self-configuration

Inspect or modify Letta Code's own memory, model, context window, system prompt, compaction, permissions, toolsets, mods, skills, channels, schedules, and local runtime settings. Use when the user asks how this agent or conversation is configured, or asks you to change how you behave or how the harness runs you.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%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 well-structured, highly actionable skill body with clear workflows and validation checkpoints for destructive server/config operations, and appropriately split reference material. The main weakness is length — several sections could be tightened or offloaded to references to improve token efficiency.

Suggestions

Trim or move the long global-settings key table ('tokenStreaming', 'reasoningTabCycleEnabled', etc.) into a reference file, keeping only the keys the model must act on inline.

Consolidate the repeated LETTA_BASE_URL / api.letta.com caveat, which appears in at least four sections, into a single guardrail statement referenced where needed.

Move the provider-specific 'letta connect' example list into references/provider-connections.md, since it is version-sensitive and likely to drift.

Dimension	Reasoning	Score
Conciseness	Largely efficient and assumes Claude's competence, but the body runs ~440 lines and some sections (long settings-key tables, repeated base-url caveats) restate guidance that could be trimmed or pushed to references.	4 / 5
Actionability	Provides copy-paste-ready, executable commands throughout (letta agents config, the update-agent-settings.ts dry-run/live examples, add_permission.py) with specific flags and concrete examples covering common cases.	5 / 5
Workflow Clarity	The 'Safe workflow' section gives a clear numbered sequence (identify scope, inspect+rollback, dry-run, apply smallest change, verify, report) with explicit validation checkpoints (dry-run previews, read-back verification, effective-state inspection) for risky server writes.	5 / 5
Progressive Disclosure	SKILL.md is an overview that points one level deep to real reference files (model-settings.md, compaction-prompt-patterns.md, api-patch-examples.md) and helper scripts, all of which exist in the bundle; navigation is clearly signaled via the References and Helper scripts sections.	5 / 5
	Total	19 / 20 Passed

Description

92%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, specific description that clearly scopes both the action surface and the trigger conditions. It uses third person and avoids fluff, with only minor reliance on internal terminology over user-natural phrasing.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions (inspect/modify memory, model, context window, system prompt, compaction, permissions, toolsets, mods, skills, channels, schedules, runtime settings) with comprehensive coverage across the runtime configuration surface.	5 / 5
Completeness	Explicitly answers both what it does ('Inspect or modify Letta Code's own memory, model, ... runtime settings') and when to use it ('Use when the user asks how this agent or conversation is configured, or asks you to change how you behave or how the harness runs you').	5 / 5
Trigger Term Quality	Includes natural user-facing phrases like 'how this agent or conversation is configured' and 'change how you behave', though it leans on internal jargon (compaction, toolsets, mods) more than everyday synonyms a user would say.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche (the agent's own configuration and runtime) with distinct, self-referential triggers ('change yourself', 'how the harness runs you') that are unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 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/self-configuration/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.