syncing-memory-filesystem

Diagnose and repair MemFS repository setup, remote sync, authentication failures, optional backup remotes, or merge/rebase conflicts. Do not load for routine memory reads or edits.

Quality

76%

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 ./src/skills/builtin/syncing-memory-filesystem/SKILL.md

Quality

Content

82%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 concrete executable commands, a clear failure checklist, and validation/feedback checkpoints for destructive git operations. It is well-structured and self-contained, with only minor conciseness and workflow-linearity gaps.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly lean, focused on MemFS/letta-specific behaviors Claude would not know (harness push timing, layout rules, `/memfs` commands) with minimal generic explanation; a few explanatory sentences could be trimmed but nothing is heavily padded.	4 / 5
Actionability	It provides copy-paste-ready, executable commands throughout ("git -C \"$MEMORY_DIR\" status --short --branch", "letta memory pull --agent \"$AGENT_ID\"", "/memfs enable", "GIT_EDITOR=true git -C \"$MEMORY_DIR\" rebase --continue") covering the common repair cases.	5 / 5
Workflow Clarity	The closing "Failure Checklist" gives an explicit numbered sequence with inspection checkpoints (confirm $MEMORY_DIR, check backend, inspect git status) before acting, plus a feedback loop (rerun with LETTA_DEBUG=1) and rebase-vs-merge detection; the multi-branch scenario structure leaves minor gaps versus a single linear flow.	4 / 5
Progressive Disclosure	No bundle files exist, so the skill is self-contained; it is well-organized into clearly headed sections ("Start With the Harness", "Inspect a Broken Checkout", "Merge or Rebase Conflicts", "Failure Checklist") with no nested references and content that does not need splitting, though it exceeds the 50-line simple-skill threshold.	4 / 5
	Total	17 / 20 Passed

Description

70%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 is specific, distinctive, and uses strong domain trigger terms, with explicit negative-trigger guidance. Its main weakness is the absence of an explicit positive "Use when..." clause, leaving the activation condition implied rather than stated.

Suggestions

Add an explicit positive trigger clause, e.g. "Use when the agent's memory repository fails to set up, sync, authenticate, or merge/rebase."

Vary the action verbs beyond "Diagnose and repair" (e.g., reinitialize, re-sync, rebase-resolve) to broaden trigger-term coverage.

Consider adding common user phrasings like "memory git errors" or "memory not syncing" as natural synonyms.

Dimension	Reasoning	Score
Specificity	"Diagnose and repair" applied to a concrete enumerated list ("repository setup, remote sync, authentication failures, optional backup remotes, or merge/rebase conflicts") lists several specific domains with comprehensive coverage, but the action verbs are limited to diagnose/repair rather than many distinct concrete actions.	4 / 5
Completeness	The "what" is clear (diagnose/repair the listed failures) and there is explicit negative trigger guidance ("Do not load for routine memory reads or edits"), but there is no explicit positive "Use when..." clause — the positive trigger is only implied by the failure list, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Natural domain terms a user of this system would say ("remote sync", "authentication failures", "merge/rebase conflicts", "backup remotes", "memory reads or edits") are well covered, though a few common synonyms or phrasings users might say are absent.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (MemFS repository repair) with distinct triggers and explicitly distinguishes itself from routine memory skills via "Do not load for routine memory reads or edits," giving minimal conflict risk.	5 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: letta-ai/letta-code
Path: src/skills/builtin/syncing-memory-filesystem/SKILL.md
Commit: 7a4337e

Reviewed: 2 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.