auto-claude-memory

Auto-Claude Graphiti memory system configuration and usage. Use when setting up memory persistence, configuring LLM/embedding providers, querying knowledge graph, or optimizing memory performance.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/auto-claude-memory/SKILL.md

Quality

Content

65%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 content is highly actionable with executable config and code across all providers, but it is overlong for a SKILL.md, inlines material that belongs in reference files, and lacks validation feedback loops around its destructive database-reset operations.

Suggestions

Move the per-provider configuration blocks and troubleshooting recipes into reference files (e.g. references/providers.md, references/troubleshooting.md) and link to them from SKILL.md, including a pointer to the existing references/.env.example rather than re-inlining every env var.

Add explicit validation steps before destructive operations — e.g. back up, then verify the backup exists, before 'rm -rf ~/.auto-claude/memories/embeddings', and confirm a fresh DB is created afterward.

Trim the repeated GRAPHITI_ENABLED=true lines and the illustrative 'Memory in Action' narrative, and relocate time-sensitive model/version names to a clearly dated section so they do not penalize conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete config blocks, but includes padding — repeated GRAPHITI_ENABLED=true across every provider block, a narrative 'Memory in Action' example, and time-sensitive model names (gpt-4o-mini, claude-sonnet-4-5-latest, gemini-2.0-flash) outside any deprecated section — so it could be tightened rather than earning 4.	3 / 5
Actionability	Copy-paste-ready env vars, bash install/pull commands, a runnable Python API example, and concrete CLI query commands cover the common cases fully, matching the 'fully executable' top anchor.	5 / 5
Workflow Clarity	Steps are present in 'How Memory Works' and troubleshooting, but validation checkpoints are implicit or missing; the destructive 'rm -rf ~/.auto-claude/memories/embeddings' reset has no validate-before-proceed loop, which caps workflow_clarity at 3 per the destructive-operation rule.	3 / 5
Progressive Disclosure	Section headers give reasonable structure, but ~370 lines of provider configs, troubleshooting, and advanced usage are inlined in SKILL.md instead of split out, and the existing references/.env.example bundle file is never linked from the body — fitting 'some structure but content that should be separate is inline'.	3 / 5
	Total	14 / 20 Passed

Description

83%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, well-formed description that clearly states what the skill does and when to invoke it with concrete, mostly natural trigger phrases. The main limitation is trigger-term synonym coverage and a slight overlap risk on the broad 'memory' term.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'setting up memory persistence, configuring LLM/embedding providers, querying knowledge graph, optimizing memory performance' — with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the fully comprehensive level 5.	4 / 5
Completeness	Explicitly answers both what ('Auto-Claude Graphiti memory system configuration and usage') and when ('Use when setting up... configuring... querying... or optimizing...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Good keyword coverage across 'memory persistence', 'LLM/embedding providers', 'knowledge graph', and 'memory performance' that a user would plausibly say, though a few natural synonyms ('persistent memory', 'recall') are missing, keeping it below 5.	4 / 5
Distinctiveness Conflict Risk	The Graphiti-specific framing and targeted triggers make it mostly distinct from sibling auto-claude skills, with only minor overlap risk on the generic 'memory' term, so it sits above 3 but below the minimal-conflict level 5.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/auto-claude-memory/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.