creating-mods

Creates and edits trusted local Letta Code mods, including tools, slash commands, local-only model providers, lifecycle/turn events, scoped conversation helpers, panels, and capability-gated behavior. Use when asked to make a mod, add an agent-callable tool, add a slash command, add a local provider/model adapter, transform turns, react to app events, or add lightweight mod UI outside the dedicated /statusline flow.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%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.

The body is a well-structured, actionable overview with a sequenced workflow, validation checklist, recovery guidance, and clean progressive disclosure to 9 reference files. The main weakness is mild redundancy in the capability-to-reference mapping and stubbed registration bodies in the core code example.

Suggestions

Consolidate the capability→reference mapping: keep it in the References table and have Workflow step 4 point there rather than re-listing all nine reference files inline.

Flesh out one registration body in the 'Core mod shape' example (e.g., a minimal tool or command with name/description/schema) so the canonical example is copy-paste ready.

Trim the enumerated letta.capabilities.* list or collapse it into a compact inline reference, since the guard-everything rule is already stated in prose.

Dimension	Reasoning	Score
Conciseness	Lean body that assumes Claude's competence (no 'what is a mod' preamble) and uses tight tables and code blocks, but the capability-to-reference mapping is restated between the 'Choose the right capability' table, Workflow step 4, and the References table, introducing minor redundancy.	4 / 5
Actionability	Provides executable code (activate shape, capability guards), concrete scoped APIs (ctx.conversation.fork, forked.sendMessageStream), and recovery commands (letta --no-mods), but registration bodies are left as /* ... */ stubs, leaving a minor gap for copy-paste readiness.	4 / 5
Workflow Clarity	A clear 9-step sequenced workflow is backed by an explicit 'Pre-flight checklist for complex mods' validation step and an error-recovery feedback loop (/reload, letta --no-mods, LETTA_DISABLE_MODS=1), matching the checklist-plus-recovery anchor.	5 / 5
Progressive Disclosure	SKILL.md is a well-signaled overview pointing one level deep to 9 existing reference files, each with a 'Load when' navigation cue and a dedicated References table; all referenced paths resolve to real files.	5 / 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.

The description is specific, uses third-person voice, and explicitly covers both what the skill does and when to invoke it with natural trigger terms. It carves a clear niche distinct from the dedicated statusline skill.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete capabilities — 'tools, slash commands, local-only model providers, lifecycle/turn events, scoped conversation helpers, panels, and capability-gated behavior' — with comprehensive coverage of the mod surface.	5 / 5
Completeness	Explicitly answers both what ('Creates and edits trusted local Letta Code mods, including...') and when (the concrete 'Use when asked to...' trigger clause), each with specific triggers.	5 / 5
Trigger Term Quality	The 'Use when asked to make a mod, add an agent-callable tool, add a slash command, add a local provider/model adapter, transform turns, react to app events, or add lightweight mod UI' clause uses natural phrases a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche ('Letta Code mods' via mod APIs, not app internals) with explicit boundary ('not this skill' for statusline), giving minimal conflict risk with other 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/creating-mods/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.