Tessl • The management layer for AI agent skills

SkillPublic

memory-layer-bridge

Teaches agents when to query Cipher/Mem0, when to consult Obsidian, and when to log decisions inline — routing context retrieval to the right memory layer.

Quality

72%

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 ./skills/memory-layer-bridge/SKILL.md

Quality

Content

67%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.

A well-organized, appropriately lean routing contract whose decision tree and failure modes give a clear sequence. Its main weakness is actionability: the concrete "how" (tool names, write commands, vault structure) is delegated to companion skills and external docs that are not part of this bundle.

Suggestions

Add the concrete execution details for each route: the MCP tool names used to query Mem0/Cipher, and the vault write mechanism (e.g. via the Obsidian Local REST API or obsidian-vault-manager) with an example note path.

Consolidate the intro paragraph and "Purpose" section, and merge Rules that restate decision-tree branches to remove redundancy.

Either bundle the companion-skill references (obsidian-vault-manager, homelab-logbook) as real files or inline the minimal instructions needed to invoke them.

Dimension	Reasoning	Score
Conciseness	Lean overall — the decision tree is compact and no space is spent explaining concepts Claude already knows. Minor trimmable redundancy: the intro paragraph and the "Purpose" section restate each other, and Rules 1–5 partially restate the decision tree.	4 / 5
Actionability	The decision tree gives concrete routing ("Query Mem0/Cipher first (semantic search) → fall back to Obsidian vault search") and one concrete path ("Projects/<project>/decisions/"), but key execution details are missing: no MCP tool names for querying Mem0/Cipher, no concrete write mechanism for the Obsidian vault, and the companion skills that would provide the "how" are named but not bundled.	3 / 5
Workflow Clarity	The decision tree is a clearly sequenced routing workflow with an explicit fallback path (Mem0 → Obsidian) and a Failure Modes section covering unreachable stores and conflicting records — real error recovery, not just a happy path. Not a 5 because no verification step exists after a route is chosen or a write is performed.	4 / 5
Progressive Disclosure	A single self-contained file with well-organized sections; the references/ and scripts/ directories are empty and all guidance lives appropriately in one file. External links (Mem0 docs, Obsidian REST API) are one level deep, but the "Companion Skills" section points at skills not present in the bundle — minor organization gap, anchor 4.	4 / 5
	Total	15 / 20 Passed

Description

66%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 fairly strong description: specific, tool-named, and distinct, but it never tells the agent when to invoke the skill. The "when to query" phrasing is about internal routing content, not skill-activation triggers.

Suggestions

Add an explicit activation clause, e.g. "Use when deciding where to store or retrieve information across Mem0/Cipher, Obsidian, or inline session context."

Include natural trigger variations users would say, such as "remember", "recall a past decision", or "memory" alongside the tool names.

Mention the recall/update operations (not just query/log) so capability coverage is comprehensive.

Dimension	Reasoning	Score
Specificity	Names the memory-routing domain and several concrete actions ("query Cipher/Mem0", "consult Obsidian", "log decisions inline", "routing context retrieval"). Falls short of anchor 5 because coverage has gaps — no mention of searching, updating, or recalling past decisions.	4 / 5
Completeness	The "what" is clear, but the "when to query/consult/log" phrasing describes the skill's internal routing logic rather than when to invoke the skill itself — there is no "Use when..." clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Strong natural keywords: "Mem0", "Obsidian", "Cipher", "log decisions", "memory layer" — terms a user of these tools would actually say. Not anchor 5 because common variations and synonyms ("remember", "recall", "notes", "past decisions") are missing.	4 / 5
Distinctiveness Conflict Risk	Naming specific tools (Cipher/Mem0/Obsidian) creates a clear niche with distinct triggers, but the skill ecosystem includes sibling skills covering overlapping Obsidian/memory territory (e.g. obsidian-vault-manager, homelab-logbook), leaving minor overlap risk — anchor 4.	4 / 5
	Total	15 / 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: pvnkmnk/AgenticSelfHostSkills
Path: skills/memory-layer-bridge/SKILL.md
Revision: ff4471e

Reviewed: 16 hours ago

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.

memory-layer-bridge

Table of Contents

Is this your skill?