resume-quantifier

Find opportunities to add metrics and estimate numbers when exact data unavailable

Quality

30%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/resume-quantifier/SKILL.md

Quality

Content

27%

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

This skill is far too verbose for its purpose, explaining many concepts Claude already knows (metric categories, why numbers matter, role-specific metrics). While it provides useful templates and examples, the content would be dramatically more effective at 20-30% of its current length, focusing on the output format, estimation techniques, and discovery question framework. The lack of a clear sequential workflow and the monolithic structure further reduce its effectiveness.

Suggestions

Cut the content by 70-80%: remove 'Why Quantification Matters', the exhaustive role-specific metric lists, and the categories of metrics section — Claude already knows these. Focus on the output format, estimation techniques, and discovery questions.

Add a clear numbered workflow at the top: 1) Count unquantified bullets, 2) Ask discovery questions for each, 3) Apply estimation technique, 4) Write quantified version, 5) Verify with quality checklist.

Split role-specific metrics and common situations into separate reference files (e.g., ROLE_METRICS.md, ESTIMATION.md) and reference them from a concise overview.

Remove the 'Studies Show' statistics section entirely — Claude doesn't need to be convinced that quantification matters, it just needs to know how to do it.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~300+ lines. Explains obvious concepts Claude already knows (why quantification matters, what categories of metrics exist, what sales/marketing/engineering metrics are). The 'Studies Show' section, the exhaustive role-specific metric lists, and the lengthy estimation technique explanations are all things Claude inherently understands. Most of this content is reference material Claude doesn't need.	1 / 3
Actionability	Provides concrete templates and before/after examples which are useful, but much of the content is descriptive lists (categories of metrics, role-specific metrics) rather than executable instructions. The output format template is helpful but the skill lacks a clear procedural instruction set for Claude to follow when actually performing the task.	2 / 3
Workflow Clarity	The output format section implies a multi-step process (analyze bullets → ask discovery questions → quantify → note estimations), but the workflow is never explicitly sequenced as steps to follow. The discovery questions and estimation techniques are presented as reference material rather than as a clear ordered workflow with checkpoints.	2 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files. The role-specific metric discovery section, estimation techniques, and common situations could all be separate reference files. Everything is inlined in one massive document with no navigation structure beyond headers.	1 / 3
	Total	6 / 12 Passed

Description

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 conveys a general idea of what the skill does—adding metrics and estimating numbers when exact data is unavailable—but it is too vague to be effective for skill selection. It lacks a 'Use when...' clause, concrete action details, and sufficient trigger terms that users would naturally use. The description would benefit significantly from explicit trigger guidance and more specific capability enumeration.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user is writing content that could benefit from quantitative support, such as proposals, reports, presentations, or blog posts that lack specific numbers.'

Include natural trigger terms users would say, such as 'quantify', 'add data points', 'statistics', 'KPIs', 'benchmarks', 'back up claims with numbers', or 'Fermi estimation'.

Specify concrete actions more clearly, e.g., 'Identifies claims that would be stronger with quantitative support, suggests relevant metrics, and provides reasonable estimates using Fermi estimation when exact data is unavailable.'

Dimension	Reasoning	Score
Specificity	The description names a domain (metrics/numbers estimation) and describes some actions ('find opportunities to add metrics', 'estimate numbers'), but lacks concrete specifics about what types of metrics, what contexts, or what outputs are produced.	2 / 3
Completeness	The description addresses 'what' at a high level (finding opportunities to add metrics and estimating numbers) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also weak, so this scores a 1.	1 / 3
Trigger Term Quality	Includes some relevant keywords like 'metrics' and 'estimate numbers', but misses common variations users might say such as 'quantify', 'data points', 'statistics', 'KPIs', 'benchmarks', or 'approximate figures'. The phrase 'find opportunities' is not something a user would naturally say.	2 / 3
Distinctiveness Conflict Risk	The concept of adding metrics and estimating numbers is somewhat specific, but it could overlap with data analysis skills, writing improvement skills, or business reporting skills. The lack of a clear niche or explicit context makes it moderately prone to conflicts.	2 / 3
	Total	7 / 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: paramchoudhary/resumeskills
Path: skills/resume-quantifier/SKILL.md
Commit: 74ae19e

Reviewed: about 12 hours 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.