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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./docs/project/launch/bankr-skills/breakra/SKILL.md

The canonical home for this skill is breakra in danbuildss/breakra

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.

The body is a dense, highly actionable operational guide with an exemplary paid-API workflow: explicit validation checklist before signing, a single-signature rule, and recovery guidance for every failure mode. Only minor redundancy, the signing code living in an external reference rather than inline, and the absence of a local bundle keep conciseness and progressive disclosure at 4.

DimensionReasoningScore

Conciseness

The body is dense and operational with no padding and no explanations of concepts Claude already knows (it never explains what OpenAPI or semver is): "POST the body with no payment. You get 402 with the terms in the payment-required header (base64 JSON)." It is a 4 rather than 5 because of minor redundancy — the never-charged conditions are stated in both the Paying rules ("Not charged only when...") and the Errors section header "Errors (never charged)" — and a few long sentences could be tightened. Not a 3: there are no unnecessary explanations.

4 / 5

Actionability

Concrete, executable guidance throughout: exact commands ("bun src/cli.ts check before.yaml after.yaml", "claude mcp add breakra -- bun /path/to/breakra/src/cli.ts mcp"), exact endpoints, full example request and response JSON, and an error table with specific fixes. It is a 4 rather than 5 because the hosted paid path names the exact functions ("x402HTTPClient.getPaymentRequiredResponse, createPaymentPayload and encodePaymentSignatureHeader") but leaves the actual signing code to an external reference client instead of inline copy-paste code. Well above 3: nearly everything is directly executable.

4 / 5

Workflow Clarity

The payment workflow is a numbered sequence with explicit pre-sign validation ("Check the terms before signing. Refuse anything that differs" plus a field-by-field terms table), a one-signature rule, and feedback loops for every failure mode: retry rules per error code, and for unknown outcomes "wait at least 60 s ... and check your wallet's USDC transfers to payTo before trying again." This matches the level-5 anchor (explicit validation steps, error-recovery loops, checklist for a complex process), including for the irreversible paid operation.

5 / 5

Progressive Disclosure

No local bundle files exist (no references/, scripts/, or assets/), but bulk detail is appropriately offloaded to clearly signaled, one-level-deep links: "The full rule table is in RULES.md", "Example request and response: examples/", "A reference client ... examples/client.ts." It is a 4 rather than 5 because the ~125-line body inlines dense protocol material (the full payment-terms table, the complete error-code table) that could have been split into a bundled reference file, and all references are external URLs rather than a local bundle. Not a 3: references are clearly signaled, not buried, and the body is well-sectioned.

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.

The description communicates a distinct, concrete capability with strong specificity and a well-defined niche, but it omits any explicit 'when to use' trigger guidance, which caps completeness at 3. It also loses a point on specificity for the second-person phrase 'the operations you depend on'. An explicit 'Use when...' clause with natural synonyms would materially improve it.

Suggestions

Add an explicit trigger clause such as 'Use when reviewing a PR that changes an OpenAPI spec, upgrading a third-party API dependency, or writing release notes / a migration guide' — the 'when' is currently only implied, capping completeness at 3.

Include natural synonyms users actually say — 'breaking change', 'backward compatibility', 'API diff' — alongside the current domain keywords to round out trigger-term coverage.

Rewrite 'the operations you depend on' in third person (e.g. 'the operations a caller depends on') to avoid the second-person voice penalty.

DimensionReasoningScore

Specificity

Quotes: "get a verdict (safe/review/block), a semver bump, and every change classified with evidence and a recommended fix" — multiple concrete, specific actions with comprehensive coverage, matching the level-5 anchor. However, the second-person phrase "the operations you depend on" incurs the rubric's 1-point voice penalty, dropping it to 4. It is not a 3 because it far exceeds '1-2 concrete actions'.

4 / 5

Completeness

The 'what' is explicit and clear ("Check whether an OpenAPI 3.0/3.1 change ... may break API consumers ... get a verdict ... semver bump"), but there is no 'Use when...' clause or equivalent explicit trigger guidance — 'when' is only weakly implied by "an OpenAPI 3.0/3.1 change", which caps this at 3 per the judging guidelines. Not a 4 because the 'when' is not present in any explicit form.

3 / 5

Trigger Term Quality

Quotes: "OpenAPI 3.0/3.1 change", "may break API consumers", "old and new contract", "semver bump", "CLI/MCP" — good natural keyword coverage users would plausibly say. It is a 4 rather than 5 because common variations like "breaking change", "backward compatibility", "API diff", or "Swagger" are missing; not a 3 since coverage goes well beyond 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

Quotes: "OpenAPI 3.0/3.1 change (JSON or YAML)", "may break API consumers", "contract" — a clear niche (OpenAPI contract compatibility checking) with distinct trigger terms and minimal conflict risk with other skills. Not a 4: the domain and vocabulary are so specific that overlap risk is essentially nil.

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

docs/project/launch/bankr-skills/breakra/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.