Eval Suite Planner
microsoft/eval-guide
Plan standalone — populates the Eval Suite Planning & Logging Template from an Agent Vision or plain-English agent description.
Untangle the spreadsheet formula nobody dares touch — decompose the seven-function nest into named readable steps, explain what it actually does (vs.
Install Formula Detangler
$ npx skills add mohitagw15856/pm-claude-skills --skill formula-detangler -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mohitagw15856/pm-claude-skills formula-detangler --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/formula-detangler .claude/skills/formula-detangler && 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 "formula-detangler" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/formula-detangler into .claude/skills/formula-detangler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "formula-detangler", 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/formula-detanglerType 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 formula-detangler -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mohitagw15856/pm-claude-skills formula-detangler --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/formula-detangler .agents/skills/formula-detangler && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "formula-detangler" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/formula-detangler into .agents/skills/formula-detangler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "formula-detangler", 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 formula-detangler -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mohitagw15856/pm-claude-skills formula-detangler --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/formula-detangler .cursor/skills/formula-detangler && 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 "formula-detangler" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/formula-detangler into .cursor/skills/formula-detangler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "formula-detangler", 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/formula-detangler--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 formula-detangler -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mohitagw15856/pm-claude-skills formula-detangler --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/formula-detangler .gemini/skills/formula-detangler && 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 "formula-detangler" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/formula-detangler into .gemini/skills/formula-detangler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "formula-detangler", 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 formula-detanglerInstalls 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 formula-detangler -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/formula-detangler .github/skills/formula-detangler && 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 "formula-detangler" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/formula-detangler into .github/skills/formula-detangler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "formula-detangler", 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 formula-detangler -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 formula-detangler --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/formula-detangler .opencode/skills/formula-detangler && 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 "formula-detangler" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/formula-detangler into .opencode/skills/formula-detangler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "formula-detangler", 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
formula-detangler- GitHub stars
- 1.4k
- Token cost
- ~1.4k tokens
- SKILL.md length
- 652 words
- Files
- 1
- Skills in repo
- 1,348
- Repo updated
- First seen
- Licence
- MIT
At a glance
Untangle the spreadsheet formula nobody dares touch — decompose the seven-function nest into named readable steps, explain what it actually does (vs.
- Works in 5 steps: Read inside-out, name each layer:… → IFERROR is where sins hide: every… → Decompose to helper columns: each named… → …
- Asked what does this formula do
- SKILL.md covers What This Skill Produces, Required Inputs, Framework: The Detangle Rules and Output Format, plus 7 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Formula Detangler is an agent skill from mohitagw15856/pm-claude-skills. Untangle the spreadsheet formula nobody dares touch — decompose the seven-function nest into named readable steps, explain what it actually does (vs. what it's believed to do), and rebuild it maintainably with helper columns and modern functions. Use when asked what does this formula do, this IFERROR-VLOOKUP monster broke, make this formula maintainable, or nobody understands the sheet the analyst left. Produces the plain-language decode, the step decomposition into helper columns, the believed-vs-actual gaps…
Its SKILL.md is about 1.4k 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 Writing & Content, covering Plain language and style rules and Excel spreadsheets. 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 what does this formula do
- This IFERROR-VLOOKUP monster broke
- Make this formula maintainable
- Nobody understands the sheet the analyst left
Example prompts
- “/formula-detangler”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Read inside-out, name each layer: innermost function first — "MATCH finds the customer's row" → "INDEX pulls that row's price" → "IFERROR…
- IFERROR is where sins hide: every error-suppression layer gets interrogated — what error, from what cause, and is hiding it right?…
- Decompose to helper columns: each named layer becomes a column with a header saying its job (_customer_row, _tier_price…
- Rebuild with the platform's decade: IF-chains → IFS · nested VLOOKUP acrobatics → XLOOKUP/INDEX-MATCH with explicit if-not-found ·…
- Verify by parallel run: the rebuild lives beside the original across the real data; a diff column proves equivalence (or surfaces the…
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
Formula Detangler loads about 1.4k tokens when it runs. Until then it costs about 140 tokens; SKILL.md has 652 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). 652 words, ~1,364 tokens.
