mps-quotations

Use when writing or debugging MPS quotations and anti-quotations — "node literals" that create SNode trees inline in behavior, typesystem, intentions, generator, and other model code. Covers heavy quotations (`Quotation`, `<...>`), light quotations (`NodeBuilder`, constructor-style for bootstrapping), and the four anti-quotation varieties: child (`%(...)%`), list (`*(...)*`), reference (`^(...)^`), property (`$(...)$`). Reach for this skill whenever the task involves splicing runtime values into quoted node trees or choosing between heavy and light quotations.

Quality

81%

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

71%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 skill body is an efficient, actionable overview with a clear workflow, explicit validation step, and concrete MCP tooling — strong on conciseness, actionability, and workflow clarity. Its main weakness is progressive disclosure: the body points to 11 `references/*.md` files, but the `references/` directory is absent from the bundle, so the navigation it promises is not backed by real files.

Suggestions

Ship the `references/` directory with the 11 referenced `.md` files (heavy-vs-light.md, heavy-quotation.md, antiquotations.md, antiquotation-list.md, antiquotation-property.md, antiquotation-reference.md, property-and-reference-ids.md, light-quotation.md, model-and-node-id.md, concept-catalog.md, source-locations.md) so the Reference Index resolves.

Add an explicit validate→fix→retry loop to the Common-Path Workflow (e.g., 'If `mps_mcp_check_root_node_problems` reports missing used-languages, add them and re-run') to push workflow clarity to the top anchor.

Inline one minimal JSON blueprint example (e.g., a child antiquotation) in the main body so the core case is actionable without opening a reference file.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, assuming MPS competence and front-loading directives and a workflow without padding, but the dense 'Critical Directives' bullet list and the long Reference Index restate some detail that could be trimmed; minor over-explanation keeps it just below the lean/efficient anchor.	4 / 5
Actionability	Concrete, executable guidance dominates: specific MCP tool calls (`mps_mcp_insert_root_node_from_json`, `mps_mcp_check_root_node_problems`), exact syntax tokens, a step-by-step editor workflow, and a decision table, with only minor gaps (no copy-paste JSON blueprint inline in the main body — those live in referenced files).	4 / 5
Workflow Clarity	The 'Common-Path Workflow' is a clear numbered sequence with an explicit validation checkpoint at step 5 (`mps_mcp_check_root_node_problems`) and a rebuild fallback, and the directives call out error conditions; minor gaps (no explicit validate→fix→retry loop spelling out error recovery) keep it just below the highest anchor, and the destructive-cap note is satisfied by the present validation step.	4 / 5
Progressive Disclosure	The body is well-structured as an overview with a clearly signaled, one-level-deep Reference Index pointing to 11 `references/*.md` files — but no `references/` directory (nor `scripts/`/`assets/`) is present in the bundle, so the referenced paths cannot resolve; per the judging guideline to score against the actual bundle structure, the missing files drag this down to the 'some structure but references not verifiable / could be better organized' anchor.	3 / 5
	Total	15 / 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 highly specific and complete, naming concrete capabilities and syntax for both quotation forms and all four anti-quotation kinds while explicitly providing 'Use when'/'Reach for' trigger guidance. Its only minor gap is trigger-term breadth — the vocabulary is technically precise but offers few synonyms a user might phrase differently.

Dimension	Reasoning	Score
Specificity	Names multiple concrete capabilities — heavy quotations (`Quotation`, `<...>`), light quotations (`NodeBuilder`), and all four anti-quotation varieties with their syntax (`%(...)%`, `(...)`, `^(...)^`, `$(...)$`) — giving comprehensive coverage rather than vague domain naming.	5 / 5
Completeness	Explicitly answers both 'what' (node literals creating SNode trees; the quotation/anti-quotation kinds with syntax) and 'when' ('Use when writing or debugging...', 'Reach for this skill whenever the task involves...'), matching the anchor that requires concrete trigger phrases for both.	5 / 5
Trigger Term Quality	Strong natural trigger phrases ('writing or debugging MPS quotations and anti-quotations', 'splicing runtime values into quoted node trees', 'choosing between heavy and light quotations') with concrete syntax tokens users would mention, though the term set is fairly technical and lacks common synonyms beyond the core vocabulary.	4 / 5
Distinctiveness Conflict Risk	The MPS quotations niche, the `jetbrains.mps.lang.quotation` language, and the specific anti-quotation syntax tokens form a clear, narrow trigger surface with minimal overlap risk against other skills.	5 / 5
	Total	19 / 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: 15 missing	Warning

	Total	14 / 16 Passed

Repository: JetBrains/MPS
Path: .agents/skills/mps-quotations/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.