Analyze

Skill Lemonaderrrrr/flow-kit/skills/analyze

Stop Claude from winging it — 7 workflow skills that route every task through two thinking modes (Philosopher = absorb / Engineer = ship). Works in Claude Code + Codex.

Install

npx -y skills add Lemonaderrrrr/flow-kit --skill analyze

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Turn data, a situation, or a set of options into a structured analysis with a confidence-rated conclusion. Default Engineer mode. Two branches — 🧮 Decision analysis (which path to choose) and 📈 Data analysis (find insight in data). Hands off to the research skill when external data is missing. Saves to outputs/analysis/. Use when the user says "analyze this", "run the numbers", "which of these should I pick", "what does this data say", or invokes the skill.

SKILL.md

2.3 KB, as published. Nobody here has run it

Analyze Workflow

Turn data / a situation / options into a structured analysis + a confidence-rated conclusion.

Start

Route-confirm (see CONVENTIONS.md): one line stating this is the analyze workflow and the suggested mode; wait for the go-ahead.
Confirm mode: default ⚙️ Engineer; the user may switch to 🧠 Philosopher.
Confirm branch: 🧮 Decision analysis or 📈 Data analysis.

🧮 Decision-analysis branch (which path / whether to do it)

Define the decision — choosing between what? Supporting what action?
Pick a framework — decision matrix / cost-benefit / weighted scoring.
List options + criteria + weights — lay out candidates and judging dimensions.
Score + run the numbers — show the work, don't hand-wave.
Conclusion + confidence + sensitivity — what to pick, how sure, what would flip it.
Capture — outputs/analysis/analysis_<english-slug>.md.

📈 Data-analysis branch (find insight in data)

Define the question — what are we answering?
Inspect the data — structure / quality / missing values.
Explore — descriptive stats / distributions / correlations.
Findings — patterns / anomalies / relationships.
Conclusion + limits — don't claim what the data doesn't support.
Capture — same location.

Wrap-up conventions

Separate fact / inference / opinion; give the conclusion a confidence level.
When external data is missing, hand off to the research skill — don't invent numbers from memory.
For any quantitative claim, show the calculation, not just the result.
Promote: if it's directional/reusable, offer to save it to long-term memory; one-off outputs stay put.
Filenames use English slugs.