identify-assumptions — Claude Code skill: what it does, how to install
identify-assumptions — a skill for Claude Code that uncovers product assumptions and scores impact against confidence. Runs before engineering experiments start or when team members debate delivery risks.
LicenseRef-MIT-Commons-Clause 102 installs ★ 1,183 updated 2026-10-23
npx skills add borghei/Claude-Skills --skill identify-assumptions -a claude-codeWhat identify-assumptions does
The system evaluates product bets by adopting adversarial angles from product managers, UI designers, and engineers. Existing products rely on Teresa Torres' four core pillars, while brand-new bets add four extra buckets: ethics, go-to-market execution, strategic alignment, and internal team capabilities.
Every surfaced premise receives an impact rank between 1 and 10 beside high, medium, or low confidence weightings. An included utility named assumption_tracker.py sorts items using the formula Risk Score = Impact x (1 - Confidence) and slots entries across four distinct action quadrants.
Running the prioritization script requires a local Python 3 environment. Execution yields exit code 1 whenever the priority quadrant holds over roughly 20% of the mapped entries.
What it helps with
- uncover hidden bets inside unverified product concepts
- clarify internal team disagreements regarding feature priorities
- calculate mathematical risk metrics combining confidence and impact
- isolate top assumptions needing immediate discovery experiments
Example prompts for the agent
- Map underlying assumptions for our checkout redesign bet
- Expose engineering and usability risks for the new mobile flow
- Score assumptions in
sample_assumptions.jsonusingassumption_tracker.py
How to install identify-assumptions
1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill identify-assumptions -a claude-code2Manually: put the files in place
~/.claude/skills/identify-assumptions/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/identify-assumptions/
1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill identify-assumptions -a codex2Manually: put the files in place
.agents/skills/identify-assumptions/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill identify-assumptions -a cursor2Manually: put the files in place
.cursor/skills/identify-assumptions/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install borghei/Claude-Skills project-management/discovery/identify-assumptions2Manually: put the files in place
.github/skills/identify-assumptions/SKILL.md1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill identify-assumptions -a gemini-cli2Platform CLI
gemini skills install https://github.com/borghei/Claude-Skills --path project-management/discovery/identify-assumptionsManually: put the files in place
.devin/skills/identify-assumptions/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill identify-assumptions -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about identify-assumptions
How to install identify-assumptions in Claude Code?
Run npx skills add borghei/Claude-Skills --skill identify-assumptions -a claude-code in your terminal.
What does identify-assumptions do?
It challenges product ideas from PM, design, and engineering angles, maps them into risk quadrants, and isolates the top 20% items for early experiment validation.
What is required to run identify-assumptions?
A working python3 environment is required to execute assumption_tracker.py against assumption JSON payloads.