data-consolidation-agent
AI agent that consolidates extracted sales data into live reporting dashboards with territory, rep, and pipeline summaries
35
20%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./specialized-data-consolidation/skills/SKILL.mdQuality
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 clear sales reporting domain with some useful keywords but suffers from lacking explicit trigger guidance ('Use when...') and insufficient specificity about concrete actions. The use of 'AI agent' as a prefix is unnecessary filler that doesn't help with skill selection. It needs clearer activation triggers and more concrete action verbs to be effective in a multi-skill selection context.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to build sales dashboards, generate pipeline reports, or summarize sales performance by territory or rep.'
Replace the vague 'AI agent that consolidates' opener with specific concrete actions, e.g., 'Aggregates sales data into dashboards, generates territory breakdowns, tracks rep performance, and visualizes pipeline stages.'
Include additional natural trigger terms users might say, such as 'sales report', 'revenue summary', 'deal pipeline', 'quota tracking', 'CRM data', or 'sales analytics'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (sales data/reporting) and some actions (consolidates, summaries), but lacks specific concrete actions like 'creates charts', 'filters by date range', or 'generates CSV exports'. The terms 'territory, rep, and pipeline summaries' add some specificity but remain at a high level. | 2 / 3 |
Completeness | Describes what it does (consolidates sales data into dashboards) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also only moderately clear, warranting a score of 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'sales data', 'reporting dashboards', 'territory', 'rep', 'pipeline' that users might mention. However, it misses common variations like 'sales report', 'CRM', 'revenue', 'forecast', 'quota', or 'deals'. Coverage is partial. | 2 / 3 |
Distinctiveness Conflict Risk | The sales-specific domain (territory, rep, pipeline) provides some distinctiveness, but 'reporting dashboards' and 'extracted data' are broad enough to overlap with general data visualization or analytics skills. The niche is somewhat defined but not sharply delineated. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads like a product requirements document or agent persona description rather than actionable instructions for Claude. It lacks any concrete code, SQL queries, JSON output schemas, or executable examples. The content is heavy on aspirational descriptions ('strategic data synthesizer', 'dashboard loads in < 1 second') and light on the specific technical guidance Claude would need to actually consolidate data into dashboards.
Suggestions
Replace the abstract workflow steps with concrete, executable SQL queries or code snippets showing how to aggregate territory data, calculate attainment, and build pipeline snapshots.
Add a concrete JSON schema or example output for the dashboard report so Claude knows exactly what structure to produce.
Remove the 'Identity & Memory', 'Core Traits', and 'Success Metrics' sections — these are persona fluff that waste tokens without adding actionable guidance.
Add validation checkpoints to the workflow, such as verifying aggregate totals match detail rows and handling division-by-zero cases with explicit code examples.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is padded with personality traits ('Analytical', 'Comprehensive'), mission statements, and success metrics that Claude doesn't need. The 'Identity & Memory' section explains what Claude should be rather than what it should do. Much of this is filler that doesn't contribute actionable guidance. | 1 / 3 |
Actionability | There is no executable code, no SQL queries, no JSON schema for the dashboard output, no concrete commands. Everything is described abstractly — 'Execute parallel queries for all data dimensions' and 'revenue / quota * 100' without showing actual implementation. The skill describes rather than instructs. | 1 / 3 |
Workflow Clarity | The 5-step workflow is extremely vague ('Execute parallel queries for all data dimensions', 'Aggregate and calculate derived metrics') with no validation checkpoints, no error handling for division by zero (mentioned in rules but not in workflow), and no feedback loops. For a data consolidation task, there's no verification that aggregates match detail rows. | 1 / 3 |
Progressive Disclosure | The content is organized into logical sections (Critical Rules, Technical Deliverables, Workflow Process) which provides some structure. However, there are no references to external files for detailed schemas, query templates, or examples, and the deliverables section could benefit from linking to concrete templates rather than listing bullet points inline. | 2 / 3 |
Total | 5 / 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 | |
- Repository
- OpenRoster-ai/awesome-openroster
- Commit
09aef5d
- 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.