file-expenses

Help submit an expense or reimbursement on any platform. Detects the right tool (Benepass, Brex, Concur, Expensify, etc.), finds receipts, checks for duplicates, and walks through submission.

Quality

66%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Critical

Do not install without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./examples/file-expenses/SKILL.md

Quality

Discovery

82%

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 description with excellent specificity, naming concrete actions and specific platforms. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill. The natural trigger terms are well-chosen and cover the expense management domain thoroughly.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about submitting expenses, filing reimbursements, uploading receipts, or mentions any expense management platform.'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: submit expense/reimbursement, detect the right tool, find receipts, check for duplicates, and walk through submission. These are clear, actionable capabilities.	3 / 3
Completeness	The 'what' is well-covered with specific actions and platform names, but there is no explicit 'Use when...' clause or equivalent trigger guidance. The when is only implied by the nature of the actions described, which caps this at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Includes strong natural keywords users would say: 'expense', 'reimbursement', 'receipts', 'duplicates', 'submission', and names specific platforms (Benepass, Brex, Concur, Expensify). These cover common variations of how users would phrase expense-related requests.	3 / 3
Distinctiveness Conflict Risk	The description carves out a very clear niche around expense/reimbursement submission with specific platform names. This is unlikely to conflict with other skills given the distinct domain and trigger terms.	3 / 3
	Total	11 / 12 Passed

Implementation

50%

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

This skill provides a solid conversational workflow for expense submission with good user-facing design elements (progress tracker, summary card, duplicate detection). However, it lacks concrete executable examples, platform-specific navigation details, and robust validation checkpoints. The content would benefit from being less descriptive and more prescriptive, with supporting reference files for each expense platform.

Suggestions

Add concrete examples of the progress tracker format, expense summary card, and receipt findings table so Claude knows exactly what to render rather than improvising.

Create separate reference files for each supported expense platform (e.g., BREX.md, CONCUR.md) with specific navigation steps, form field mappings, and known UI patterns.

Add an explicit validation step after form submission (e.g., verify confirmation page appeared, capture confirmation number) to create a proper feedback loop for the destructive action of submitting an expense.

Remove redundant style directives ('never stall', 'without stalling', 'be warm, visual when needed, and anticipatory') that appear multiple times and consolidate into a single behavioral note.

Dimension	Reasoning	Score
Conciseness	The skill is moderately efficient but includes some unnecessary verbosity — phrases like 'Act like a concierge — proactive, visual, and always one step ahead' and 'like a boarding pass' are stylistic padding. The repeated 'without stalling' and 'never stall' instructions are redundant. However, most content is functional and not explaining things Claude already knows.	2 / 3
Actionability	The skill provides a clear procedural flow with specific tool references (ask_user_input_v0, Gmail search, Slack) and concrete behaviors (duplicate checking, pre-filling from receipts, table display). However, it lacks executable code/commands, specific platform navigation steps, or concrete examples of the 'styled expense summary card' or 'progress tracker' formats. The guidance is descriptive rather than fully executable.	2 / 3
Workflow Clarity	The multi-step flow is clearly sequenced (steps 1-9) with some validation (duplicate check, explicit OK before submitting, fallback on failure). However, there are no explicit validation checkpoints for verifying form data was entered correctly on the platform, and the duplicate check is described as 'silent' with no feedback loop if the check itself fails. Missing verification after form submission also caps this.	2 / 3
Progressive Disclosure	The content is a single monolithic file with no references to supporting documents. For a skill covering multiple expense platforms (Benepass, Brex, Concur, Expensify, Ramp), platform-specific navigation details would benefit from separate reference files. The content is reasonably organized with numbered steps but could be better structured with sections for platform-specific guidance.	2 / 3
	Total	8 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: douglasvought/wiggle-skills
Commit: b27906e

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.