Agent skill

Product Methodology

by magnus919 in magnus919/hermes-profiles

Product management frameworks embedded in references/: RICE, MoSCoW, Opportunity Solution Trees, customer interviews, spec template, stakeholder communication, decision log.

MITAuto-check passedProduct & Project Management

Install Product Methodology

skills CLI

$ npx skills add magnus919/hermes-profiles --skill product-methodology -a claude-code

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

GitHub CLI

$ gh skill install magnus919/hermes-profiles product-methodology --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/magnus919/hermes-profiles.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/product-methodology .claude/skills/product-methodology && 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/

Paste into Claude Code

Install the "product-methodology" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/product-methodology into .claude/skills/product-methodology/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-methodology", 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

$skill-installer install https://github.com/magnus919/hermes-profiles/tree/main/skills/product-methodology

Type 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.

skills CLI

$ npx skills add magnus919/hermes-profiles --skill product-methodology -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install magnus919/hermes-profiles product-methodology --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/magnus919/hermes-profiles.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/product-methodology .agents/skills/product-methodology && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "product-methodology" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/product-methodology into .agents/skills/product-methodology/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-methodology", 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.

skills CLI

$ npx skills add magnus919/hermes-profiles --skill product-methodology -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install magnus919/hermes-profiles product-methodology --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/magnus919/hermes-profiles.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/product-methodology .cursor/skills/product-methodology && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "product-methodology" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/product-methodology into .cursor/skills/product-methodology/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-methodology", 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

$ gemini skills install https://github.com/magnus919/hermes-profiles.git --path skills/product-methodology

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add magnus919/hermes-profiles --skill product-methodology -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install magnus919/hermes-profiles product-methodology --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/magnus919/hermes-profiles.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/product-methodology .gemini/skills/product-methodology && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "product-methodology" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/product-methodology into .gemini/skills/product-methodology/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-methodology", 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.

GitHub CLI

$ gh skill install magnus919/hermes-profiles product-methodology

Installs 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).

skills CLI

$ npx skills add magnus919/hermes-profiles --skill product-methodology -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/magnus919/hermes-profiles.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/product-methodology .github/skills/product-methodology && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "product-methodology" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/product-methodology into .github/skills/product-methodology/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-methodology", 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.

skills CLI

$ npx skills add magnus919/hermes-profiles --skill product-methodology -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install magnus919/hermes-profiles product-methodology --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/magnus919/hermes-profiles.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/product-methodology .opencode/skills/product-methodology && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "product-methodology" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/product-methodology into .opencode/skills/product-methodology/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-methodology", 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: product-methodology
GitHub stars: 289
Token cost: ~1.5k tokens
SKILL.md length: 596 words
Files: 9 (incl. references)
Skills in repo: 31
Repo updated: Jun 27, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Product management frameworks embedded in references/: RICE, MoSCoW, Opportunity Solution Trees, customer interviews, spec template, stakeholder communication, decision log.

Works in 6 steps: Scaffold → Build L3 Dossiers → Build L2 Analysis Files → …
Tasks that involve User research
SKILL.md covers Canonical Output, Production Flow, References and Loading
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Product Methodology is an agent skill from magnus919/hermes-profiles. Product management frameworks embedded in references/: RICE, MoSCoW, Opportunity Solution Trees, customer interviews, spec template, stakeholder communication, decision log. All output is organized as an artifact pyramid with full SOURCES navigation at every layer.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including reference files (for example `references/artifact-pyramid-mapping.md`, `references/customer-interview-guide.md` and `references/decision-log.md`).

It sits in Product & Project Management, covering User research, Architecture decision records and Internal communications. The repository describes itself as: Curated Hermes Agent profiles for specialist swarms — opinionated, Hermes-optimized, artifact-pyramid native. The licence is MIT.

When your agent uses it

Tasks that involve User research
Tasks that involve Architecture decision records
Tasks that involve Internal communications

Example prompts

“/product-methodology”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

Scaffold
Build L3 Dossiers
Build L2 Analysis Files
Build L1 Summary
Quality Gate Audit
Respond

What it can do on your machine

Read from SKILL.md and the folder at commit 867a555. 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

Product Methodology loads about 1.5k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 71 tokens; SKILL.md has 596 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~71
When it runs · the whole SKILL.md, loaded when a task matches: ~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~11k

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 magnus919/hermes-profiles at commit 867a555, republished under its MIT licence (© magnus919). 596 words, ~1,453 tokens.

Download SKILL.mdSave it as .claude/skills/product-methodology/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.

name: product-methodology
description: Product management frameworks embedded in references/: RICE, MoSCoW, Opportunity Solution Trees, customer interviews, spec template, stakeholder communication, decision log. All output is organized as an artifact pyramid with full SOURCES navigation at every layer.
version: 1.1.0
author: Hermes Agent community
license: MIT

Product Management Methodology

Canonical Output

The canonical proof of work for every engagement is an artifact pyramid — a three-layer progressively-disclosable structure at an absolute filesystem path. Every methodology and framework in this skill feeds into one of the three layers.

Respond to any caller with the absolute path to 00-index.md at the pyramid root. Not a summary. Not a handoff paragraph. A path.

The layer mapping is at references/artifact-pyramid-mapping.md.

Production Flow

Build the pyramid in this order. Each phase gates the next.

