CtrlK
BlogDocsLog inGet started
Tessl Logo

regenerate-grpc-stubs

Regenerate Python + TypeScript gRPC stubs after editing proto files. Use when proto/*.proto changes, imports from bindu.grpc.generated fail, CI reports generated-code drift, or HandleMessages calls fail with proto mismatch.

73

Quality

92%

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear, verification-gated workflow and clean sectioning. Its main weakness is structural redundancy between the Safety/Never-do sections and the Execution Contract/Steps, which costs tokens without adding clarity.

Suggestions

Consolidate 'Safety' and 'Never do': the warning against editing bindu/grpc/generated/ and sdks/typescript/src/generated/ appears near-verbatim in both — merge them into a single section to remove the duplication.

Drop the 'Execution Contract' or reduce it to a one-line summary, since its five items already restate the detailed 'Steps' section; keeping both restates the workflow twice.

Add a brief explicit error-recovery loop to the verify steps (e.g. 'if mypy/build/tests fail, fix the proto or generation script and re-run from step 2') to close the implicit feedback loop.

DimensionReasoningScore

Conciseness

The tone is lean and avoids explaining concepts Claude already knows, but it is structurally repetitive: the warning against editing the generated dirs appears near-verbatim in both 'Safety' and 'Never do', and the 'Execution Contract' restates the 'Steps' section — so it could be tightened. Not a 3 because not every token earns its place; not a 1 because there is no concept-padding verbosity.

2 / 3

Actionability

Provides fully executable, copy-paste-ready commands (e.g. 'bash scripts/generate_protos.sh all', 'uv run mypy bindu/grpc/', 'cd sdks/typescript && npm run build', 'uv run pytest tests/integration/grpc/ -v') plus a concrete commit-message template, matching the anchor-3 example.

3 / 3

Workflow Clarity

A clear 7-step sequence with explicit, gated verification checkpoints (mypy, build, integration tests in steps 3–5) and an Execution Contract checklist; validation is present so the batch-operation cap at 2 does not apply. Not a 2 because checkpoints are explicit rather than implicit.

3 / 3

Progressive Disclosure

A single-purpose skill organized into well-labeled sections (Overview, Inputs, Safety, Execution Contract, Steps, Never do), with the only file references (proto and docs paths) one level deep and clearly signaled; no bundle content needs splitting.

3 / 3

Total

11

/

12

Passed

Description

100%

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, concrete, and complete: it states exactly what the skill does and gives several explicit, natural trigger conditions. It is highly specific to its niche with low conflict risk.

DimensionReasoningScore

Specificity

Names a concrete action with specific artifacts — 'Regenerate Python + TypeScript gRPC stubs after editing proto files' — which is more specific than the anchor-2 example and lists the distinct targets/languages rather than vague abstraction.

3 / 3

Completeness

Explicitly answers both what ('Regenerate Python + TypeScript gRPC stubs') and when (a 'Use when…' clause with multiple triggers), matching the anchor-3 example.

3 / 3

Trigger Term Quality

The 'Use when proto/*.proto changes, imports from bindu.grpc.generated fail, CI reports generated-code drift, or HandleMessages calls fail with proto mismatch' clause gives good coverage of natural phrases a developer in this codebase would actually say.

3 / 3

Distinctiveness Conflict Risk

Occupies a tight niche (gRPC stub regeneration after proto edits) bound to codebase-specific symbols (bindu.grpc.generated, HandleMessages), making conflict with other skills unlikely.

3 / 3

Total

12

/

12

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
GetBindu/Bindu
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.