Markitdown
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
Audit the user's REAL spreadsheet by opening it in the Cowork sandbox — not by reading a description of it.
Install Spreadsheet Audit Live
$ npx skills add mohitagw15856/pm-claude-skills --skill spreadsheet-audit-live -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mohitagw15856/pm-claude-skills spreadsheet-audit-live --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/spreadsheet-audit-live .claude/skills/spreadsheet-audit-live && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "spreadsheet-audit-live" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/spreadsheet-audit-live into .claude/skills/spreadsheet-audit-live/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spreadsheet-audit-live", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/spreadsheet-audit-liveType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mohitagw15856/pm-claude-skills --skill spreadsheet-audit-live -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mohitagw15856/pm-claude-skills spreadsheet-audit-live --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/spreadsheet-audit-live .agents/skills/spreadsheet-audit-live && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "spreadsheet-audit-live" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/spreadsheet-audit-live into .agents/skills/spreadsheet-audit-live/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spreadsheet-audit-live", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mohitagw15856/pm-claude-skills --skill spreadsheet-audit-live -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mohitagw15856/pm-claude-skills spreadsheet-audit-live --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/spreadsheet-audit-live .cursor/skills/spreadsheet-audit-live && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "spreadsheet-audit-live" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/spreadsheet-audit-live into .cursor/skills/spreadsheet-audit-live/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spreadsheet-audit-live", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mohitagw15856/pm-claude-skills.git --path skills/spreadsheet-audit-live--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mohitagw15856/pm-claude-skills --skill spreadsheet-audit-live -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mohitagw15856/pm-claude-skills spreadsheet-audit-live --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/spreadsheet-audit-live .gemini/skills/spreadsheet-audit-live && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "spreadsheet-audit-live" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/spreadsheet-audit-live into .gemini/skills/spreadsheet-audit-live/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spreadsheet-audit-live", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mohitagw15856/pm-claude-skills spreadsheet-audit-liveInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mohitagw15856/pm-claude-skills --skill spreadsheet-audit-live -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/spreadsheet-audit-live .github/skills/spreadsheet-audit-live && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "spreadsheet-audit-live" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/spreadsheet-audit-live into .github/skills/spreadsheet-audit-live/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spreadsheet-audit-live", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mohitagw15856/pm-claude-skills --skill spreadsheet-audit-live -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mohitagw15856/pm-claude-skills spreadsheet-audit-live --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/spreadsheet-audit-live .opencode/skills/spreadsheet-audit-live && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "spreadsheet-audit-live" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/spreadsheet-audit-live into .opencode/skills/spreadsheet-audit-live/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spreadsheet-audit-live", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
spreadsheet-audit-live- GitHub stars
- 1.4k
- Token cost
- ~1.2k tokens
- SKILL.md length
- 590 words
- Files
- 1
- Skills in repo
- 1,348
- Repo updated
- First seen
- Licence
- MIT
At a glance
Audit the user's REAL spreadsheet by opening it in the Cowork sandbox — not by reading a description of it.
- Works in 4 steps: Hardcode hunt first — constants typed… → Range-edge check on every aggregate —… → Unit & time-grain consistency —… → …
- Asked to check this sheet before we present it
- SKILL.md covers What This Skill Produces, Required Inputs, Framework: The Hunt Rules and Execution (Cowork), plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Spreadsheet Audit Live is an agent skill from mohitagw15856/pm-claude-skills. Audit the user's REAL spreadsheet by opening it in the Cowork sandbox — not by reading a description of it. Use when asked to check this sheet before we present it, audit the model in my Drive, why don't these numbers add up, or is this spreadsheet safe to build on. Pulls the file via the Google Drive connector (or an uploaded .xlsx), opens it programmatically in the sandbox to trace formulas, hunts hardcodes / broken ranges / unit mixes, and produces a ranked findings artifact with a verified-vs-suspect ledger…
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Documents & Office, covering Excel spreadsheets. It works with Microsoft Excel and Google Drive. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.
When your agent uses it
- Asked to check this sheet before we present it
- Audit the model in my Drive
- Why dont these numbers add up
- Is this spreadsheet safe to build on
Example prompts
- “/spreadsheet-audit-live”
Requirements
- Python 3
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Hardcode hunt first — constants typed over formulas: invisible, wrong-forever. Flag every constant where a column is otherwise formulaic.
- Range-edge check on every aggregate — SUM/AVERAGE/LOOKUP vs the data's real extent (the stops-at-row-40 error).
- Unit & time-grain consistency — monthly-vs-annual, currency, thousands-vs-units mixes at every junction (tell: a ratio ~12× or ~1000× off).
- Trace the load-bearing outputs — the 3–5 numbers the sheet exists to produce get full precedent traces.
