CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/grpcurl-cli

Use when calling a gRPC service by hand or from a script: listing and describing services via reflection or proto files, invoking unary and streaming methods with JSON input, TLS and plaintext options, auth headers and exit codes for smoke tests and CI gates. Uses grpcurl.

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

Overview
Quality
Evals
Security
Files

Quality

Content

82%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.

A dense, highly actionable reference: nearly all guidance is executable command examples with flag tables, validation via exit codes, and an honest limitations/anti-patterns section. The main costs are minor repetition (README and status-code citations repeated multiple times) and an implicit rather than explicit workflow sequence, with everything inlined into one ~330-line file.

Suggestions

Cite the grpcurl README and the status-code catalog once (e.g., in References) instead of repeating the links four and three times respectively, and drop or de-emphasize the pinned v1.9.3 version to trim tokens.

Add a brief explicit step sequence at the top of Running (e.g., 1. pick descriptor source → 2. list/describe → 3. invoke with -d → 4. check exit code) so the workflow order is stated, not implied by section layout.

Move the full GitHub Actions smoke-test workflow and the reflection smoke matrix into a references/ file (e.g., ci-examples.md) linked from a short CI integration section, to reduce inline length and enable true progressive disclosure.

DimensionReasoningScore

Conciseness

The body is command-first with tables and assumes Claude's competence (no gRPC tutorials), but it is not fully lean: the grpcurl README link is repeated four times, the status-code catalog citation three times, and a pinned "v1.9.3" release version adds time-sensitive detail outside any old-patterns section. This fits the efficient-with-minor-trimming anchor rather than the every-token-earns-its-place anchor at 5, and there is no unnecessary conceptual explanation that would drop it to 3.

4 / 5

Actionability

Everything is copy-paste executable: list/describe commands, plaintext/TLS/mTLS invocations, a flags table, newline-delimited streaming via `-d @` heredoc, an exit-code `if/else` script, `jq` parsing, and a complete GitHub Actions workflow. Specific examples cover the common cases, matching the fully-executable anchor.

5 / 5

Workflow Clarity

Sections imply a coherent sequence (install → choose descriptor source → discover → invoke → parse results) and validation checkpoints exist ("grpcurl -version" verify, exit-code branching, the reflection smoke matrix). It stops short of the 5 anchor because the sequence is implicit in section order rather than an explicit ordered workflow with fix-and-retry feedback loops, but checkpoints are present so it is above the 3 anchor.

4 / 5

Progressive Disclosure

A single-file skill with clear section headers and clearly signaled one-level-deep references to companion skill files ("Companion catalogs: `buf-cli-lint-breaking-build` (references/versioning-strategy.md), `grpc-streaming-test-author` (references/status-codes.md)"). No bundle files exist for this skill, so all content — including the full CI workflow — lives inline in SKILL.md, which keeps it at the good-structure-with-minor-gaps anchor rather than the clear-split-with-references anchor at 5.

4 / 5

Total

17

/

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.

A strong description: third-person, concise, and comprehensive, pairing an explicit "Use when" trigger clause with an itemized capability list that names the tool. The only weakness is modest synonym/extension coverage in trigger terms (no ".proto", "protobuf", or "endpoint" phrasing).

DimensionReasoningScore

Specificity

Enumerates concrete actions across the tool's full surface: "listing and describing services via reflection or proto files, invoking unary and streaming methods with JSON input, TLS and plaintext options, auth headers and exit codes for smoke tests and CI gates". This matches the comprehensive-coverage anchor; a score of 4 would require minor coverage gaps, and none are present.

5 / 5

Completeness

Opens with an explicit "Use when calling a gRPC service by hand or from a script" giving concrete trigger contexts (manual and scripted), and the "what" is fully itemized in the same sentence. The when-clause is explicit and specific, exceeding the 4 anchor where "when" could be more explicit.

5 / 5

Trigger Term Quality

Good natural-term coverage ("calling a gRPC service", "smoke tests", "CI gates", "proto files", "streaming", "grpcurl") matching the good-coverage anchor. It falls short of the 5 anchor because it omits synonyms and file extensions users might naturally say (".proto", "protobuf", "test a gRPC endpoint"), but sits well above the some-keywords anchor at 3.

4 / 5

Distinctiveness Conflict Risk

"Uses grpcurl" plus the invocation/smoke-test scope carves a clear niche that would not naturally trigger for sibling concerns like load testing (ghz) or mocking. Distinct triggers give minimal conflict risk, matching the 5 anchor rather than the minor-overlap 4 anchor.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 6 missing

Warning

Total

15

/

16

Passed

Reviewed

On this page