CtrlK
BlogDocsLog inGet started
Tessl Logo

customizing-commands

Creates, edits, and enables Letta Code mod-provided slash commands. Use when the user asks to add a custom /command, slash command, command shortcut, scoped conversation-backed command, or command-driven panel behavior.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

93%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 exemplary skill body: token-efficient, immediately actionable with executable code and specific rules, and cleanly structured with a decision table and one-level-deep references. The only minor gap is the absence of an explicit post-registration validation step in the workflow.

DimensionReasoningScore

Conciseness

The body is lean and earns every token: a decision table, a five-step workflow, one complete code example, a result-type union, and terse rules — no explanation of what slash commands or mods are, and no padding. It matches the 5-anchor ("lean and efficient; assumes Claude's competence") rather than 4, which would require identifiable over-explanation to trim.

5 / 5

Actionability

Guidance is fully executable: exact file paths (~/.letta/mods/review.ts), a copy-paste-ready activate() example with register(), a concrete result-type union with usage guidance for each variant, and a workflow with specific API calls (letta.commands.register(), letta.capabilities.commands guard, /reload). Rules are checkable ("Command IDs omit the slash"), leaving no significant gaps from the 5-anchor.

5 / 5

Workflow Clarity

"1. Inspect ~/.letta/mods/... 2. Preserve unrelated mod code... 3. Register... 4. Return the unregister function... 5. Tell the user... to run /reload" is a clear, ordered sequence, and the upfront decision table acts as a checkpoint. It stops short of 5 because there is no explicit validation or error-recovery step (e.g. verifying the command registered correctly after /reload) — this is file creation, not a destructive/batch operation, so the cap-at-3 rule does not apply.

4 / 5

Progressive Disclosure

The body is a well-organized overview (~85 lines, seven headed sections) that delegates all advanced material through clearly signaled, one-level-deep references with per-file topic labels ("Simple output command, panel command...: ../creating-mods/references/commands.md" etc. under "More recipes"), exactly matching the 5-anchor pattern. No bundle directories exist in this skill, and no content that should be separate is inlined, so there is no nesting or burial to penalize.

5 / 5

Total

19

/

20

Passed

Description

83%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 well-formed description with an explicit what-and-when structure and domain-specific trigger phrases. Its main weakness is that the action verbs ("creates, edits, and enables") are somewhat generic relative to the concrete mechanics the body actually covers.

Suggestions

Make the capability verbs more concrete by naming the actual mechanics, e.g. "Registers, edits, and enables Letta Code mod slash commands via letta.commands.register(), including prompt, output, and panel result types."

Add one or two natural trigger variants users commonly say, such as "add a /command" or "mod command", to widen keyword coverage.

Sharpen distinctiveness from sibling mod skills by scoping the trigger, e.g. "command-specific entrypoint for local mods" phrasing mirrored from the body.

DimensionReasoningScore

Specificity

"Creates, edits, and enables Letta Code mod-provided slash commands" names a specific domain and lists three concrete actions, matching the anchor for several specific actions with minor coverage gaps ("enables" is the least concrete; registration/result types/panels are left to the body). It falls below 5 because the actions are less granular than the 5-anchor's multi-action comprehensiveness, and above 3 because three actions plus a named domain exceed the 1-2-action anchor.

4 / 5

Completeness

It explicitly answers both questions: what ("Creates, edits, and enables Letta Code mod-provided slash commands") and when ("Use when the user asks to add a custom /command, slash command, command shortcut...") with concrete trigger phrases, matching the 5-anchor pattern exactly. The explicit 'Use when' clause rules out the cap at 3.

5 / 5

Trigger Term Quality

"custom /command, slash command, command shortcut, scoped conversation-backed command, or command-driven panel behavior" gives good coverage of natural phrases a user would say. Not 5 because a few natural synonyms are missing (e.g. "add a /command", "mod command" as a plain keyword, "create a command for..."); not 3 because coverage clearly goes beyond one or two generic keywords.

4 / 5

Distinctiveness Conflict Risk

"Letta Code mod-provided slash commands" carves a clear niche, but generic trigger terms like "slash command" and "command shortcut" carry minor overlap risk with closely related command or mod skills (this very skill defers to a sibling creating-mods skill for broader command recipes). Not 5 because of that adjacent-skill overlap; not 3 because the Letta Code mod scoping makes wrong-skill triggering unlikely.

4 / 5

Total

17

/

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
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.