Download SKILL.mdSave it as
.claude/skills/formula-detangler/SKILL.md (or your agent's skills folder).- name
- formula-detangler
- description
- Untangle the spreadsheet formula nobody dares touch — decompose the seven-function nest into named readable steps, explain what it actually does (vs. what it's believed to do), and rebuild it maintainably with helper columns and modern functions. Use when asked what does this formula do, this IFERROR-VLOOKUP monster broke, make this formula maintainable, or nobody understands the sheet the analyst left. Produces the plain-language decode, the step decomposition into helper columns, the believed-vs-actual gaps, and the rebuilt version.
Formula Detangler Skill
Every long-lived sheet grows one: the 400-character nest of IFs inside IFERROR inside INDEX-MATCH that one departed analyst understood — now load-bearing, feared, and edited by no one. Detangling is decompilation: read it inside-out, name each layer's job in plain language, check the believed behavior against the actual (the gaps are where the sheet has been quietly wrong), then rebuild as steps a successor can read — helper columns with named headers beat heroic one-liners in every sheet that outlives its author.
What This Skill Produces
- The decode — the formula's actual behavior in plain language, layer by layer
- The believed-vs-actual gaps — where what it does differs from what the team thinks it does (the silent-wrong findings)
- The decomposition — the nest split into named helper-column steps, each testable alone
- The rebuild — modern equivalents (LOOKUP-family upgrades, IFS over IF-chains) where the platform allows, with the migration check
Required Inputs
Ask for these if not provided:
- The formula, verbatim — and the cells/ranges it references (the decode reads the actual text, not a description)
- The believed behavior — what the team thinks it does ("it pulls the latest price for the customer's tier") — the decode is diffed against this, and the diff is often the payoff
- The platform — Excel/Sheets and roughly the version; rebuild options (XLOOKUP, LET, IFS, dynamic arrays) depend on it
- The blast radius — what reads this cell; rebuilds get verified against current outputs before anything switches over
Framework: The Detangle Rules
- Read inside-out, name each layer: innermost function first — "MATCH finds the customer's row" → "INDEX pulls that row's price" → "IFERROR hides when the customer's missing" — each layer gets one plain sentence. The decode is these sentences in order, and writing them usually surfaces the surprise.
- IFERROR is where sins hide: every error-suppression layer gets interrogated — what error, from what cause, and is hiding it right? IFERROR-to-blank routinely masks broken lookups as legitimate empties; the decode names what's being swallowed, because that's usually the believed-vs-actual gap.
- Decompose to helper columns: each named layer becomes a column with a header saying its job (
_customer_row,_tier_price,_final_with_fallback) — individually inspectable, individually testable, and readable by the next person as documentation. Hide or group the helpers if aesthetics demand; never re-inline them to look clever. - Rebuild with the platform's decade: IF-chains → IFS · nested VLOOKUP acrobatics → XLOOKUP/INDEX-MATCH with explicit if-not-found · repeated subexpressions → LET (names inside the formula) where available. Modern functions exist precisely to make yesterday's nests unnecessary.
- Verify by parallel run: the rebuild lives beside the original across the real data; a diff column proves equivalence (or surfaces the original's bugs — findings, not failures, and they route to the believed-vs-actual report before anyone "fixes" the rebuild to match old wrongness). Only then does the switchover happen, original commented/parked per spreadsheet-audit hygiene.
Show full SKILL.md (192 more words)Show less
Output Format
Detangle: [cell/formula name]
The Decode (inside-out)
[Layer → plain sentence, in order · the one-paragraph summary of what it actually does]
Believed vs Actual
| The team thinks | It actually | Consequence |
|---|---|---|
| [Including every IFERROR's swallowed cases] |
The Decomposition
[Helper columns: name · job · formula — each testable alone]
The Rebuild + Verification
[Modern version · the parallel-run diff result · switchover only on clean diff (or documented divergence-is-the-old-bug)]
Quality Checks
- Every layer has its plain-language sentence
- Every error-suppression names what it swallows
- Helper columns carry job-stating headers
- The rebuild was parallel-run against real data before switchover
- Diffs were investigated as possible original-bugs, not auto-matched
Anti-Patterns
- Do not "fix" before decoding — editing a formula you can't narrate is surgery blindfolded
- Do not preserve heroic one-liners for pride — maintainability is the requirement; cleverness was the problem
- Do not let IFERROR survive uninterrogated — silent blanks are how sheets lie politely
- Do not match the rebuild to the original's bugs — believed-vs-actual gaps get decided, not replicated
- Do not switch over without the parallel diff — equivalence is demonstrated, never assumed
Example Trigger Phrases
- "What does this formula do?"
