New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Product Multi Role Analysis

by digoal in digoal/blog

Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles…

GPL-2.0Auto-check passedDevelopment

Install Product Multi Role Analysis

skills CLI
$ npx skills add digoal/blog --skill product-multi-role-analysis -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install digoal/blog product-multi-role-analysis --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/product-multi-role-analysis .claude/skills/product-multi-role-analysis && rm -rf skills-src

Use ~/.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/

Facts

Skill name
product-multi-role-analysis
GitHub stars
8.6k
Token cost
~1.8k tokens
SKILL.md length
840 words
Files
4 (incl. scripts, references)
Skills in repo
98
Repo updated
First seen
Licence
GPL-2.0

At a glance

Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles…

  • Works in 9 steps: Confirm the product, inputs, intended… → Create a run folder under the current… → Run scripts/create_analysis_workspace.py… → …
  • The user asks for product analysis
  • SKILL.md covers Overview, Workflow, Workspace Script and Evidence Rules, plus 5 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Product Multi Role Analysis is an agent skill from digoal/blog. Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles (user, investor, product manager, market operator, brand operator, competitor, partner), then synthesize a sourced illustrated Markdown report. Use when the user asks for product analysis, product teardown, multi-role evaluation, investment/product/marketing/brand/competitive/partnership perspectives, or a report with…

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/role-checklist.md` and `scripts/create_analysis_workspace.py`).

It sits in Development, covering Landing pages and Changelog and release notes. The repository describes itself as: AI,Opensource,Database,Business,Finance,Minds. git clone --depth 1 https://github.com/digoal/blog. The licence is GPL-2.0.

When your agent uses it

  • The user asks for product analysis
  • Product teardown
  • Multi-role evaluation
  • Investment/product/marketing/brand/competitive/partnership perspectives

Example prompts

  • “/product-multi-role-analysis”

Requirements

  • Python 3

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. Confirm the product, inputs, intended audience, and output language from the user request. If unspecified, write Chinese Markdown for…
  2. Create a run folder under the current project, preferably markdown/product-analysis/-/.
  3. Run scripts/create_analysis_workspace.py to create subfolders and role templates.
  4. Collect evidence from provided docs or links first. Browse current public sources when claims, pricing, market data, leadership, users…
  5. Save normalized source notes to sources/source-notes.md, including URL/file, access date, publisher, key facts, and reliability notes.
  6. Complete the seven role files in roles/ before writing the synthesis
  7. Create visual assets. If using SVG, save each SVG as a separate .svg file under assets/ and reference it from Markdown; do not inline SVG…
  8. Write the final integrated report as final-report.md.
  9. Verify that every strong conclusion is supported by at least one cited source or is clearly labeled as inference.

What it can do on your machine

Read from SKILL.md and the folder at commit ad6fcb7. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    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

Product Multi Role Analysis loads about 1.8k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 153 tokens; SKILL.md has 840 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~153
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.3k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from digoal/blog at commit ad6fcb7, republished under its GPL-2.0 licence (© digoal). 840 words, ~1,803 tokens.

Download SKILL.mdSave it as .claude/skills/product-multi-role-analysis/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
product-multi-role-analysis
description
Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles (user, investor, product manager, market operator, brand operator, competitor, partner), then synthesize a sourced illustrated Markdown report. Use when the user asks for product analysis, product teardown, multi-role evaluation, investment/product/marketing/brand/competitive/partnership perspectives, or a report with assumptions, boundaries, verification signals, and scenario updates.

Product Multi-Role Analysis

Overview

Create a source-backed product analysis from user-provided documents, files, or links. Produce seven role-specific intermediate Markdown files, then integrate them into one clear final report with diagrams and explicit assumptions.

Workflow

  1. Confirm the product, inputs, intended audience, and output language from the user request. If unspecified, write Chinese Markdown for non-expert readers.
  2. Create a run folder under the current project, preferably markdown/product-analysis/<product-slug>-<YYYYMMDD>/.
  3. Run scripts/create_analysis_workspace.py to create subfolders and role templates.
  4. Collect evidence from provided docs or links first. Browse current public sources when claims, pricing, market data, leadership, users, regulations, or competitors may have changed.
  5. Save normalized source notes to sources/source-notes.md, including URL/file, access date, publisher, key facts, and reliability notes.
  6. Complete the seven role files in roles/ before writing the synthesis:
    • 01-user.md
    • 02-investor.md
    • 03-product-manager.md
    • 04-market-operator.md
    • 05-brand-operator.md
    • 06-competitor.md
    • 07-partner.md
  7. Create visual assets. If using SVG, save each SVG as a separate .svg file under assets/ and reference it from Markdown; do not inline SVG in the Markdown.
  8. Write the final integrated report as final-report.md.
  9. Verify that every strong conclusion is supported by at least one cited source or is clearly labeled as inference.

Workspace Script

Use the helper script to avoid missing required files:

bash
python3 /path/to/product-multi-role-analysis/scripts/create_analysis_workspace.py "Product Name" --base markdown/product-analysis

The script prints the created run directory. It creates roles/, sources/, and assets/ plus templates for all required role analyses.

