CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

generating-grpc-services

Generate gRPC service definitions, stubs, and implementations from Protocol Buffers. Use when creating high-performance gRPC services. Trigger with phrases like "generate gRPC service", "create gRPC API", or "build gRPC server".

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/api-development/grpc-service-generator/skills/generating-grpc-services/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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, concise overview with sound progressive disclosure, but the core workflow steps lack executable commands (which exist only in references/examples.md) and validation checkpoints, and two of the three reference files deliver generic REST content instead of the promised gRPC material.

Suggestions

Inline the actual stub-generation commands in Instructions step 3 (e.g., the `buf generate` and `protoc` invocations already present in references/examples.md) so the body's compile step is executable rather than descriptive.

Add explicit validation checkpoints with a fix-and-retry loop: run `buf lint` after defining messages (step 2), verify generated stubs compile after step 3, and re-run on failure before proceeding — rather than deferring all validation to the integration tests in step 8.

Rewrite references/implementation.md and references/errors.md to match what the body promises — they currently contain generic REST-API guidance (HTTP endpoints, 429/Retry-After headers, OpenAPI, curl/Postman) instead of a gRPC implementation guide and gRPC error-status patterns.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — it uses gRPC status codes and concepts like "oneof" and mTLS without explaining them, and the error table is dense and useful. Not anchor 5 only because the Overview paragraph ("Generate gRPC service definitions, client/server stubs...") largely repeats the frontmatter description and could be trimmed.

4 / 5

Actionability

Steps name concrete tools and specifics ("grpc_tools_node_protoc_plugin", "grpcio-tools", `grpc.health.v1.Health`, status codes `INVALID_ARGUMENT`/`PERMISSION_DENIED`), but the body contains no executable code or commands — step 3's "Compile `.proto` files with `protoc`" never shows the invocation, and step 8's testing gives no command. This sits between anchor 3 (concrete but incomplete, missing key executable details) and anchor 4 (mostly executable with minor gaps); the total absence of commands in the body pulls it to 3.

3 / 5

Workflow Clarity

The 9 steps form a coherent sequence (design → compile → implement → interceptors → health → TLS → tests → gateway), but validation is only an end-of-process test step with no intermediate checkpoints (e.g., run `buf lint` after step 2, verify stubs compile after step 3) and no fix-and-retry feedback loop. This mirrors anchor 3's example ("...4. Test the output") rather than anchor 4, which requires most checkpoints present.

3 / 5

Progressive Disclosure

Three real, one-level-deep, clearly signaled references ("See references/implementation.md for the full implementation guide", "for comprehensive error patterns", "for additional examples") with a well-organized 66-line overview body. Not anchor 5 because the split is partially mismatched: references/implementation.md and references/errors.md actually contain generic REST-API guidance (HTTP endpoints, OpenAPI, "Return 429 status with Retry-After header") rather than the promised gRPC implementation guide and gRPC error patterns.

4 / 5

Total

14

/

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 that clearly states what the skill does and when to use it, backed by natural trigger phrases. Minor improvement is possible by mentioning .proto files or additional capability keywords (streaming, interceptors, gateway) for broader trigger coverage.

DimensionReasoningScore

Specificity

"Generate gRPC service definitions, stubs, and implementations from Protocol Buffers" names the domain (gRPC/protobuf) and three concrete actions. It is above anchor 3 (only 1-2 actions) but not anchor 5's comprehensive coverage, since streaming patterns, interceptors, health checks, and the REST gateway mentioned in the body are absent from the description.

4 / 5

Completeness

The description explicitly answers both: what ("Generate gRPC service definitions, stubs, and implementations from Protocol Buffers") and when ("Use when creating high-performance gRPC services") with concrete trigger phrases ("generate gRPC service", "create gRPC API", "build gRPC server"), matching the anchor-5 example structure exactly. Anchor 4's caveat ('when' could be more explicit) does not apply since the when-clause plus trigger list is explicit.

5 / 5

Trigger Term Quality

"generate gRPC service", "create gRPC API", "build gRPC server" are phrases users would naturally say, with "Protocol Buffers" also present. Below anchor 5 because common synonyms and file extensions like ".proto", "protobuf service", or "streaming RPC" are missing; clearly above anchor 3's partial keyword coverage.

4 / 5

Distinctiveness Conflict Risk

gRPC service generation is a clear niche with distinct, unambiguous triggers ("gRPC", "Protocol Buffers"); no generic terms like "works with files" that would collide with other skills. This matches anchor 5's 'clear niche with distinct triggers; minimal conflict risk'.

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

jeremylongshore/tons-of-skills-marketplace

Path

plugins/api-development/grpc-service-generator/skills/generating-grpc-services/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.