self-configuration

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

Quality

94%

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

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 well-structured, highly actionable skill body with clear sequenced workflows, validation checkpoints, and well-signaled references; the main weaknesses are overall length and a few large tables that would be better split into references.

Suggestions

Move the large 'Selected global settings keys' and 'Rule types' tables into a reference file to tighten the SKILL.md overview and lift progressive_disclosure toward 5.

Trim justifying prose such as the compaction rationale paragraph to a one-line rule, reducing length without losing actionability.

Consider consolidating the repeated <SKILL_DIR>/scripts/update-agent-settings.ts invocations behind a short variable or a single --help pointer to cut token cost.

Dimension	Reasoning	Score
Conciseness	Dense with operational specifics (env vars, flag names, precedence, guardrails) and avoids basic-concept padding, but the body is long with a few justifying-but-trimmable explanatory sentences (e.g., the compaction rationale), fitting 'efficient; minor instances that could be trimmed' better than the lean 5 anchor.	4 / 5
Actionability	Copy-paste-ready commands throughout (letta agents config, full npx tsx --dry-run invocations, letta secret set --env GITHUB_TOKEN, letta cron add, JSON permission examples) covering the common cases, matching the fully-executable top anchor.	5 / 5
Workflow Clarity	An explicit Safe workflow (scope, inspect+rollback, dry-run, smallest change, verify, report) with validation checkpoints and read-back verification, plus error-recovery guidance; the destructive-op validation cap does not apply because validation is present.	5 / 5
Progressive Disclosure	Three real one-level-deep references are clearly signaled via links and a References section, plus a Helper scripts table; scored 4 rather than 5 because several large inline tables (global settings keys, permission rule types) could be moved into reference files.	4 / 5
	Total	18 / 20 Passed

Description

100%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 states what the skill does and gives concrete natural-language triggers for when to use it, with no first/second-person voice issues in the capability clause.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete capabilities (memory, model, context window, system prompt, compaction, permissions, toolsets, mods, skills, channels, schedules, agent secrets, local runtime settings) with two concrete verbs ('Inspect or modify'), matching the comprehensive-coverage anchor rather than the 4 anchor's 'minor gaps'.	5 / 5
Completeness	Explicitly answers both what ('Inspect or modify...') and when ('Use when the user asks...') with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Natural user phrasings are present ('how this agent or conversation is configured', 'change how you behave', 'how the harness runs you', 'renames you'), giving comprehensive trigger coverage; the 4 anchor's 'a few natural terms missing' does not fit.	5 / 5
Distinctiveness Conflict Risk	Scoped to self-configuration of this specific harness with distinct triggers and minimal overlap risk; not the 4 anchor's 'minor overlap with closely related skills'.	5 / 5
	Total	20 / 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: 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.