to Use' section—most triggers are self-evident from the skill title and workflows, or consolidate into a single sentence.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary explanation (e.g., 'that compounds durable facts across sessions', the 'When to Use' section largely restates obvious triggers). The durable facts list and some phrasing could be tightened, but it's not egregiously verbose. | 2 / 3 |
Actionability | Provides a concrete data model with exact directory structure, a complete JSON schema for facts, executable bash setup command, and specific workflows with clear steps. The JSONL format is copy-paste ready and the category/status enums are well-defined. | 3 / 3 |
Workflow Clarity | Three workflows are clearly sequenced with numbered steps, but they lack explicit validation checkpoints. Fact extraction has no verification step (e.g., check for duplicates before appending is mentioned in rules but not in the workflow). Weekly synthesis doesn't validate that superseded facts are correctly marked. For an append-only data store that could accumulate errors, feedback loops would be valuable. | 2 / 3 |
Progressive Disclosure | Content is reasonably well-organized with clear sections, but everything is inline in a single file. The skill is moderately long (~100 lines) and could benefit from separating the JSON schema or workflow details into referenced files. However, it doesn't have deeply nested references and sections are logically ordered. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Repository
- jdrhyne/agent-skills
- Commit
6768672
- 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.