- "Untangle this nested IF formula."
- "Make this formula maintainable."
- "Rewrite this formula with helper columns."
© 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/formula-detangler of mohitagw15856/pm-claude-skills.
Open the folder on GitHubat commit 1cbf1f0
Compare with similar skills
Formula Detangler 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 |
|---|---|---|---|---|---|---|
| Formula Detangler this skillmohitagw15856/pm-claude-skills | 1.4k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Eval Suite Plannermicrosoft/eval-guide | 138 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Regression Modelerzebbern/claude-code-guide | 4.7k | — | ~909 | Automated safety check: Pass | MIT | |
| Announce Articleopen-cqrs/opencqrs | 118 | — | ~2.6k | Automated safety check: Notes | Apache-2.0 | |
| Data Analyticsvivy-yi/xiaohongshu-skills | 481 | — | ~1.5k | Automated safety check: Pass | None | |
| Workflow AutomatorLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.7k | Automated safety check: Pass | MIT |
Similar skills
- Official
Regression Modeler
zebbern/claude-code-guide
Run regression analysis (OLS or logistic) on uploaded CSV/Excel data, generating coefficients, R², p-values, VIF, and plain-language interpretation.
Announce Article
open-cqrs/opencqrs
Generate the release announcement package for a finished blog article — Google-Sheet row fields plus three LinkedIn-post variants — and print everything to the terminal as copy-ready templates.
Data Analytics
vivy-yi/xiaohongshu-skills
A skill your agent uses when needing to optimize Xiaohongshu content performance, understanding why posts succeed or fail, making data-driven decisions about content strategy, or tracking account…
Workflow Automator
LeoYeAI/openclaw-master-skills
Automate repeatable workflows with WhatsApp/Telegram notifications, Excel/CSV processing, browser automation, and flexible scheduling.
Readability
brycewang-stanford/Auto-Empirical-Research-Skills
Correct grammar errors, typos, and improve academic readability in LaTeX, Markdown, or plain-text manuscripts.
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
Categories
Questions about Formula Detangler
What does Formula Detangler do?
Untangle the spreadsheet formula nobody dares touch — decompose the seven-function nest into named readable steps, explain what it actually does (vs. Formula Detangler is an agent skill from mohitagw15856/pm-claude-skills. Untangle the spreadsheet formula nobody dares touch — decompose the seven-function nest into named readable steps, explain what it actually does (vs.
When should I use Formula Detangler?
Formula Detangler fits situations like: asked what does this formula do; this IFERROR-VLOOKUP monster broke; make this formula maintainable; nobody understands the sheet the analyst left.
How do I install Formula Detangler in Claude Code?
Run `npx skills add mohitagw15856/pm-claude-skills --skill formula-detangler -a claude-code`. Or copy the skill folder (skills/formula-detangler in mohitagw15856/pm-claude-skills) into .claude/skills/formula-detangler in your project. Claude Code loads it when a task matches its description.
How do I install Formula Detangler in Codex?
Run `npx skills add mohitagw15856/pm-claude-skills --skill formula-detangler -a codex`. Or copy the skill folder (skills/formula-detangler in mohitagw15856/pm-claude-skills) into .agents/skills/formula-detangler in your project. Codex loads it when a task matches its description.
Can I use Formula Detangler 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 formula-detangler -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/formula-detangler, .gemini/skills/formula-detangler, .github/skills/formula-detangler and .opencode/skills/formula-detangler in your project.
What does Formula Detangler need to run?
SKILL.md names no scripts, command-line tools or credentials: Formula Detangler is instructions for the agent only.
Does Formula Detangler 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 Formula Detangler 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 Formula Detangler use?
Formula Detangler 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 Formula Detangler use?
About 1.4k tokens (SKILL.md is roughly 5.5k 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 Formula Detangler?
Skills that share tags, products or a category with Formula Detangler: Eval Suite Planner (microsoft/eval-guide, 138 stars), Regression Modeler (zebbern/claude-code-guide, 4.7k stars), Announce Article (open-cqrs/opencqrs, 118 stars) and Data Analytics (vivy-yi/xiaohongshu-skills, 481 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Formula Detangler?
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.