CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

azure-typespec-author

Authors Azure TypeSpec API specifications. MUST BE USED for all .tsp changes except naming-only client.tsp SDK overrides handled by azure-typespec-sdk-naming. WHEN: versions, resources, operations, models, properties, decorators, visibility, constraints, breaking changes, LRO for ARM or data-plane. DO NOT USE FOR: naming-only client.tsp overrides, SDK generation/releases, single MCP calls. INVOKES: azure-sdk-mcp:azsdk_typespec_retrieve_knowledge, azure-sdk-mcp:azsdk_run_typespec_validation.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/azure-typespec-author/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

66%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 excels at workflow clarity — sequenced steps, mandatory validation, a fix-and-rerun loop, and detailed case-specific checklists — and its reference structure is well designed. It is dragged down by fourfold repetition of the 'no simple edits' rule and by the fact that all seven referenced reference files are missing from the bundle, leaving the detailed executable guidance unavailable.

Suggestions

Consolidate the 'no simple edits' mandate, which is stated four times in the Triggers section and Rules list, into a single rule to save tokens without losing the point.

Ship the seven referenced references/*.md files (analyze-project.md, intake.md, authoring-plan.md, client-configuration.md, agentic-search.md, reference-document-links.md, validation.md) with the skill, or inline the critical commands they contain, since every step currently points to a file that is absent from the bundle.

Tighten the knowledge-route rules (catalog access, route selection, one-source rule), which span multiple long bullets and partially overlap, into one compact decision rule.

DimensionReasoningScore

Conciseness

The body mostly avoids explaining concepts Claude already knows, but the 'no simple edits' mandate is restated four times ('must be invoked immediately... regardless of how simple the task appears', 'Do NOT skip this skill for "simple" declaration tasks', 'Always follow the full source-authoring workflow — even seemingly simple changes', 'Mandatory for ordinary .tsp edits — even a single ? change can be breaking'), and the opening paragraph plus Triggers section repeat the frontmatter description. It could be tightened noticeably without losing information.

3 / 5

Actionability

Some concrete guidance is present (the `tsp compile .` command, exact MCP tool names, the ordered Analyze→...→Validate pipeline, and an enumerated §6.2 Case 3 checklist), but the per-step executable detail is delegated to seven 'See [x.md](references/x.md)' files that are not present in the bundle, so key operational details are missing as shipped. Not score 2, since the body itself gives specific commands and specific direction rather than high-level hints.

3 / 5

Workflow Clarity

Clear seven-step sequence with an overview pipeline line, explicit validation checkpoints ('Run validation MCP when available and always run tsp compile .'), a required ✅/❌ output checklist, and an explicit feedback loop ('Fix every ❌ and re-run until all checks pass, subject to the retry limit... report a blocker if errors remain'). This matches the anchor-5 example with validation, error recovery, and checklists; it clearly exceeds anchor 4's 'minor validation gaps'.

5 / 5

Progressive Disclosure

The structure is genuinely good: an overview body with well-signaled, one-level-deep references organized in a per-step layout plus a Reference Files table with purposes. However, none of the seven referenced references/*.md files exist in the bundle, so the disclosure chain is broken in practice — more than the 'minor organization gaps' of anchor 4, but well above anchor 3's vaguely-signaled or inlined content.

4 / 5

Total

15

/

20

Passed

Description

87%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.

A strong description: third-person, concrete, with explicit what/when and clear scope boundaries against the sibling naming skill and SDK workflows. Only minor gaps — a single-verb capability statement and a few missing natural trigger variations.

DimensionReasoningScore

Specificity

Names the domain ('Authors Azure TypeSpec API specifications') and enumerates many concrete change types ('versions, resources, operations, models, properties, decorators, visibility, constraints, breaking changes, LRO for ARM or data-plane'), but the capability statement rests on a single verb and body-covered topics (suppressions, operationId, spread models, Swagger conversion) are omitted — minor gaps rather than the comprehensive action list of a 5.

4 / 5

Completeness

Explicitly answers both: what ('Authors Azure TypeSpec API specifications') and when ('WHEN: versions, resources, operations, models, properties, decorators, visibility, constraints, breaking changes, LRO for ARM or data-plane') with concrete trigger phrases, plus 'MUST BE USED for all .tsp changes' and a 'DO NOT USE FOR' exclusion list. This matches the anchor-5 example structure and clearly exceeds anchor 4's looser 'when' clause.

5 / 5

Trigger Term Quality

Good natural keyword coverage including the file extension ('.tsp changes', 'TypeSpec', 'ARM', 'data-plane', 'models', 'decorators', 'breaking changes'), which users of this domain would actually say. A few natural variations are missing ('add API version', 'REST API spec', 'bump version'), keeping it below the synonym-complete anchor 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche (Azure TypeSpec .tsp authoring) with distinct triggers and an explicit boundary against the sibling skill ('except naming-only client.tsp SDK overrides handled by azure-typespec-sdk-naming', 'DO NOT USE FOR: ... SDK generation/releases, single MCP calls'), so mis-triggering risk is minimal.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 14 missing

Warning

referenced_paths_exist

Referenced path issues: 14 missing

Warning

Total

14

/

16

Passed

Repository

Azure/azure-rest-api-specs

Path

.github/skills/azure-typespec-author/SKILL.md

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.