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

96%

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

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.

Strong body content: dense, actionable, and well-organized, with executable commands, a complete worked example, and verified bundle files referenced one level deep. The only gap is the absence of an explicit fix-and-re-validate loop after the validation step in the workflow.

Suggestions

After the validation step, add one recovery line such as "If validation fails, fix the reported env errors and re-run the validator before proceeding to /mods learn" to close the feedback loop.

Consider adding a brief note on interpreting common validator errors (e.g., stray prompt in an assertion-only scenario, brittle trace marker) so failures are diagnosable without re-reading the full Env shape section.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout: terse imperative guidance ("No comments or trailing commas", "Use unique sentinels, e.g. `MY-MOD-CANARY-OK`, not common phrases") with zero padding or explanation of concepts Claude already knows. Every token earns its place.	5 / 5
Actionability	Fully executable guidance: copy-paste validate command ("bun src/skills/builtin/generating-mod-envs/scripts/validate-mod-env.ts path/to/env.json"), the /mods learn invocation, a complete minimal scenario-suite JSON example, and a real template asset path. Covers the common case end-to-end.	5 / 5
Workflow Clarity	Clear numbered sequence (define behavior/eval, choose path, draft, scenario design, validate, run) with an explicit validation checkpoint and concrete command. Falls short of a 5 because there is no error-recovery feedback loop: the body never says what to do when validation fails (fix the env and re-validate), which the anchor-5 example includes.	4 / 5
Progressive Disclosure	Well-sectioned overview with real one-level-deep bundle references: assets/mod-learning-env.template.json and scripts/validate-mod-env.ts both exist and are clearly signaled with concrete paths. Core env-shape and quality-rule content is compact and belongs inline; navigation is easy.	5 / 5
	Total	19 / 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.

Excellent description. It states concrete capabilities in third person, gives an explicit "Use when..." trigger clause rich with natural synonyms and domain terms, and occupies a distinct niche with minimal conflict risk. No weaknesses identified.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions with comprehensive coverage: "Generates and reviews mod learning env JSON files", "design evaluation scenarios, memory fixtures, requiredResultMarkers, requiredTraceMarkers, negative controls, and candidate diversity hints". No minor gaps in action coverage that would justify a 4.	5 / 5
Completeness	Clearly answers both: what ("Generates and reviews mod learning env JSON files for Letta Code local mods") and when ("Use when asked to teach, learn, or optimize a mod behavior; create, draft, validate, improve, or explain envs...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms ("teach, learn, or optimize"; "create, draft, validate, improve, or explain"), the file format ("JSON files"), and the concrete command ("/mods learn --env"). No natural phrasing a user would say is identifiable as missing.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Letta Code local mod learning envs, /mods learn) with distinct, domain-specific triggers; minimal overlap risk with other skills.	5 / 5
	Total	20 / 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: d4d1db7

Reviewed: 5 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.