generating-mod-envs

Generates and reviews mod learning env JSON files for Letta Code local mods. Use when asked to teach, learn, or optimize a mod behavior; create, draft, validate, improve, or explain envs for `/mods learn --env`; or design evaluation scenarios, memory fixtures, requiredResultMarkers, requiredTraceMarkers, negative controls, and candidate diversity hints.

Quality

91%

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

90%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 dense, executable, and free of padding, with a concrete validation step and a complete worked example that make it directly actionable. The two minor gaps are an implicit error-recovery loop in the workflow and references that are signaled as inline code rather than explicit navigational pointers.

Suggestions

Add an explicit validate→fix→re-validate retry loop after step 5 (e.g., 'If validation fails, read the errors, fix the JSON, and re-run the validator before proceeding').

Surface the bundle references as clearly signaled navigational pointers (e.g., a short '## References' section listing the template asset and validator script) rather than only inline code paths.

In the workflow, mark the validation step as a hard gate ('Only proceed to step 6 after validation passes') to make the checkpoint unmissable.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout: it never explains concepts Claude already knows (JSON, mods, evals) and every line is actionable reference material or guidance, so every token earns its place.	5 / 5
Actionability	Provides copy-paste-ready executable commands ('bun .../validate-mod-env.ts path/to/env.json', '/mods learn --env=... --model=auto ...') plus a complete minimal JSON example covering the common case.	5 / 5
Workflow Clarity	A clear 6-step sequence with an explicit validation checkpoint (step 5 runs the validator) and an install-location branch, but it stops short of spelling out a validate→fix→re-validate error-recovery loop.	4 / 5
Progressive Disclosure	Well-organized into Workflow / Env shape / Quality rules / Example sections with one-level-deep references to real bundle files (assets/mod-learning-env.template.json, scripts/validate-mod-env.ts), though those references are inline code paths rather than clearly signaled navigational links.	4 / 5
	Total	18 / 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.

The description is third-person, specific, and explicitly pairs a concrete capability statement with a well-detailed 'Use when...' trigger clause, hitting a narrow niche with low conflict risk. Its only weakness is that some listed triggers are field-specific jargon rather than phrases a user would naturally say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Generates and reviews', 'create, draft, validate, improve, or explain envs', and 'design evaluation scenarios, memory fixtures, requiredResultMarkers... negative controls' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Clearly answers both 'what' ('Generates and reviews mod learning env JSON files for Letta Code local mods') and 'when' via an explicit 'Use when asked to teach, learn, or optimize...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage with 'teach, learn, or optimize a mod behavior' and the explicit '/mods learn --env' command, though the remaining triggers lean on domain jargon (requiredResultMarkers, candidate diversity hints) rather than user-natural synonyms.	4 / 5
Distinctiveness Conflict Risk	A clear niche (Letta Code mod learning envs) anchored by a distinct command trigger ('/mods learn --env') makes conflict with other skills minimal.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 missing, 2 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: letta-ai/letta-code
Path: src/skills/builtin/generating-mod-envs/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.