CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

managing-shared-memory

Create and manage shared memory — git-tracked repositories hosted on Letta Cloud that are attached to one or more agents and projected into their filesystems. Use when the user wants to share memory or files across agents, store context outside your own MemFS, attach or detach shared memory, or inspect its file history.

Quality

90%

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.

A highly actionable, well-structured skill: every workflow is backed by executable commands and explicit error-recovery loops, with no padding or basic-concept explanations. The only room for improvement is splitting the detailed commit protocol into a reference file and trimming a few redundant phrases.

DimensionReasoningScore

Conciseness

The body is dense and assumes git competence — no explanations of concepts Claude already knows — but a few spots could be trimmed (e.g. 'reachable from any environment (sandboxes, remote machines, sessions)' and some restated provenance rules in the commit section). Efficient with minor instances of over-explanation fits anchor 4 rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Fully executable, copy-paste-ready guidance: concrete bash for reading mounts ($MEMORY_DIR/../<repo-name>), git commands (pull --rebase, log), the complete letta shared-memory subcommand set with flags and comments, and a complete commit-message template with worked examples. This covers the common cases as anchor 5 requires; the <repo-name> placeholders are normal parameterization, not gaps.

5 / 5

Workflow Clarity

The normal path (edit, commit, harness push) is clearly sequenced, and error recovery is explicit: rejected pushes get 'git pull --rebase then push again', conflicts get a resolve/finish/leave-clean procedure, and Troubleshooting gives recovery for each failure mode (missing mount → sync; occupied mount path → inspect, salvage, re-run sync). Explicit feedback loops for error recovery match anchor 5; operations are versioned and reversible, so the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist and the body is well-organized into clear sections with a valid internal anchor link ([Commit memory changes](#commit-memory-changes)). However, the skill is over 50 lines, so the simple-skill exception doesn't apply, and the ~20-line commit protocol is self-contained enough that it could live in a reference file — good structure with minor organization gaps fits anchor 4 rather than the appropriately-split anchor 5.

4 / 5

Total

18

/

20

Passed

Description

88%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 strong description that clearly states what the skill does and when to use it, with concrete actions and a well-defined niche. Trigger coverage is good but could add a few more natural synonyms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — create, manage, attach, detach, share memory or files, store context outside MemFS, inspect file history — and grounds them in a concrete mechanism (git-tracked repos hosted on Letta Cloud, projected into filesystems). This matches the anchor for comprehensive concrete-action coverage, not the minor-gaps level below it.

5 / 5

Completeness

The first sentence explicitly states what the skill does and the 'Use when the user wants to...' clause gives concrete trigger scenarios, matching the anchor that requires both what and when with explicit trigger phrases. Not 4, because the when-clause is explicit and specific rather than vague.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ('share memory or files across agents', 'attach or detach shared memory', 'inspect its file history') but offers few synonym variations (e.g. no 'shared repo', 'collaborative files', 'versioned file store' as triggers). Good coverage with a few natural terms missing fits anchor 4 rather than the comprehensive-synonym anchor 5.

4 / 5

Distinctiveness Conflict Risk

The Letta Cloud org-owned shared-repository niche is distinct and 'outside your own MemFS' actively disambiguates from the agent's own memory skill, but 'share memory or files across agents' retains minor overlap risk with generic memory- or file-sharing skills. Mostly distinct with minor overlap risk fits anchor 4; the explicit disambiguation keeps it above anchor 3.

4 / 5

Total

18

/

20

Passed

Validation

100%

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/managing-shared-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.