excel-variance-analyzer
Automate budget vs actual variance analysis in Excel with flagging, commentary, and executive summaries for financial reporting and FP&A teams
Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security
Installation for Agentic Skill
View all platforms →skilz install jeremylongshore/claude-code-plugins-plus-skills/excel-variance-analyzer skilz install jeremylongshore/claude-code-plugins-plus-skills/excel-variance-analyzer --agent opencode skilz install jeremylongshore/claude-code-plugins-plus-skills/excel-variance-analyzer --agent codex skilz install jeremylongshore/claude-code-plugins-plus-skills/excel-variance-analyzer --agent gemini
First time? Install Skilz: pip install skilz
Works with 14 AI coding assistants
Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...
Extract and copy to ~/.claude/skills/ then restart Claude Desktop
git clone https://github.com/jeremylongshore/claude-code-plugins-plus-skills cp -r claude-code-plugins-plus-skills/backups/skills-migration-20251108-070147/plugins/business-tools/excel-analyst-pro/skills/excel-variance-analyzer ~/.claude/skills/ Need detailed installation help? Check our platform-specific guides:
Related Agentic Skills
gemini
by SpillwaveSolutionsShell out to Gemini CLI from Claude for any task. Use this skill when you need to leverage Gemini 2.5 Pro's capabilities alongside Claude, pipe conten...
clinical-reports
by davila7"Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (...
clinical-decision-support
by davila7"Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses ...
research-grants
by davila7"Write competitive research proposals for NSF, NIH, DOE, and DARPA. Agency-specific formatting, review criteria, budget preparation, broader impacts, ...
Agentic Skill Details
- Owner
- jeremylongshore (GitHub)
- Repository
- claude-code-plugins-plus-skills
- Type
- Non-Technical
- Meta-Domain
- general
- Primary Domain
- general
- Sub-Domain
- analysis research skill
- Market Score
- 22.5
Agent Skill Grade
D
Score: 62/100
Click to see breakdown
Score Breakdown
Areas to Improve
- No trigger phrases
- References resources folder with REFERENCE.md and templates that do not exist
- 357 lines for a single skill; content could be 60% smaller without losing functionality
Recommendations
- Focus on improving Pda (currently 12/30)
- Focus on improving Writing Style (currently 5/10)
- Address 2 high-severity issues first
Graded: 1/5/2026
Developer Feedback
I took a look at your excel-variance-analyzer skill and wanted to share some thoughts.
Links:
The TL;DR
You're at 62/100 – solid D grade territory. This is based on Anthropic's agentic skill best practices.
What's strong: Ease of Use scored 19/25 – your metadata is clean, triggers are clear ("variance analysis", "budget vs actual"), and the workflow steps are well-structured.
What's holding you back: Progressive Disclosure Architecture is way too heavy at 12/30. You're burning tokens on things that should be slimmed down or moved elsewhere.
What's Working Well
- Trigger phrases are solid – You've got good coverage for discovery ("variance analysis", "budget actual comparison"). This makes the skill easy to find.
- Domain expertise shows – The skill is specific to FP&A work. You're not trying to be everything to everyone, which is smart.
- Multiple examples – You've included input/output pairs that show real variance scenarios, which helps users understand what to expect.
- Consistent terminology – "variance", "budget", "actual" used throughout without mixing terms. That consistency matters for users.
The Big One: Cut the File Down (High Priority)
Your SKILL.md is 357 lines when it should be around 120-150 lines. You're repeating similar example patterns from lines 172-295, and that's just bloat – it's making the file harder to navigate and burning tokens for readers.
What to do: Move your detailed example responses into a separate REFERENCE.md file and keep SKILL.md focused on the workflow overview, triggers, and one concise example. This alone could bump you +5 points and make the skill way more readable.
Concrete fix:
- Create
REFERENCE.mdwith your verbose examples and variance analysis best practices - Keep SKILL.md to workflow + triggers + one brief example
- Add a "See REFERENCE.md for detailed examples" note
Other Things Worth Fixing
Those referenced files don't exist (lines 337-339) – You mention
resources/REFERENCE.mdandtemplates/but they're not there. Either create them or remove the references. This is misleading and costs you credibility (+3 points if fixed).Add a Table of Contents – At 357 lines, users need navigation. Add a
## Contentssection after your frontmatter with links to major sections. Small change, big usability win (+2 points).Inconsistent voice – You're mixing "Ask the user for..." with "I'll analyze your Q1 variance". Pick imperative and stick with it. Makes the skill feel more polished (+2 points).
Add workflow checklists – Your six-step process is wordy. Break out the validation and flagging rules into checkboxes so users can follow along without mental overhead (+2 points).
Quick Wins
Focus on these in order:
- Trim SKILL.md to ~130 lines, move examples to REFERENCE.md (+5 points)
- Remove or create the referenced resources so you're not making claims you can't back up (+3 points)
- Add a TOC and consistent voice (quick wins, +4 points total)
- Tighten the workflow checklists for better clarity (+2 points)
You're looking at ~14 points of improvement with focused effort – that'd put you solidly in C territory and closer to B if you nail the larger refactoring.
Checkout your skill here: SkillzWave.ai | SpillWave We have an agentic skill installer that install skills in 14+ coding agent platforms. Check out this guide on how to improve your agentic skills.
Browse Category
More general Agentic SkillsReport Security Issue
Found a security vulnerability in this agent skill?