CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/chargeback-flow-test-author

Workflow-driven skill that builds the chargeback / dispute test suite: canonical reason codes (Visa 10.4 fraud, 13.1 services-not-provided; Mastercard MCC 4855), per-gateway dispute APIs (Stripe Disputes, Adyen Chargeback notifications, PayPal Disputes), the evidence-submission flow + window, and disposition outcomes (won / lost / accepted). Use when designing dispute coverage; for refunds use refund-test-matrix-builder, for webhook redelivery + idempotency use payment-webhook-replay, and for the lifecycle state model use payment-flow-states-reference.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Overview
Quality
Evals
Security
Files

Quality

Content

85%

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

A well-structured, highly actionable body with executable tests, explicit validation checkpoints, and a real one-level-deep reference for the reason-code tables. Its main weakness is mild redundancy between the How-to-use list, the numbered Steps, and the Worked example, which costs some token efficiency.

Suggestions

Collapse the 'How to use' 7-step list and the 'Step 1-7' sections into a single sequenced workflow to remove overlapping restatements of the same guidance.

Trim the 'Worked example' to only the parts not already shown as code in Steps 1-5 (e.g. the 13.1 → product_not_received mapping and the final cell-status note), since it currently re-narrates the prior steps.

Move the per-gateway API snippets (Stripe/Adyen/PayPal) into a references/gateway-disputes.md file so the body stays an overview, consistent with how the reason-code catalog is already externalized.

DimensionReasoningScore

Conciseness

It largely avoids explaining concepts Claude already knows (only a one-line chargeback definition, no primer on Stripe/PDFs) and leans on executable code, but the 'How to use' 7-step list overlaps with the 'Step 1-7' sections, and the 'Worked example' re-narrates Steps 1-4; tightening that redundancy would lift it to a 3.

2 / 3

Actionability

Provides fully executable, copy-paste-ready TypeScript tests with real SDK calls (stripe.paymentIntents.create with pm_card_createDispute, stripe.disputes.update with concrete evidence fields), exact assertions, a YAML matrix, and ledger reconciliation tests with specific entry types.

3 / 3

Workflow Clarity

A clear sequenced multi-step process (How-to-use 7 steps mirrored by Steps 1-7) with explicit validation checkpoints — assert status === 'needs_response', assert has_evidence before due_by, webhook-driven confirmation of final state, and ledger assertions — and the Anti-patterns table reinforces due-date tracking and webhook handling.

3 / 3

Progressive Disclosure

The reason-code catalog is appropriately offloaded to references/reason-codes.md (a real, confirmed bundle file), referenced inline via markdown links at multiple points, keeping the body an overview with one-level-deep, clearly signaled navigation.

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.

A highly specific, third-person description that cleanly answers what the skill does and when to use it, with concrete enumerated capabilities and explicit routing away from sibling skills. The only minor cost is a slight density of domain jargon, but it remains natural enough for the target user.

DimensionReasoningScore

Specificity

Names concrete, enumerated actions — 'builds the chargeback / dispute test suite', 'canonical reason codes (Visa 10.4 fraud, 13.1 services-not-provided; Mastercard MCC 4855)', 'per-gateway dispute APIs (Stripe Disputes, Adyen Chargeback notifications, PayPal Disputes)', 'evidence-submission flow + window', and 'disposition outcomes (won / lost / accepted)' — rather than vague language.

3 / 3

Completeness

Explicitly answers both what (builds the suite covering reason codes, gateway APIs, evidence flow, and outcomes) and when ('Use when designing dispute coverage'), and additionally routes to sibling skills, so neither axis is missing or implied.

3 / 3

Trigger Term Quality

Covers natural terms a user would say — 'chargeback', 'dispute', 'dispute coverage', 'designing dispute coverage', 'evidence-submission', 'reason codes' — with good variation across both the problem domain and the testing intent.

3 / 3

Distinctiveness Conflict Risk

It carves a clear niche — chargeback/dispute test authoring — and explicitly disambiguates from siblings ('for refunds use refund-test-matrix-builder, for webhook redelivery + idempotency use payment-webhook-replay'), making a wrong-skill trigger unlikely.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents