tdg-personal/finance-billing-ops
Evidence-first revenue, pricing, refunds, team-billing, and billing-model truth workflow for ECC. Use when the user wants a sales snapshot, pricing comparison, duplicate-charge diagnosis, or code-backed billing reality instead of generic payments advice.
82
82%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that clearly communicates specific capabilities (sales snapshots, pricing comparisons, duplicate-charge diagnosis), defines explicit trigger conditions, and carves out a distinct niche through the 'evidence-first' and 'code-backed' qualifiers tied to the ECC domain. The contrast with 'generic payments advice' further sharpens when this skill should and should not be selected. Minor improvement could come from expanding file type or format triggers if applicable.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'sales snapshot', 'pricing comparison', 'duplicate-charge diagnosis', and 'code-backed billing reality'. These are distinct, actionable capabilities rather than vague language. | 3 / 3 |
Completeness | Clearly answers both what ('evidence-first revenue, pricing, refunds, team-billing, and billing-model truth workflow') and when ('Use when the user wants a sales snapshot, pricing comparison, duplicate-charge diagnosis, or code-backed billing reality instead of generic payments advice'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'revenue', 'pricing', 'refunds', 'billing', 'sales snapshot', 'pricing comparison', 'duplicate-charge', and contrasts with 'generic payments advice' to clarify scope. These are terms users would naturally use when asking about billing issues. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with the 'ECC' context, 'evidence-first' and 'code-backed billing reality' framing, and explicit contrast against 'generic payments advice'. The combination of domain (ECC billing) and methodology (evidence-first, code-backed) creates a clear niche unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured operational skill that clearly defines its scope, distinguishes itself from related skills, and provides a logical workflow with a useful output template. Its main weaknesses are the lack of concrete executable examples (no API calls, code snippets, or specific tool invocations) and the absence of explicit validation gates within the workflow steps. The content reads more as a decision framework than an actionable playbook.
Suggestions
Add concrete executable examples for key steps—e.g., a Stripe API call to pull recent charges/subscriptions, or a specific code path to inspect for entitlement logic.
Insert explicit validation checkpoints between workflow steps, such as 'Confirm snapshot data is complete before proceeding to diagnosis' with a specific check (e.g., verify subscription count matches expected range).
Include a brief worked example showing the output format populated with realistic data to make the template immediately actionable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient and avoids explaining concepts Claude already knows, but some sections are slightly verbose—e.g., the 'When to Use' and 'Guardrails' sections repeat ideas that are already implicit in the workflow. The skill stack section listing other skills with brief descriptions is useful but could be tighter. | 2 / 3 |
Actionability | Provides structured guidance with clear categories and classification steps, but lacks concrete executable examples—no actual Stripe API calls, no code snippets for inspecting checkout paths or entitlement logic, no specific commands. The workflow is descriptive rather than executable. | 2 / 3 |
Workflow Clarity | The four-step workflow is clearly sequenced and logically ordered, with a good output format template. However, it lacks explicit validation checkpoints or feedback loops—there's no 'verify before proceeding' step between evidence gathering and diagnosis, and the verification section is a passive checklist rather than an active gate. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections, a skill stack that references related skills by name, and appropriate content length for a SKILL.md overview. The content is structured for quick scanning with headers, bullet lists, and a clear output template without being monolithic or requiring deep nesting. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
Reviewed
Table of Contents