Not in the top 1,000 by GitHub stars

ipavelm/ultimate-product-discovery-skill

Ultimate Claude Skill for Product Discovery. 18 tasks across 6 blocks: Market Analysis, Customers (JTBD/CJM), Strategy (Lean Canvas/OST/SWOT), Validation (rapid testing/PMF), Main Scenario, Artifacts (one-pager, financial plan, pitch deck, interview guide). 3 modes: Light / Full / Geographic Expansion. Run on latest Claude Opus.

Claude Code Finance Testing Research

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → aa26c2e0d56c

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit aa26c2e0d56ce2eb1939561345b230b86c5da7ba

Version-pinned installation · Claude Code

git clone --filter=blob:none --no-checkout https://github.com/ipavelm/ultimate-product-discovery-skill.git .hotskills/ipavelm-ultimate-product-discovery-skill && git -C .hotskills/ipavelm-ultimate-product-discovery-skill checkout --detach aa26c2e0d56ce2eb1939561345b230b86c5da7ba
# Copy each selected skill directory from .hotskills/ipavelm-ultimate-product-discovery-skill into .claude/skills/<skill-name>/

23GitHub stars

3stars in 7 days

1skill in this repository

0commits in 30 days

Heat

2.9

Star growth, last 7 daysNot available
Star growth, last 24 hoursNot available
Rank movement, last 7 daysNot available
Commits, last 30 daysNot available
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

30-day change not yet available: not enough history.

Individual skills in this repository

product-discovery /

How it works

product-discovery

When your agent uses it

Product Discovery through an 18-task methodology in 6 blocks — from market analysis to an investor-ready financial plan. Use when someone wants to run Product Discovery, validate a startup, assess a market hypothesis, prepare for an investment round, or raises an adjacent topic — idea validation, niche sizing, competitor teardown, product-market fit, pitch preparation, startup unit economics, geographic expansion into a new country, go-to-market for SEA / Asia / MENA. People rarely name PD explicitly; they say 'is there a market for this', 'assess my idea', 'I need a deck for an angel', 'we are entering Thailand/Singapore/UAE, how do we size it'. Use the skill in those cases too. Three modes: Light (~45 min, idea stage), Full (~2-3 h, MVP with customers), Geographic Expansion (~2 h, product entering a new geography). Produces 3-4 artifacts in /mnt/user-data/outputs/: one-pager.pptx, financial-plan.xlsx, presentation.pptx, optionally interview-guide.docx.

What it loads into context

Frontmatter

237 tokens

Always available to the agent

SKILL.md

11,056 tokens

When the skill is activated

Reference documents

33,763 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Where this skill lives
How the skill is organised
Critical safety rules
Scope of the skill
Modes: Light, Full, Geographic Expansion
Red flags: when to interrupt PD
Step 0: gathering the inputs
Summary format after each block
Knowledge Base and saving progress
Working with uncertainty
Tool-call budget
Finishing PD
Investment readiness tracker
Next steps after PD
Data sources
Communicating with the user

Scripts executed separately

scripts/add_competitor_comparison_slide.py
scripts/delete_light_slides.py
scripts/finalize_docx.sh
scripts/finalize_pptx.sh
scripts/init_kb.py
scripts/pd_status.py
scripts/preflight_check.sh
scripts/reorder_summary_first.py
scripts/roll_formulas.py
scripts/self_check.py