What it can do on your machine
Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Spreadsheet Audit Live loads about 1.2k tokens when it runs. Until then it costs about 139 tokens; SKILL.md has 590 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 590 words, ~1,181 tokens.
Download SKILL.mdSave it as
.claude/skills/spreadsheet-audit-live/SKILL.md (or your agent's skills folder).- name
- spreadsheet-audit-live
- description
- Audit the user's REAL spreadsheet by opening it in the Cowork sandbox — not by reading a description of it. Use when asked to check this sheet before we present it, audit the model in my Drive, why don't these numbers add up, or is this spreadsheet safe to build on. Pulls the file via the Google Drive connector (or an uploaded .xlsx), opens it programmatically in the sandbox to trace formulas, hunts hardcodes / broken ranges / unit mixes, and produces a ranked findings artifact with a verified-vs-suspect ledger and a fix list.
Spreadsheet Audit (Live)
Spreadsheets fail silently — the SUM that stops at row 40, the hardcoded 1.1 typed over a formula, the column that's monthly in one section and annual in another. In Claude Cowork this skill opens the actual file in the sandbox and traces the real formulas, so the mistake is caught before the meeting corrects it.
What This Skill Produces
- Findings ranked by damage — each with cell location, what's wrong, and what it's currently mis-stating
- The verified/suspect ledger — which load-bearing outputs were traced clean and which remain unverified (unverified ≠ wrong; the label is the honesty)
- The fix list — ordered, with make-it-robust upgrades where they matter
- A findings artifact — the above as a shareable report, plus (on request) a corrected copy of the sheet
Required Inputs
Ask for these if not provided:
- The sheet — a Drive file/link or an uploaded
.xlsx; the audit needs the real formulas, not a screenshot - The stakes — what decision it feeds (budget approval? pricing? a board number?) — depth and ranking follow the damage potential
- Growth pattern — does data get appended? The fragility check keys on it
Framework: The Hunt Rules
- Hardcode hunt first — constants typed over formulas: invisible, wrong-forever. Flag every constant where a column is otherwise formulaic.
- Range-edge check on every aggregate — SUM/AVERAGE/LOOKUP vs the data's real extent (the stops-at-row-40 error).
- Unit & time-grain consistency — monthly-vs-annual, currency, thousands-vs-units mixes at every junction (tell: a ratio ~12× or ~1000× off).
- Trace the load-bearing outputs — the 3–5 numbers the sheet exists to produce get full precedent traces.
Execution (Cowork)
- Get the file — via the Google Drive connector, download the sheet (or take the uploaded
.xlsx). Never audit from values alone. - Open in the sandbox — use the spreadsheet tooling (the
xlsxskill / a Python pass with openpyxl) to read formulas, not just cached values. Enumerate sheets, named ranges, and the formula map. - Run the hunt rules programmatically — scan for constants-in-formula-columns, aggregate ranges shorter than the data, and cross-section grain mismatches; trace precedents for the headline outputs.
- Rank by damage — location × what-it-mis-states × the decision it feeds.
- Emit the artifact — findings + verified/suspect ledger + fix list. On request, write a corrected copy (never overwrite the original) with the fixes applied and a change log.
Guardrails: read-only on the source unless a corrected copy is explicitly requested, and then only as a new file; label unverified outputs honestly; if the connector/file is unavailable, say so — don't audit a sheet you couldn't open.
Show full SKILL.md (180 more words)Show less
Output Format
A Spreadsheet Audit artifact:
Verdict
Safe to present / Fix before presenting / Do not trust — one line why
Findings (ranked by damage)
| # | Cell/range | Class | What's wrong | Currently mis-stating |
|---|
Verified / suspect ledger
| Output | Traced | Status |
|---|
Fix list
- [fix] — [robust upgrade if relevant]
Quality Checks
- Formulas were read from the real file, not inferred from values
- Every finding names an exact cell/range
- Load-bearing outputs are each marked verified or suspect (none silently assumed)
- The original file was not modified; any corrected copy is a new file with a change log
- The verdict follows the findings, not optimism
Anti-Patterns
- Auditing the screenshot — open the actual formulas.
- Overwriting the source — corrections go to a copy.
- Claiming "looks fine" without tracing the headline numbers.
- Cosmetic tidying dressed up as an audit — protect the decision, not the formatting.
Example Trigger Phrases
- "Audit the budget model in my Drive before the board call."
- "Check this spreadsheet — why don't the totals add up?"
- "Is this sheet safe to build on? Open it and trace it."
- "Someone left me this model; hunt it for hardcodes in Cowork."
© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/spreadsheet-audit-live of mohitagw15856/pm-claude-skills.
