sales-data-extraction-agent

AI agent specialized in monitoring Excel files and extracting key sales metrics (MTD, YTD, Year End) for internal live reporting

Quality

20%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./specialized-sales-extraction/skills/SKILL.md

Quality

Discovery

32%

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 identifies a reasonably specific domain (Excel-based sales metrics extraction) but suffers from missing explicit trigger guidance ('Use when...'), uses first-person-adjacent framing ('AI agent specialized in'), and lacks comprehensive trigger terms users would naturally use. It would benefit from concrete action verbs, a 'Use when' clause, and broader keyword coverage.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about sales metrics, revenue reports, MTD/YTD figures, or needs data extracted from Excel sales files for reporting.'

Remove 'AI agent specialized in' and replace with concrete action verbs in third person, e.g., 'Monitors Excel files and extracts key sales metrics (MTD, YTD, Year End) to generate internal live reports.'

Include common user-facing trigger terms and file extensions such as 'spreadsheet', '.xlsx', 'sales dashboard', 'revenue tracking', 'sales performance' to improve keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (Excel files, sales metrics) and some actions (monitoring, extracting), and mentions specific metric types (MTD, YTD, Year End), but doesn't list multiple concrete actions beyond monitoring and extracting. The phrase 'AI agent specialized in' is filler rather than actionable detail.	2 / 3
Completeness	Describes what it does (monitoring Excel files and extracting sales metrics) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also somewhat weak, so this scores a 1.	1 / 3
Trigger Term Quality	Includes some relevant keywords like 'Excel files', 'sales metrics', 'MTD', 'YTD', 'Year End', and 'live reporting', but misses common variations users might say (e.g., 'spreadsheet', '.xlsx', 'dashboard', 'sales report', 'revenue tracking'). The acronyms are helpful but niche.	2 / 3
Distinctiveness Conflict Risk	The combination of Excel + sales metrics + live reporting is somewhat specific, but 'monitoring Excel files' could overlap with general Excel/spreadsheet skills. The sales metrics focus (MTD, YTD) adds some distinctiveness but without explicit trigger boundaries, overlap risk remains.	2 / 3
	Total	7 / 12 Passed

Implementation

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

This skill reads more like a product requirements document or agent persona description than actionable instructions for Claude. It lacks any executable code, concrete examples, SQL schemas, or specific library usage. The persona/identity section and success metrics waste tokens on content that doesn't help Claude perform the task.

Suggestions

Replace the abstract descriptions with executable Python code examples showing Excel parsing with openpyxl/pandas, fuzzy column matching logic, and PostgreSQL insertion

Remove the 'Identity & Memory', 'Core Mission', and 'Success Metrics' sections entirely—they add no actionable value

Add a concrete example showing an input Excel structure (column names, sheet names) mapped to expected output/database schema

Add explicit validation checkpoints to the workflow: e.g., validate parsed data before DB insert, verify row counts after insertion, rollback on failure

Dimension	Reasoning	Score
Conciseness	The 'Identity & Memory' section with 'Core Traits' and persona description is entirely unnecessary fluff that Claude doesn't need. The 'Core Mission' section restates what the title already conveys. 'Success Metrics' like '< 2% row-level failures' are aspirational statements, not actionable instructions. Significant token waste throughout.	1 / 3
Actionability	No executable code, no concrete commands, no specific library recommendations, no example Excel structures, no SQL schemas, no configuration examples. Everything is described abstractly ('use fuzzy column name matching', 'bulk insert into PostgreSQL') without showing how to actually do it.	1 / 3
Workflow Clarity	The 8-step workflow is a high-level description without any concrete commands, validation checkpoints, or error recovery steps. For a batch data processing pipeline involving database writes, there are no explicit validation gates or feedback loops, which should cap this at 2 at best—but the steps are too vague even for that.	1 / 3
Progressive Disclosure	The content has reasonable section structure (File Monitoring, Metric Extraction, Data Persistence, Workflow Process), but it's a monolithic document with no references to external files for detailed schemas, examples, or configuration. The sections themselves contain the right categories but lack depth.	2 / 3
	Total	5 / 12 Passed

Validation

90%

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 — 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

Repository: OpenRoster-ai/awesome-openroster
Commit: 09aef5d

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.