Files

.gitignoreasset274 bytes
CHANGELOG.mddoc10,394 bytes
CLAUDE.mddoc873 bytes
LICENSEasset1,064 bytes
README.mddoc8,466 bytes
SKILL.mdcore45,787 bytes
SKILL.mdcore45,787 bytes
SKILL.mdcore45,787 bytes
SKILL.mdcore45,787 bytes
SKILL.mdcore45,787 bytes
SKILL.mdcore45,787 bytes
SKILL.mdcore45,787 bytes
SKILL.mdcore45,787 bytes
SKILL.mdcore45,787 bytes
SKILL.mdcore45,787 bytes
SKILL.mdcore45,787 bytes
assets/financial-plan-template.xlsxasset289,368 bytes
assets/interview-guide-template.docxasset24,068 bytes
assets/one-pager-template.pptxasset102,130 bytes
assets/presentation-template.pptxasset91,642 bytes
evals/README.mddoc2,651 bytes
evals/results-control.jsonasset2,325 bytes
evals/results.jsonasset2,096 bytes
evals/trigger-evals.jsonasset911 bytes
references/block-1-market.mddoc9,750 bytes
references/block-2-customers.mddoc9,361 bytes
references/block-3-strategy.mddoc11,552 bytes
references/block-4-validation.mddoc6,568 bytes
references/block-5-main-scenario.mddoc1,983 bytes
references/block-6-artifacts.mddoc38,304 bytes
references/customer-development.mddoc5,493 bytes
references/examples.mddoc10,864 bytes
references/glossary.mddoc3,793 bytes
references/step-0-questions.mddoc6,563 bytes
references/strategic-pivot.mddoc7,831 bytes
scripts/add_competitor_comparison_slide.pyruns10,832 bytes
scripts/delete_light_slides.pyruns4,255 bytes
scripts/finalize_docx.shruns3,580 bytes
scripts/finalize_pptx.shruns5,874 bytes
scripts/init_kb.pyruns4,140 bytes
scripts/pd_status.pyruns9,558 bytes
scripts/preflight_check.shruns4,418 bytes
scripts/reorder_summary_first.pyruns1,910 bytes
scripts/roll_formulas.pyruns4,333 bytes
scripts/self_check.pyruns13,155 bytes
skills.sh.jsonasset484 bytes

Read SKILL.md


# Product Discovery

This skill runs a structured investigation of a startup's market hypothesis. It combines several methodologies: Jobs-to-be-Done (Ulwick/Christensen), Opportunity Solution Tree (Teresa Torres), Customer Development (Steve Blank), The Mom Test (Rob Fitzpatrick), Lean Canvas (Ash Maurya), PESTEL, SWOT and the Business Model Canvas.

The output is three artifacts, or four in Full mode, in `/mnt/user-data/outputs/`:
- `one-pager-[slug].pptx` — a short summary for a CEO or investor
- `financial-plan-[slug].xlsx` — a financial model built on the main scenario
- `presentation-[slug].pptx` — Verification-stage deck
- `interview-guide-[slug].docx` — guide for live interviews (Full mode only, from task 9)

## Where this skill lives

The instructions below refer to the skill's own files as `$SKILL_DIR/assets/...` and
`$SKILL_DIR/scripts/...`. Resolve `$SKILL_DIR` to the directory this SKILL.md sits in:

View the complete source on GitHub

Skills included

product-discovery

Repository facts

License: MIT
Created: Apr 22, 2026
Last pushed: Aug 27, 2026
Forks: 3
Open issues: 0
Project activity: Slowing

Before you install

Local scripts

Automated signals, not a guarantee

Checked Nov 5, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 10 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
4 dangerous shell commandsin 3 files: scripts/finalize_pptx.sh:67 references/block-6-artifacts.md:513 scripts/finalize_docx.sh:66
9 network referencesin 3 files: README.md:3 skills.sh.json:1 references/block-4-validation.md:70
No hidden or obfuscated text
No instruction overrides
10 executable scriptsin 10 files: scripts/add_competitor_comparison_slide.py:1 scripts/delete_light_slides.py:1 scripts/finalize_docx.sh:1 and 7 more
1 reference to secretsin 1 file: scripts/delete_light_slides.py:25
No requests to vote in Hot

Show all 24 signals by file

`README.md`

Network accessline 3

[![Version](https://img.shields.io/badge/version-4.0-blue.svg)](CHANGELOG.md)

Network accessline 4

[![License: MIT](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)

Network accessline 5

[![Made for Claude](https://img.shields.io/badge/made%20for-Claude%20Skills-D97706.svg)](https://docs.claude.com/en/docs/agents-and-tools/agent-skills)

Network accessline 6

[![Requires: Opus](https://img.shields.io/badge/requires-latest%20Claude%20Opus-black.svg)](https://www.anthropic.com/claude)

Network accessline 7

[![Methodology](https://img.shields.io/badge/methodology-JTBD%20%7C%20OST%20%7C%20Lean-purple.svg)](#methodology-foundation)

Network accessline 124

git clone https://github.com/ipavelm/ultimate-product-discovery-skill.git

`references/block-4-validation.md`

Network accessline 70

https://[landing]/?utm_source=[channel]&utm_medium=[type]&utm_campaign=smoke-test-[project]

