initializing-memory

Comprehensive guide for initializing or reorganizing agent memory. Load this skill when running /init, when the user asks you to set up your memory, or when you need guidance on creating effective memory files.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./src/skills/builtin/initializing-memory/SKILL.md

Quality

Content

52%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 body delivers concrete, actionable guidance and a well-sequenced workflow with validation checkpoints, but it is notably verbose and ships as a single monolithic file with no bundle references, hurting both token efficiency and progressive disclosure.

Suggestions

Extract the long history-analyzer worker prompt template (Steps 5a-5d) and the troubleshooting table into reference files under references/, keeping SKILL.md as a concise overview with one-level-deep links.

Trim the philosophical identity framing in 'Context Management Principles' and de-duplicate the overlapping guidance across that section, 'What to Remember', and 'Memory Structure' to reduce token cost.

Tighten broad workflow steps like '6. Research the project' with explicit sub-checkpoints so the validation pattern is consistent throughout the flow rather than concentrated near the end.

Dimension	Reasoning	Score
Conciseness	The ~726-line body is noticeably verbose, with philosophical padding ('Your context is not just data storage — it is your identity, memory, and continuity', 'Like synaptic connections') and redundant sections (Context Management Principles, What to Remember, and Memory Structure overlap heavily). Matches the score-2 anchor; below 3 because the padding is substantial, above 1 because concrete commands and templates are still present.	2 / 5
Actionability	Provides concrete executable commands ('letta trajectories export --out ...', 'git shortlog -sn --all', jq recipes, a validation 'find' one-liner) and a full copy-paste worker prompt template. Mostly executable with minor gaps (some steps like 'Research the project' remain high-level); below 5 because a few sections describe rather than instruct, above 3 because real runnable code dominates.	4 / 5
Workflow Clarity	A clear 9-step Initialization Flow with sub-steps and explicit validation/checkpoints (Step 8 structural check, Step 5c-3d 'verify no information was lost', feedback loops for fix-and-revalidate). Below 5 because some steps (Step 6 'Research the project') are broad without tight per-step checkpoints; above 3 because validation is explicit, not merely implied.	4 / 5
Progressive Disclosure	The skill is a single monolithic 726-line SKILL.md with no references/, scripts/, or assets/ bundle files; long content that belongs in separate files (the full history-analyzer prompt template, the troubleshooting table, the example directory tree) is all inlined. Matches the score-2 anchor (content that clearly belongs in separate files is inlined); above 1 because section headers provide some structure.	2 / 5
	Total	12 / 20 Passed

Description

78%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 strong: it explicitly states both what the skill does and when to load it, anchored by a concrete '/init' trigger. The main weakness is the generic 'Comprehensive guide' framing and a lack of multiple specific concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('initializing or reorganizing agent memory') and 1-2 concrete actions ('creating effective memory files'), but the word 'Comprehensive guide' is generic and it does not enumerate several specific concrete actions. Fits the score-3 anchor and is below 4 (no list of several specific actions) and above 2 (it names actions beyond the bare domain).	3 / 5
Completeness	Explicitly answers both what ('initializing or reorganizing agent memory', 'creating effective memory files') and when ('Load this skill when running /init, when the user asks you to set up your memory...') with concrete trigger phrases. Matches the score-5 anchor directly.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('running /init', 'the user asks you to set up your memory', 'creating effective memory files'). Good keyword coverage with a specific command trigger; below 5 because it lacks synonyms and file extensions, above 3 because the triggers are explicit and natural rather than generic.	4 / 5
Distinctiveness Conflict Risk	The memory-initialization niche is mostly distinct with specific triggers ('/init', 'set up your memory'); minor overlap risk with general memory-management skills. Above 3 (clearer niche than 'Works with document files') and below 5 (the 'creating effective memory files' phrasing could overlap with related memory skills).	4 / 5
	Total	16 / 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
skill_md_line_count	SKILL.md is long (726 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: letta-ai/letta-code
Path: src/skills/builtin/initializing-memory/SKILL.md
Commit: 051b47f

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.