agentmods.dev

evo-xlsx-recover-data

evo-xlsx-recover-data is a skill for Claude Code, Codex from OpenLAIR/OpenSkill. It costs 53 tokens per session (824 once invoked), scanned A, original, Apache-2.0.

A tool for recovering missing values marked with “???” in a multi-sheet NASA budget Excel workbook. It uses totals, year-over-year percentages, category shares, and growth calculations across related sheets.

In plain words
What is it for?
It is for repairing the NASA budget, year-over-year changes, directorate shares, and growth-analysis sheets while applying specified rounding rules.
Why use it?
It removes the need to fill gaps manually when the missing numbers can be worked out from the workbook’s existing relationships.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 97repo +1 1mo ago A scan 53 tokens original Apache-2.0

Good fit It is for repairing the NASA budget, year-over-year changes, directorate shares, and growth-analysis sheets while applying specified rounding rules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openlair/openskill/evo-xlsx-recover-data
View source ↗ OpenLAIR/OpenSkill openlair.github.io
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add OpenLAIR/OpenSkill --skill evo-xlsx-recover-data
Clone the repo
git clone --depth 1 https://github.com/OpenLAIR/OpenSkill

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for evo-xlsx-recover-data

README.md
[![agentmods](https://agentmods.dev/badge/skills/openlair/openskill/evo-xlsx-recover-data/github.svg)](https://agentmods.dev/skills/openlair/openskill/evo-xlsx-recover-data)
Your own site
<a href="https://agentmods.dev/skills/openlair/openskill/evo-xlsx-recover-data"><img src="https://agentmods.dev/badge/skills/openlair/openskill/evo-xlsx-recover-data/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for evo-xlsx-recover-data

Your own site · 80×15
<a href="https://agentmods.dev/skills/openlair/openskill/evo-xlsx-recover-data"><img src="https://agentmods.dev/badge/skills/openlair/openskill/evo-xlsx-recover-data.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 824 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.00824
Opus 5.5 $0.00021 $0.00330
Sonnet 5.5 $0.00011 $0.00165
Haiku 4.5 $0.00005 $0.00082

Measured 1mo ago against content hash 356b4bf17870, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

evo-xlsx-recover-data scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

tasks-evolved/xlsx-recover-data/environment/skills/evo-xlsx-recover-data/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

evo-xlsx-recover-data

Purpose

Recover missing values (marked as "???") in a multi-sheet NASA budget Excel workbook. The workbook has 4 interdependent sheets:

  1. Budget by Directorate - Raw dollar values ($M) per category per year (FY2015-FY2024)
  2. YoY Changes (%) - Year-over-year percentage changes
  3. Directorate Shares (%) - Each category as % of yearly total
  4. Growth Analysis - Summary statistics (CAGR, averages, deltas) for FY2019-2024

Key Formulas

  • Row Sum: Total = sum of all category columns
  • YoY%: ((current - previous) / previous) * 100, rounded to 2dp
  • Share%: (category / total) * 100, rounded to 2dp
  • CAGR%: ((end/start)^(1/n) - 1) * 100, rounded to 2dp, n=5 for FY2019-FY2024
  • Average Budget: mean of FY2019-FY2023 (5 years), rounded to 1dp
  • 5-Year Change: FY2024 - FY2019, integer

Rounding Rules

  • Budget amounts: integer (no decimals)
  • YoY/Share/CAGR percentages: 2 decimal places
  • Average budgets: 1 decimal place
  • Dollar change/delta: integer

Sheet Layout Details

  • Budget: rows 4-13 (FY2015-2024), cols B(2)-K(11), K=Total
  • YoY: rows 4-12 (2016-2024), cols B-K. YoY row N maps to budget rows N and N+1
  • Shares: rows 4-13 (2015-2024), cols B-J (no Total column)
  • Growth: row 4=CAGR, row 5=FY2019, row 6=FY2024, row 7=Change, row 8=Avg. Cols B-J

Dependency Resolution Strategy

The recover_all() function uses iterative constraint propagation:

  1. Solve Budget sheet row sums (Total column vs category columns)
  2. Use YoY percentages to recover Budget values and vice versa
  3. Use Share percentages to recover Budget values and vice versa
  4. Cross-sheet sync: Growth Analysis ↔ Budget sheet (FY2019=row8, FY2024=row13)
  5. Compute CAGR, 5-Year Change, and Average Budget in Growth Analysis
  6. Repeat until no more progress (handles cascading dependencies)
  7. Final pass: recompute all Growth Analysis averages for consistency

Robustness Features

  • Handles merged cells safely (skips MergedCell objects)
  • Floating-point tolerance checks using math.isclose()
  • Type inference: preserves int vs float based on context
  • Multiple missing values in same row/column: only solves when exactly 1 unknown
  • Iterates up to 50 passes to handle deep dependency chains
  • Graceful handling of edge cases (division by zero, negative CAGR inputs)

Read the full file on GitHub · 65 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 65 lines · 53 tokens per session scan A 356b4bf17870

Subscribe to this mod's changes

evo-xlsx-recover-data is a skill published in the GitHub repository OpenLAIR/OpenSkill (97 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 824 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-11.

Analytics and metricsDocumentsSpreadsheetsagent-skillsai-agentsllm-agentsopen worldself-evolving-agents
Related

evo-xlsx-recover-data compared with skills from other repositories

evo-xlsx-recover-data next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
evo-xlsx-recover-dataOpenLAIR/OpenSkillSkill971mo agoApache-2.0A53Claude Code, Codex
data-formatsA-EVO-Lab/a-evolveSkill842yesterdaynoneA34Claude Code, Codex
xlsxYunjueTech/Yunjue-AgentSkill5458mo agoApache-2.0A68Claude Code, Codex
xlsxRaidriar7170/hermes-skillevalSkill291mo agoMITA96Claude Code, Codex
xlsxRaidriar7170/hermes-skillevalSkill291mo agoMITA96Claude Code, Codex
vulnerability-csv-reportingDANG-ai/SKILLERSkill82mo agononeA52Claude Code, Codex
xlsxDANG-ai/SKILLERSkill82mo agononeA96Claude Code, Codex