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

74%

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/initializing-memory/SKILL.md

Quality

Content

70%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 skill is a well-sequenced, highly actionable memory-initialization workflow with strong validation checkpoints and feedback loops. Its main weaknesses are verbosity from repeated rules and philosophical framing, and the absence of any bundled reference files to offload the inlined templates and CLI references.

Suggestions

Move the full history-worker prompt template, the trajectory export CLI reference, and the exploration subagent templates into a references/ file linked from the main body to improve progressive disclosure and cut inlined bulk.

Deduplicate rules stated across sections (e.g. 'frontmatter description states purpose not summary' appears in Structural Requirements, Hierarchy Principles, and Step 7) into a single canonical statement.

Trim the philosophical identity framing in 'Context Management Principles' and 'What to Remember' to the operational essentials, trusting Claude to grasp the motivation in fewer tokens.

Dimension	Reasoning	Score
Conciseness	The operational core (commands, jq recipes, git merge strategy, troubleshooting table) is efficient and novel, but the ~700-line body repeats several rules across sections and spends substantial prose on philosophical identity framing ('your context is your identity', 'would you still be you?') that could be tightened.	3 / 5
Actionability	Provides concrete, mostly copy-paste-ready bash commands, a full Agent({...}) prompt template, git merge commands, and a runnable validation find script; minor gaps are the templated placeholders ([MEMORY_DIR], [focus and/or slice]) and some principle-level research guidance.	4 / 5
Workflow Clarity	A clearly sequenced 9-step workflow with explicit validation checkpoints (the find-based overlap violation check, the Step 5c-3d information-loss verification, git branch -d that only succeeds after the ancestry merge) and a troubleshooting table providing error-recovery feedback loops.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ all absent); section structure is clear and navigable, but large detailed material (the full history-worker prompt template, trajectory export CLI reference, exploration subagent templates, troubleshooting table) is inlined in SKILL.md rather than split into one-level-deep reference files.	3 / 5
	Total	15 / 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 clearly states both what the skill does and when to load it, with concrete natural triggers including the literal /init command. It is held back from a top score mainly by limited action specificity and minor overlap risk with adjacent memory skills.

Suggestions

Replace 'Comprehensive guide for' with a more concrete verb-led action list (e.g. 'Initialize, reorganize, and curate agent memory files') to lift specificity.

Add a few natural trigger synonyms (e.g. 'memory setup', 'reorganize memory', 'agent memory') to broaden keyword coverage.

Sharpen distinctiveness by naming the memory-filesystem projection ($MEMORY_DIR) or the target artifact to reduce overlap with generic memory skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('agent memory') and a few related actions ('initializing', 'reorganizing', 'creating effective memory files'), but these are variations of one meta-task rather than several distinct concrete capabilities, and 'Comprehensive guide' is mild fluff.	3 / 5
Completeness	Explicitly answers both 'what' ('Comprehensive guide for initializing or reorganizing agent memory') and 'when' with concrete trigger phrases ('Load this skill when running /init, when the user asks you to set up your memory, or when you need guidance...').	5 / 5
Trigger Term Quality	Includes strong natural triggers a user would actually say — '/init', 'set up your memory', 'creating effective memory files' — with good keyword coverage, though it misses some synonyms/extensions like 'reorganize memory' or 'memory setup'.	4 / 5
Distinctiveness Conflict Risk	The agent-memory niche with a distinctive '/init' trigger is mostly distinct from other skills, with only minor overlap risk against closely related memory-management 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: 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.