CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

breakra

Check whether an OpenAPI 3.0/3.1 change (JSON or YAML) may break API consumers, or the operations you depend on. Send the old and new contract; get a verdict (safe/review/block), a semver bump, and every change classified with evidence and a recommended fix. Free locally (CLI/MCP), or hosted at $0.02 USDC on Base via x402.

Quality

80%

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 ./SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 strong, information-dense body that provides executable commands, concrete request/response examples, and an exemplary validated payment workflow with feedback loops for the risky paid path. Nearly all content is novel operational detail rather than explanation of known concepts. The residual weaknesses are minor: some repetition around charging rules, signing code kept external, and a local scripts/ directory that is shipped but never referenced.

DimensionReasoningScore

Conciseness

The body is dense but almost every token is operational fact Claude could not know (payment terms, limits, error codes, retry rules) and it assumes competence — no explanation of what OpenAPI or semver is. It stops short of anchor 5 because charge-related warnings are repeated across the Price, Paying, and Rules sections and a few clauses could be tightened.

4 / 5

Actionability

Mostly executable: copy-paste commands ('bun src/cli.ts check before.yaml after.yaml', 'claude mcp add breakra -- ...'), a concrete request body and response example, an error table with fixes, and exact verification steps. The paid path names library functions ('x402HTTPClient.getPaymentRequiredResponse', 'createPaymentPayload', 'encodePaymentSignatureHeader') and defers full code to an external examples/client.ts rather than inlining it — a minor gap that keeps it off anchor 5.

4 / 5

Workflow Clarity

The x402 payment flow is a clear numbered sequence (POST unpaid -> check terms -> sign once -> resend with header) with an explicit validation checklist ('Check the terms before signing. Refuse anything that differs'), error-recovery guidance (retry policy per error code), and handling for unknown outcomes (wait 60 s, check wallet transfers) — exactly the anchor-5 pattern of sequence plus checkpoints plus feedback loops.

5 / 5

Progressive Disclosure

Good structure: the body is well-sectioned and bulk detail is linked one level deep and clearly signaled (RULES.md for the full rule table, examples/client.ts for the reference client, openapi.json for the contract). It falls short of anchor 5 because the local scripts/ bundle files are never referenced or navigated from the body, and the full payment-terms and error tables are inlined rather than split out.

4 / 5

Total

17

/

20

Passed

Description

70%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 specific, distinctive description that clearly states what the tool does and what it returns, with strong domain keywords. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which both caps completeness and leaves the natural trigger phrases ('before merging an API change', 'upgrading a third-party API') implicit. A minor second-person phrase also costs it specificity points under the voice rule.

Suggestions

Add an explicit trigger clause such as 'Use when reviewing a PR that changes an OpenAPI contract, upgrading a dependency on a third-party API, or writing release notes / migration guides for an API change.'

Include natural synonym phrases users say — 'breaking change', 'backward compatibility', 'API diff' — to broaden trigger term coverage.

Rewrite 'the operations you depend on' in third person (e.g., 'the operations the caller depends on') to keep the description in a consistent third-person voice.

DimensionReasoningScore

Specificity

The description lists multiple concrete, comprehensive actions — 'Check whether an OpenAPI 3.0/3.1 change (JSON or YAML) may break API consumers', 'get a verdict (safe/review/block), a semver bump, and every change classified with evidence and a recommended fix' — which is anchor-5 coverage, but the second-person phrase 'the operations you depend on' triggers the rubric's 1-point voice penalty, dropping it to 4.

4 / 5

Completeness

The 'what' is clearly and concretely answered (compatibility verdict, semver bump, classified changes with evidence and fixes), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guidelines. The 'when' is only weakly implied by 'Send the old and new contract'.

3 / 5

Trigger Term Quality

Good natural keyword coverage: 'OpenAPI', 'break', 'API consumers', 'semver bump', 'JSON or YAML' — phrases users would plausibly say. It falls short of anchor 5 because common synonyms like 'breaking change', 'backward compatibility', or 'API diff' are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers: OpenAPI 3.0/3.1 breaking-change analysis with a safe/review/block verdict is highly specific and unlikely to fire for unrelated skills; 'Don't use it for Swagger 2.0' boundaries in the body reinforce this.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

danbuildss/breakra

Path

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.