`references/block-6-artifacts.md`

Dangerous shell operationline 513

(cd unpacked && rm -f ../out.pptx && zip -qXr ../out.pptx .)   # zip from INSIDE the dir

`scripts/add_competitor_comparison_slide.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/delete_light_slides.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 25
```
[Credential-related source omitted]
```

`scripts/finalize_docx.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```
Dangerous shell operationline 66
```
rm -rf "$TMP_DIR"
```

`scripts/finalize_pptx.sh`

Executable scriptline 1
```
#!/bin/bash
```
Dangerous shell operationline 67
```
trap 'rm -rf "$TMPDIR"' EXIT
```

Dangerous shell operationline 73

( cd "$INPUT" && rm -f "$STEP1" && zip -qXr "$STEP1" . )

`scripts/init_kb.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/pd_status.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/preflight_check.sh`

Executable scriptline 1
```
#!/bin/bash
```

`scripts/reorder_summary_first.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/roll_formulas.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/self_check.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills.sh.json`

Network accessline 1

{   "$schema": "https://skills.sh/schemas/skills.sh.schema.json",

Network accessline 2

"$schema": "https://skills.sh/schemas/skills.sh.schema.json",

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 22 facts

Network access in prose of documentationREADME.md:3Low confidence
Network access in prose of documentationREADME.md:4Low confidence
Network access in prose of documentationREADME.md:5Low confidence
Network access in prose of documentationREADME.md:6Low confidence
Network access in prose of documentationREADME.md:7Low confidence
Network access in code of documentationREADME.md:124Low confidence
Network access in code of documentationreferences/block-4-validation.md:70Low confidence
Dangerous shell operation in code of documentationreferences/block-6-artifacts.md:513Low confidence
Executable script in code of a file that runsscripts/add_competitor_comparison_slide.py:1High confidence
Executable script in code of a file that runsscripts/delete_light_slides.py:1High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/delete_light_slides.py:25Low confidence
Executable script in code of a file that runsscripts/finalize_docx.sh:1High confidence
Dangerous shell operation in code of a file that runsscripts/finalize_docx.sh:66High confidence
Executable script in code of a file that runsscripts/finalize_pptx.sh:1High confidence
Dangerous shell operation in code of a file that runsscripts/finalize_pptx.sh:67High confidence
Dangerous shell operation in code of a file that runsscripts/finalize_pptx.sh:73High confidence
Executable script in code of a file that runsscripts/init_kb.py:1High confidence
Executable script in code of a file that runsscripts/pd_status.py:1High confidence
Executable script in code of a file that runsscripts/preflight_check.sh:1High confidence
Executable script in code of a file that runsscripts/reorder_summary_first.py:1High confidence
Executable script in code of a file that runsscripts/roll_formulas.py:1High confidence
Executable script in code of a file that runsscripts/self_check.py:1High confidence

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Native	Path CLAUDE.md	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

ipavelm/ultimate-product-discovery-skill

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

product-discovery

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Before you install

README.md

references/block-4-validation.md

references/block-6-artifacts.md

scripts/add_competitor_comparison_slide.py

scripts/delete_light_slides.py

scripts/finalize_docx.sh

scripts/finalize_pptx.sh

scripts/init_kb.py

scripts/pd_status.py

scripts/preflight_check.sh

scripts/reorder_summary_first.py

scripts/roll_formulas.py

scripts/self_check.py

skills.sh.json

How the signals fit together

Works with

You might also use

Mahanaicoach/competitor-x-ray

zarazhangrui/frontend-slides

DreambigOu/ELI5

rediumvex/ai-video-generator-claude

ahmedyehya92/saas-platform-teardown-kit

googlarz/finance-assistant

`SKILL.md`

`README.md`

`references/block-4-validation.md`

`references/block-6-artifacts.md`

`scripts/add_competitor_comparison_slide.py`

`scripts/delete_light_slides.py`

`scripts/finalize_docx.sh`

`scripts/finalize_pptx.sh`

`scripts/init_kb.py`

`scripts/pd_status.py`

`scripts/preflight_check.sh`

`scripts/reorder_summary_first.py`

`scripts/roll_formulas.py`

`scripts/self_check.py`

`skills.sh.json`