CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-rpc-endpoint

Add a WorldMonitor JSON API endpoint as a sebuf RPC — proto definition, make generate, handler, gateway, client wrapper, and contract checks. Use when adding or changing an RPC method or service, or when tempted to add a standalone api/*.js or api/*.ts data endpoint.

Quality

89%

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

86%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 lean, highly actionable skill body that front-loads project-specific rules, sequences the work in numbered steps, and closes with a concrete verification checklist. The only weaknesses are the absence of a minimal example for the handler and client-wrapper steps, and no error-recovery loop for failing checks.

Suggestions

Add a minimal handler or client-wrapper skeleton (a few lines each) so steps 3 and 5 are copy-paste ready rather than directory pointers.

Add one line of recovery guidance in Verify (e.g., what to do when `make breaking` or `lint:api-contract` fails) to close the feedback loop.

DimensionReasoningScore

Conciseness

Every line carries repo-specific knowledge Claude cannot infer ("getCachedJson(key, true)", "[(sebuf.http.int64_encoding) = INT64_ENCODING_NUMBER]", "PREMIUM_RPC_PATHS"), with zero padding or explanation of known concepts. Matches the lean anchor-5 example.

5 / 5

Actionability

Concrete commands ("make generate", "npm run lint:api-contract", "npm run test:related") and an inline proto option template make most guidance executable. Minor gaps: "Wrap the generated client in src/services/{domain}/" and the handler implementation step give no example of what the result looks like.

4 / 5

Workflow Clarity

Six clearly numbered steps plus a dedicated Verify section with explicit checks ("make lint and make breaking", "Confirm the generated diff matches the proto change only") and one contingency for toolchain unavailability. It sits between anchors 4 and 5 because there is no fix-and-retry feedback loop when a verification check fails.

4 / 5

Progressive Disclosure

Under 50 lines with well-organized Rules/Steps/Verify sections and clearly signaled one-level-deep references ("Full walkthrough with examples: [docs/adding-endpoints.mdx]", "Framework notes: [CONTRIBUTING.md#...]"). No bundle files exist or are needed, so the simple-skill organization applies.

5 / 5

Total

18

/

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 following the best-practice pattern: concrete action list for "what" plus an explicit "Use when" clause with multiple concrete triggers, including a clever behavioral trigger for the common mistake it prevents. Only minor keyword variations are absent from the trigger set.

DimensionReasoningScore

Specificity

"proto definition, make generate, handler, gateway, client wrapper, and contract checks" lists multiple concrete actions covering the entire pipeline, matching the comprehensive anchor-5 example. Not 4: there are no coverage gaps in the action list for this task.

5 / 5

Completeness

The description explicitly answers both "what" (the sebuf RPC pipeline action list) and "when" ("Use when adding or changing an RPC method or service, or when tempted to add a standalone api/*.js or api/*.ts data endpoint") with concrete trigger phrases, matching the anchor-5 good example pattern.

5 / 5

Trigger Term Quality

"adding or changing an RPC method or service", "JSON API endpoint", and "api/*.js or api/*.ts data endpoint" give good natural keyword coverage including file patterns. A few plausible user phrasings (e.g. "API route", "backend endpoint") are missing, so it falls just short of the comprehensive-synonyms anchor 5.

4 / 5

Distinctiveness Conflict Risk

"Add a WorldMonitor JSON API endpoint as a sebuf RPC" carves out a clear project-specific niche, and the anti-pattern trigger for standalone api/*.js endpoints makes wrong-skill triggering unlikely. Minimal conflict risk with any generic skill.

5 / 5

Total

19

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 2 suspicious

Warning

Total

13

/

16

Passed

Repository

koala73/worldmonitor

Path

.agents/skills/add-rpc-endpoint/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.