CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

An unusually strong operational skill: concrete commands at every step, executable validation code, a ten-step sequence with real feedback loops (coverage retry, verification checklist, commit confirmation), and the mechanical complexity correctly pushed into two real, well-signaled scripts. The only costs are a long, occasionally essayistic body that could shed its Principles and commit-protocol sections into reference files, and minor tightening opportunities in the prose.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious, judgment-bearing instruction ("Each directory's MEMORY.md describes its immediate children", "Provenance gates promotion here too") and teaches nothing Claude already knows. Below anchor 5 because the Principles/identity passages run essayistic ("Build a self that survives a model swap: what you value, your perspective, the quotes and traits that make you recognizably you") and the ~226-line body could be tightened in places; well above anchor 3 because there is no concept padding and almost every sentence carries a rule or constraint.

4 / 5

Actionability

Nearly every step ships copy-paste-ready commands — `git shortlog -sn --all | head -5`, `letta trajectories export --out /tmp/letta-trajectories`, `node <SKILL_DIR>/scripts/prepare-history.mjs --export ... --out ...`, the find-based violation check — and even the deliberately flexible Workflow step is pinned with complete, executable JSON-schema code (`const historySchema = cohort => {...}`) plus hard constraints. Matches anchor 5: fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

A ten-step numbered flow (inspect → detect → identify → ask → export → research → analyze → curate → verify → commit) with explicit validation and feedback loops: Step 8's coverage accounting ("launch one follow-up Workflow over retry.json, then rerun the script with both --journal paths. If coverage is still incomplete, say so plainly"), Step 9's verification checklist, and Step 10's post-commit `git status` / `git ls-tree` confirmation. This is exactly anchor 5 — clear sequence, explicit validation, error-recovery loops, and a checklist.

5 / 5

Progressive Disclosure

Scored against the actual bundle: the two mechanical helpers exist as real files (scripts/prepare-history.mjs, scripts/history-coverage.mjs) and are referenced by exact path at the point of use with their behavior summarized, one level deep and clearly signaled. Below anchor 5 because the 21KB body retains substantial self-contained material inline — the ~20-line "Commit memory changes" protocol and the Principles section — that could live in reference files, and there is no overview map of the bundle; above anchor 3 because what is externalized is appropriately split and navigation within the body is easy.

4 / 5

Total

18

/

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.

A solid description with an explicit, well-phrased trigger clause ("Load this skill when running /init, when the user asks you to set up your memory...") that clearly answers when to use it. The what half is the weak spot: "Comprehensive guide for initializing or reorganizing agent memory" relies on padding and does not convey the skill's concrete capabilities. Distinctiveness is good, with only minor overlap risk via the /init trigger.

Suggestions

Replace "Comprehensive guide for" with the skill's concrete capabilities, e.g., "Structures agent memory into an indexed root with deferred topic directories, validates frontmatter and index rules, analyzes prior session history, and commits the result. Load when running /init..." — this raises specificity and completeness toward anchor 5.

Add natural trigger synonyms users would say — "reorganize my memory", "set up MEMORY.md", "remember things long-term" — so common phrasing variants match, improving trigger term coverage toward anchor 5.

DimensionReasoningScore

Specificity

"Comprehensive guide for initializing or reorganizing agent memory" names the domain and two concrete actions (initializing, reorganizing), but "Comprehensive guide" is filler and the description never enumerates what the skill actually covers (structuring memory directories, analyzing session history, validation, commits). It is above anchor 2 because real actions are named, but below anchor 4 because it does not list several specific actions with minor gaps.

3 / 5

Completeness

Both parts are present: the what ("guide for initializing or reorganizing agent memory") and an explicit when ("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"), so the missing-when cap of 3 does not apply. Below anchor 5 because the what is generic — "Comprehensive guide" padding instead of enumerated capabilities — even though the when carries concrete trigger phrases, matching anchor 4 (both present, one could be more specific).

4 / 5

Trigger Term Quality

Includes multiple natural trigger phrases — "when running /init", "set up your memory", "creating effective memory files" — plus the concrete /init command trigger. Below anchor 5 because common synonyms like "reorganize my memory", "memory files" alone, or "MEMORY.md" are absent; above anchor 3 because coverage of natural phrasings is good, not just partial.

4 / 5

Distinctiveness Conflict Risk

"agent memory" / "memory files" carve a clear niche with distinct triggers, but "when running /init" overlaps with generic project-initialization skills (e.g., a CLAUDE.md /init skill), creating minor conflict risk with a closely related skill — anchor 4. Not anchor 5 because of that /init overlap; not anchor 3 because the memory-specific triggers would not plausibly fire a documentation or code skill.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

letta-ai/letta-code

Path

src/skills/builtin/initializing-memory/SKILL.md

Reviewed

Table of Contents

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.