Evidence Rules

  • Prefer primary sources: official docs, pricing pages, changelogs, product pages, filings, investor presentations, app store listings, repository docs, customer case studies, and official blogs.
  • Use reputable secondary sources for market size, adoption, benchmarks, historical cases, regulatory context, and competitor comparison.
  • Include dates for time-sensitive facts such as pricing, user counts, funding, market share, product availability, and regulations.
  • Distinguish facts, source-backed interpretation, and your own inference.
  • Do not use unsourced numbers in conclusions. If a useful number cannot be verified, state that it is unverified and avoid making it load-bearing.

Seven Role Analyses

For each role file, answer the common questions and then the role-specific questions.

Common questions:

  • What does this product do, for whom, and in what use scenario?
  • What is the strongest evidence for real demand or real usage?
  • What is the main value exchange: what users/customers give up and what they get?
  • What are the product's constraints, risks, switching costs, and failure modes?
  • Which conclusions are facts, and which are inferences?

Role-specific focus:

  • User: jobs-to-be-done, pain severity, activation path, learning cost, retention triggers, trust blockers, willingness to pay, substitutes.
  • Investor: market size, growth drivers, monetization quality, unit economics signals, defensibility, regulatory risk, capital intensity, exit paths.
  • Product manager: positioning, target segment, core workflow, feature gaps, roadmap options, success metrics, onboarding, pricing-product fit.
  • Market operator: acquisition channels, funnel, content themes, conversion hooks, community/referral loops, channel risks, low-cost growth experiments.
  • Brand operator: category narrative, brand promise, proof points, tone, trust assets, perception risks, memorable assets, differentiation language.
  • Competitor: where this product is vulnerable, how incumbents or substitutes can respond, moat gaps, wedge attack, pricing attack, bundling attack.
  • Partner: integration value, channel fit, co-selling logic, ecosystem incentives, partner risks, API/data/process requirements, partnership priority.
Show full SKILL.md (329 more words)Show less

Final Report Structure

Use this structure unless the user asks for a different format:

  1. Title and one-sentence conclusion.
  2. Executive summary: 3 to 5 bullets with clear judgment.
  3. Product explanation for beginners: what it is, who uses it, why it matters.
  4. Evidence base: source map and credibility notes.
  5. Seven-role synthesis: compare where the roles agree and disagree.
  6. Product mechanics: user workflow, value chain, business model, growth loop, competitive map.
  7. Clear conclusion: opportunity level, biggest risk, most important next action.
  8. Boundaries and assumptions: where the conclusion applies, where it does not.
  9. Prove/disprove plan: observable signals that would validate or falsify each assumption.
  10. Scenario updates: how the conclusion changes if each key assumption changes.
  11. Appendix: role-file links, source list, and asset list.

Visual Requirements

Include at least two visuals when evidence allows:

  • A value-chain or product workflow diagram.
  • A role-consensus table, competitive map, growth loop, or assumptions-testing matrix.

Use Mermaid for flowcharts and matrices when it is sufficient. Use ASCII tables for compact comparison. Use SVG only when a custom visual materially improves clarity; save SVG files under assets/ and reference them like:

markdown
![Product workflow](assets/product-workflow.svg)

Assumptions and Scenario Logic

Every final report must include a table with:

  • Key assumption.
  • Why it matters.
  • Current evidence.
  • Signals to watch.
  • What would prove it.
  • What would disprove it.
  • How the conclusion changes if false.

Keep assumptions testable. Prefer observable signals such as retention, conversion, renewal, attach rate, gross margin trend, partner adoption, integration volume, regulatory actions, developer activity, customer references, review sentiment, pricing changes, search interest, and competitor launches.

Output Quality Bar

  • Make the conclusion explicit; avoid "it depends" unless followed by exact conditions.
  • Explain causal chains in plain language so a beginner can follow them.
  • Use historical data or authoritative cases to support conclusions where possible.
  • Cite sources near the claims they support.
  • Keep intermediate role files useful on their own, not merely outlines.
  • Keep final synthesis integrated; do not paste seven role analyses back-to-back.

© digoal, GPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in skills/product-multi-role-analysis of digoal/blog.

  • SKILL.md
  • agents/openai.yaml
  • references/role-checklist.md
  • scripts/create_analysis_workspace.py

Open the folder on GitHubat commit ad6fcb7

Compare with similar skills

Product Multi Role Analysis 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.

Product Multi Role Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Product Multi Role Analysis this skilldigoal/blog8.6k—~1.8kAutomated safety check: PassGPL-2.0
Publish Releasearietan/lite-edit167—~656Automated safety check: PassMIT
ReleaseLanternOps/breeze132—~9.8kAutomated safety check: NotesAGPL-3.0
Dev Releasealecs5am/ralphy138—~757Automated safety check: PassApache-2.0
Shipluongnv89/skills131—~3.3kAutomated safety check: PassMIT
Suede Launch PackagingJasonColapietro/suede-creator-skills127—~2.4kAutomated safety check: PassMIT

Similar skills

  • Publish Release

    arietan/lite-edit

    Publish a new LiteEdit release to GitHub — commit code, bump version, write changelog, create GitHub release, and update the landing page.

