CtrlK
BlogDocsLog inGet started
Tessl Logo

tsp-model

Use when creating, modifying, or documenting TypeSpec domain models. Triggers include adding new entities, value objects, enums, extending base types, or when asked to create a "tsp model", "domain model", "entity", or work with files in the tsp/ directory. Part of the Shep autonomous SDLC platform — https://shep.bot

72

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 content is well-structured, actionable, and concise, with concrete templates and a validation checkpoint. Its main limitation is mild redundancy between the Quick Reference and Common Mistakes sections and an implicit rather than explicit validate-fix-retry loop, which keep conciseness and workflow_clarity at 4.

Suggestions

Add an explicit validate-fix-retry loop to the Validation Commands section (e.g., "If tsp:compile fails, read the error, fix the .tsp file, and re-run until it compiles") to lift workflow_clarity to 5.

Merge or trim the Quick Reference and Common Mistakes tables — several entries (wrong import paths, missing examples) overlap — to tighten conciseness toward a 5.

Make the Required Template runnable by including one fully worked example file (e.g., a complete ActionItem.tsp) alongside the placeholder template, so users have copy-paste-ready guidance.

DimensionReasoningScore

Conciseness

The body is lean and does not explain what TypeSpec or Clean Architecture is; tables and the template earn their place. It sits above the "mostly efficient" anchor but the Quick Reference and Common Mistakes tables lightly restate nearby content, keeping it just short of fully lean.

4 / 5

Actionability

Provides a concrete Required Template, naming rules, base-type selection table, and exact validation commands ("pnpm tsp:compile", "pnpm tsp:format"). The template uses placeholders rather than literal copy-paste, which is appropriate for a generator skill but leaves minor gaps versus fully executable examples.

4 / 5

Workflow Clarity

Steps are sequenced (pick base type → write file following template → run validation) with an explicit Validation Commands checkpoint. It is not a destructive or batch operation, so the 3-cap does not apply; the validation step is present but the fix-and-retry loop is only implicit, capping it just below 5.

4 / 5

Progressive Disclosure

The skill is a single-purpose, well-organized file under ~135 lines with no external bundle files and no need for separate references; sections (Directory Structure, File Conventions, Required Template, Base Types, Validation, Quick Reference) are clearly headed and easy to navigate, matching the simple-skill exception for a 5.

5 / 5

Total

17

/

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 concise yet complete: it names the domain and several concrete actions, provides explicit "Use when" trigger guidance with natural user phrasing, and carves out a distinct niche. It cleanly matches the top anchors on all four dimensions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "creating, modifying, or documenting TypeSpec domain models" plus "adding new entities, value objects, enums, extending base types" — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both what ("creating, modifying, or documenting TypeSpec domain models") and when ("Use when... Triggers include...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases a user would actually say — "tsp model", "domain model", "entity" — plus the file-path trigger "files in the tsp/ directory", covering synonyms and a directory hint.

5 / 5

Distinctiveness Conflict Risk

Targets a clear niche (TypeSpec domain models with the tsp/ directory) with distinct triggers, making overlap with other skills minimal.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
shep-ai/shep
Reviewed

Table of Contents

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.