CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-typespec-author

Authors and modifies Azure TypeSpec (.tsp) API specifications. USE FOR: any TypeSpec/tsp change — api versions (add, bump, preview, stable, promote), resources, operations, models, properties, decorators, visibility, constraints, breaking changes, LRO, suppressions, operationId, spread model. Covers ARM resource-manager and data-plane services. DO NOT USE FOR: SDK generation, releasing SDK packages, or single MCP tool calls. INVOKES: azure-sdk-mcp:azsdk_typespec_generate_authoring_plan, azure-sdk-mcp:azsdk_run_typespec_validation.

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

Low

Low-risk findings worth noting

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 body is a well-structured overview that delegates detail to real, one-level-deep reference files and enforces validation within its workflow. The main weakness is that the single inline step (Apply Changes) is less concrete than the referenced procedures, and the validation feedback loop lives in a reference rather than inline.

Suggestions

Add a brief inline feedback loop in Step 5 (e.g. 'If validation or tsp compile fails, fix and re-run until clean') so the validate→fix→retry cycle is visible without opening validation.md.

Tighten Step 4 with one or two concrete cues (e.g. apply minimal decorator/versioning edits per the authoring plan, then re-run Step 5) instead of the current abstract instruction.

Trim redundancy between the 'When to invoke' bullet list and the description's USE FOR clause to recover a few tokens.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no padding about what TypeSpec is — but the 'When to invoke' section partially restates the description's USE FOR list and the Constraints section is slightly verbose, keeping it just below a 5.

4 / 5

Actionability

Most steps point to concrete, named reference files (analyze-project.md, intake.md, authoring-plan.md, validation.md) and an MCP tools table gives executable tool names, but Step 4's inline guidance ('Make minimal .tsp edits following the plan') is comparatively abstract, leaving a minor gap.

4 / 5

Workflow Clarity

A clear 6-step checkbox workflow with an explicit mandatory validation step and an 'Always validate after every edit' constraint; the fix-and-revalidate feedback loop itself is delegated to validation.md rather than stated inline, which is a minor checkpoint gap.

4 / 5

Progressive Disclosure

The body is an overview that points to six one-level-deep reference files, all of which exist, clearly signaled via both inline links and a Reference Files table — content is appropriately split and easy to navigate.

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 a strong, concise trigger-rich statement that clearly delineates what the skill does, when to use it, when not to use it, and which MCP tools it invokes. It satisfies every completeness and specificity anchor at the top level.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'api versions (add, bump, preview, stable, promote), resources, operations, models, properties, decorators, visibility, constraints, breaking changes, LRO, suppressions, operationId, spread model' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' ('Authors and modifies Azure TypeSpec (.tsp) API specifications') and 'when' ('USE FOR: any TypeSpec/tsp change ...'), plus a 'DO NOT USE FOR' boundary clause with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms and file extension — 'TypeSpec', 'tsp', '.tsp', 'preview', 'stable', 'decorators', 'models', 'properties', 'breaking changes' — the phrases a user would naturally say when needing this skill.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Azure TypeSpec authoring) with distinct triggers and an explicit 'DO NOT USE FOR: SDK generation, releasing SDK packages, or single MCP tool calls' clause that minimizes conflict with adjacent skills.

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
Azure/azure-rest-api-specs
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.