    167 GitHub stars~656 tokensUpdated 5 mo ago
    DevelopmentAuto-check passed

  • Release

    LanternOps/breeze

    A skill your agent uses when cutting, shipping, or announcing a Breeze RMM release — "cut a release", "ship vX.Y.Z", "release notes for X", "what do self-hosters need to know", "draft the release…

    132 GitHub stars~9.8k tokensUpdated today
    DevelopmentAuto-check: notes

  • Dev Release

    alecs5am/ralphy

    Cut a Ralphy CLI release across GitHub Releases, Homebrew, and npm.

    138 GitHub stars~757 tokensUpdated 17 days ago
    DevelopmentAuto-check passed

  • Ship

    luongnv89/skills

    Run a release end to end, autonomous by default: version bump everywhere, changelog, docs, landing page, tag, push, GitHub release, PyPI/npm.

    131 GitHub stars~3.3k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Suede Launch Packaging

    JasonColapietro/suede-creator-skills

    Suede-owned launch packaging and install verification. An agent skill from JasonColapietro/suede-creator-skills.

    127 GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed

  • Competitive Scan Lite

    mohitagw15856/pm-claude-skills

    Run a fast, honest competitive scan — the dimension table built from public evidence (sites, docs, pricing pages, changelogs, reviews), the claims-vs-observed discipline, and the so-what synthesis…

    1.4k GitHub stars~1.4k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from digoal/blog

All 98 skills in this repo

  • Article Fact Checker

    digoal/blog

    三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…

    8.6k GitHub stars~939 tokensUpdated yesterday
    Auto-check passed

  • Find Postgres Bug

    digoal/blog

    Find latent bugs in a local PostgreSQL source tree (RELxxSTABLE branch or HEAD) the way a core hacker does: build a heavily-poisoned debug instance (cassert + cache-discard + -O0/-ggdb3 + core…

    8.6k GitHub stars~4k tokensUpdated yesterday
    Auto-check passed

  • Digoal

    digoal/blog

    Portable digital employee distilled from digoal's personal blog for PostgreSQL, PolarDB, DuckDB, AI+database, vector/RAG, database operations, source-code reading, technical content creation…

    8.6k GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed

  • Paper Interpretation

    digoal/blog

    从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读，并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…

    8.6k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

  • Blog Cover Poster

    digoal/blog

    Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.

    8.6k GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

  • Article To Podcast Script

    digoal/blog

    Convert a Markdown article into a natural first-person podcast script for 1 to 4 speakers and save it as a .txt file under the current project's markdown directory.

    8.6k GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Product Multi Role Analysis

What does Product Multi Role Analysis do?

Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles…. Product Multi Role Analysis is an agent skill from digoal/blog. Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles (user, investor, product manager, market operator, brand operator, competitor, partner), then synthesize a sourced illustrated Markdown report.

When should I use Product Multi Role Analysis?

Product Multi Role Analysis fits situations like: the user asks for product analysis; product teardown; multi-role evaluation; investment/product/marketing/brand/competitive/partnership perspectives.

How do I install Product Multi Role Analysis in Claude Code?

Run `npx skills add digoal/blog --skill product-multi-role-analysis -a claude-code`. Or copy the skill folder (skills/product-multi-role-analysis in digoal/blog) into .claude/skills/product-multi-role-analysis in your project. Claude Code loads it when a task matches its description.

How do I install Product Multi Role Analysis in Codex?

Run `npx skills add digoal/blog --skill product-multi-role-analysis -a codex`. Or copy the skill folder (skills/product-multi-role-analysis in digoal/blog) into .agents/skills/product-multi-role-analysis in your project. Codex loads it when a task matches its description.

Can I use Product Multi Role Analysis 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 digoal/blog --skill product-multi-role-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/product-multi-role-analysis, .gemini/skills/product-multi-role-analysis, .github/skills/product-multi-role-analysis and .opencode/skills/product-multi-role-analysis in your project.

What does Product Multi Role Analysis need to run?

Going by SKILL.md and its folder, Product Multi Role Analysis needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Product Multi Role Analysis 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 Product Multi Role Analysis 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Product Multi Role Analysis use?

Product Multi Role Analysis is published under the GPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Product Multi Role Analysis use?

About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 462 tokens, read only when the agent opens those files.

What are the alternatives to Product Multi Role Analysis?

Skills that share tags, products or a category with Product Multi Role Analysis: Publish Release (arietan/lite-edit, 167 stars), Release (LanternOps/breeze, 132 stars), Dev Release (alecs5am/ralphy, 138 stars) and Ship (luongnv89/skills, 131 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Product Multi Role Analysis?

digoal (a GitHub user) maintains it in digoal/blog, which has 8,588 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on October 9, 2026.

Source: digoal/blog on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.