mps-dsl-memory

Create or refresh project-local DSL skills under `.agents/skills/<dsl-name>-dsl/` for one or more MPS languages after discovering concepts, sandbox examples, JSON blueprints, references, or gotchas.

Quality

63%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/mps-dsl-memory/SKILL.md

Quality

Content

75%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 reference workflow with concrete MPS MCP tool calls and an explicit verification step. It is held back from 5s by the absence of a fully-populated worked example, an explicit failure-recovery loop, and self-directed progressive disclosure.

Suggestions

Add one concrete worked example showing a populated `l:<uuid>:<languageName>` ref and a resulting `mps_mcp_get_concept_details` call so the guidance is copy-paste ready.

Spell out the verification feedback loop in step 8, e.g. 'If a recorded node ref no longer resolves, re-run discovery from step 3 before regenerating the skill.'

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what MPS or a DSL is and every bullet earns its place — with only minor instances (the lengthy 'Generated SKILL.md Requirements' list) that could be trimmed, fitting 'efficient; minor instances of over-explanation' rather than the fully lean 5.	4 / 5
Actionability	It names exact tools and arguments (`mps_mcp_get_project_structure`, `mps_mcp_get_concept_details` with `l:<uuid>:<languageName>`, `mps_mcp_insert_root_node_from_json`, `mps_mcp_check_root_node_problems`) and concrete paths, but provides no fully-populated worked example with real values, leaving a minor gap at 4 rather than 5.	4 / 5
Workflow Clarity	The 8-step workflow is clearly sequenced and ends with an explicit 'Verify' checkpoint (confirm reference files exist, blueprint JSON parses, node refs resolve), but the failure path is not spelled out as a validate→fix→retry feedback loop, so it sits at 'clear sequence with most checkpoints' rather than 5.	4 / 5
Progressive Disclosure	The body is well-organized into clearly signaled sections (When to Use, Prerequisites, Workflow, Layout, Requirements, Reference Files) with no nested references and easy navigation, but it is a single self-contained file over 50 lines describing a reference layout for generated skills rather than splitting its own detail into referenced files, so 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Description

51%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 clearly states a specific, well-scoped capability with concrete actions, but it lacks an explicit 'Use when...' trigger clause and the natural conversational phrases users would actually say. Adding trigger language would lift the two weakest dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when bootstrapping, generating, or refreshing a DSL skill for an MPS project, or when the user asks to document this DSL.'

Surface the natural user phrases ('bootstrap DSL skill', 'generate DSL skill', 'document this DSL') from the body directly into the description so trigger_term_quality reflects what users say.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Create or refresh project-local DSL skills', 'discovering concepts, sandbox examples, JSON blueprints, references, or gotchas' — with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	The 'what' is clear (create/refresh DSL skills under a specific path) but there is no 'Use when...' clause — 'when' is only weakly implied via the 'after discovering...' sequence, so per the missing-trigger cap it cannot exceed 3.	3 / 5
Trigger Term Quality	It surfaces domain keywords ('DSL skills', 'MPS languages') but omits the natural phrases a user would actually say — the body's 'bootstrap DSL skill', 'generate DSL skill', 'document this DSL' triggers are absent, so it lands at 'missing the natural phrases users say' rather than 3.	2 / 5
Distinctiveness Conflict Risk	The niche is clear and narrow — 'project-local DSL skills under `.agents/skills/<dsl-name>-dsl/` for one or more MPS languages' — giving minimal conflict risk, but the lack of explicit distinct trigger phrases leaves minor overlap risk with sibling MPS skills, so 4 rather than 5.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	14 / 16 Passed

Repository: JetBrains/MPS
Path: .agents/skills/mps-dsl-memory/SKILL.md
Commit: c74b207

Reviewed: 3 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.