Open the folder on GitHubat commit 1cbf1f0
Compare with similar skills
Spreadsheet Audit Live next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Spreadsheet Audit Live this skillmohitagw15856/pm-claude-skills | 1.4k | — | ~1.2k | Automated safety check: Pass | MIT | |
| MarkitdownImCa0/just-laws | 781 | 14 repos | ~3.2k | Automated safety check: Notes | MIT | |
| Data Table Managern8n-io/n8n | 207k | — | ~2.3k | Automated safety check: Pass | Custom licence | |
| Docx4jplutext/docx4j | 2.4k | — | ~2.5k | Automated safety check: Pass | None | |
| Instrument Data To Allotropeaws-samples/amazon-bedrock-agents-healthcare-lifesciences | 274 | 2 repos | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| Cyber Pptcrazyykhllc-bit/CyberPPT | 1.8k | — | ~10k | Automated safety check: Pass | MIT |
Similar skills
- Official
Data Table Manager
n8n-io/n8n
Load before calling data-tables or parse-file. An agent skill from n8n-io/n8n.
Docx4j
plutext/docx4j
A skill your agent uses when writing Java code that creates, reads or edits Word (.docx), PowerPoint (.pptx) or Excel (.xlsx) files with docx4j — including generating documents, editing existing…
- Official
Instrument Data To Allotrope
aws-samples/amazon-bedrock-agents-healthcare-lifesciences
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV.
Cyber Ppt
crazyykhllc-bit/CyberPPT
当用户需要把 DOCX、PDF、TXT、XLSX、研究报告、业务材料或原始数据转成高密度、可编辑、咨询风格 PPTX 时使用；也适用于需要 SCR 论证、视觉风格探索、详细图表和渲染质检的 PPT。
Jev SEO
AgriciDaniel/jev-seo
Full live SEO audit of any website from its homepage URL, powered by Jev (TypeSafe's System One model).
More from mohitagw15856/pm-claude-skills
All 1,348 skills in this repoCar Tco
mohitagw15856/pm-claude-skills
Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…
Cs Health Scorecard
mohitagw15856/pm-claude-skills
Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.
Exit Waterfall
mohitagw15856/pm-claude-skills
Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.
Feature Prioritisation
mohitagw15856/pm-claude-skills
Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.
Fire Number
mohitagw15856/pm-claude-skills
Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.
Freelance Rate
mohitagw15856/pm-claude-skills
Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.
Related
Works with
Categories
Questions about Spreadsheet Audit Live
What does Spreadsheet Audit Live do?
Audit the user's REAL spreadsheet by opening it in the Cowork sandbox — not by reading a description of it. Spreadsheet Audit Live is an agent skill from mohitagw15856/pm-claude-skills. Audit the user's REAL spreadsheet by opening it in the Cowork sandbox — not by reading a description of it.
When should I use Spreadsheet Audit Live?
Spreadsheet Audit Live fits situations like: asked to check this sheet before we present it; audit the model in my Drive; why dont these numbers add up; is this spreadsheet safe to build on.
How do I install Spreadsheet Audit Live in Claude Code?
Run `npx skills add mohitagw15856/pm-claude-skills --skill spreadsheet-audit-live -a claude-code`. Or copy the skill folder (skills/spreadsheet-audit-live in mohitagw15856/pm-claude-skills) into .claude/skills/spreadsheet-audit-live in your project. Claude Code loads it when a task matches its description.
How do I install Spreadsheet Audit Live in Codex?
Run `npx skills add mohitagw15856/pm-claude-skills --skill spreadsheet-audit-live -a codex`. Or copy the skill folder (skills/spreadsheet-audit-live in mohitagw15856/pm-claude-skills) into .agents/skills/spreadsheet-audit-live in your project. Codex loads it when a task matches its description.
Can I use Spreadsheet Audit Live in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill spreadsheet-audit-live -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/spreadsheet-audit-live, .gemini/skills/spreadsheet-audit-live, .github/skills/spreadsheet-audit-live and .opencode/skills/spreadsheet-audit-live in your project.
What does Spreadsheet Audit Live need to run?
SKILL.md names no scripts, command-line tools or credentials: Spreadsheet Audit Live is instructions for the agent only. Our summary lists: Python 3.
Does Spreadsheet Audit Live access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Spreadsheet Audit Live safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Spreadsheet Audit Live use?
Spreadsheet Audit Live is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Spreadsheet Audit Live use?
About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Spreadsheet Audit Live?
Skills that share tags, products or a category with Spreadsheet Audit Live: Markitdown (ImCa0/just-laws, 781 stars), Data Table Manager (n8n-io/n8n, 207k stars), Docx4j (plutext/docx4j, 2.4k stars) and Instrument Data To Allotrope (aws-samples/amazon-bedrock-agents-healthcare-lifesciences, 274 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Spreadsheet Audit Live?
mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.
Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.