Phase 1: Scaffold

mkdir -p <pyramid-root>/{01-summary,02-analysis,03-dossiers}

Copy assets/pyramid-template.md to <pyramid-root>/00-index.md and fill in the overview.

Phase 2: Build L3 Dossiers

For each source (interview, competitive analysis, market data):

Create a flat file directly in 03-dossiers/ — no subdirectories, no README files acting as folder indexes. A dossier is a single markdown file. If a topic has multiple sources, create multiple flat files (e.g., customer-interviews.md, competitive-analysis.md).

Include source attribution metadata at the top:

**Source:** URL or transcript identifier
**Captured:** YYYY-MM-DD
**Author:** Person or organization
**Title:** Original document title

Extract faithfully — no cherry-picking. Include counter-evidence.
Add a NOTES section with any methodology context (how the data was collected, processed, etc.)

Gate C check: Every dossier has source metadata. Extracts are faithful. Methodology is documented.

Phase 3: Build L2 Analysis Files

From dossiers, compose one file per analysis dimension (problem, stories, scope, risk, etc.):

Each file is self-contained — makes sense read alone
Each file has a clear thesis, evidence, and conclusion

Each file ends with a SOURCES section:

SOURCES (LAYER 3 NAVIGATION)
../03-dossiers/customer-interviews/transcript-001.md
 -> Primary user pain evidence supporting Section 2

../03-dossiers/competitive-analysis/feature-matrix.md
 -> Competitor feature comparison referenced in Scope section

Every file gets a SOURCES section. No exceptions. Even if the only L3 source is a stub ("Interviews pending — placeholder"), link to it. An orphaned file with no L3 traceability will be rejected at the gate.

Gate B check: Every claim traces to L3. Conflict transparency. Narrative structure. Interpretive value.

Phase 4: Build L1 Summary

From analysis files, compose the single L1 summary:

Restate the research question / mission brief
3-5 key findings
Implications for the audience

End with a SOURCES section linking to every L2 analysis file:

SOURCES (LAYER 2 NAVIGATION)
../02-analysis/01-problem-statement.md
 -> User pain this feature solves

../02-analysis/02-user-stories.md
 -> Canonical set of user needs

Gate A check: Every claim links to L2. Self-contained. Implications stated. No orphan claims.

Show full SKILL.md (256 more words)Show less

Phase 5: Quality Gate Audit

Run this checklist before responding:

00-index.md exists with navigation table
01-summary/index.md has SOURCES linking to all L2 files
Every L2 file has SOURCES linking to L3 — no orphaned analysis files
Every L3 dossier has source attribution metadata
L3 dossiers are flat files in 03-dossiers/ — no subdirectories, no README placeholders
All SOURCES paths resolve correctly (relative from file location)
Each layer is independently consumable (a reader stops at any layer and has what they need)

Phase 6: Respond

Respond with ONLY the absolute path to 00-index.md. Example:

/tmp/pm-test-pyramid/00-index.md

No summary text, no analysis recap, no conversation. The caller reads the pyramid.

References

Reference	Load when	File
Artifact Pyramid mapping	You need to map a specific methodology or artifact to its pyramid layer	`references/artifact-pyramid-mapping.md`
RICE scoring	You need to compare unrelated feature proposals by Reach × Impact × Confidence / Effort	`references/rice-framework.md`
MoSCoW	Scope is tight for a time-boxed release and you need crisp boundaries	`references/moscow-prioritization.md`
Opportunity Solution Trees	The problem space is messy and you need to connect customer needs to build decisions without jumping to solutions	`references/opportunity-solution-trees.md`
Customer interview guide	You're planning discovery interviews — how to structure them, what to ask, what to avoid	`references/customer-interview-guide.md`
Spec template	You need a requirements document that engineers, designers, and stakeholders can all work from	`references/spec-template.md`
Stakeholder communication	You're preparing a message for execs, engineers, designers, or customers — each has a different format	`references/stakeholder-communication.md`
Decision log	You've made a decision with tradeoffs that will be questioned later — log the context and expected outcome	`references/decision-log.md`

Loading

Load a reference with:

skill_view(name="product-methodology", file_path="references/rice-framework.md")

Files

SKILL.md and 8 other files (references) in skills/product-methodology of magnus919/hermes-profiles.

SKILL.md
references/artifact-pyramid-mapping.md
references/customer-interview-guide.md
references/decision-log.md
references/moscow-prioritization.md
references/opportunity-solution-trees.md
references/rice-framework.md
references/spec-template.md
references/stakeholder-communication.md

Open the folder on GitHubat commit 867a555

Compare with similar skills

Product Methodology 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 Methodology compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Product Methodology this skillmagnus919/hermes-profiles	289	—	~1.5k	Automated safety check: Pass	MIT	3 mo ago
Product Manager Toolkitdavila7/claude-code-templates	33k	7 repos	~2.2k	Automated safety check: Pass	MIT	today
Opportunity Solution Treeavelikiy/great_cto	103	—	~1.8k	Automated safety check: Pass	MIT	yesterday
Product Manager Toolkitmajiayu000/spellbook	287	—	~2.2k	Automated safety check: Pass	MIT	3 days ago
Product Discoverymajiayu000/spellbook	287	—	~3.3k	Automated safety check: Pass	MIT	3 days ago
Product Manager Toolkitborghei/Claude-Skills	891	—	~5.8k	Automated safety check: Pass	MIT	4 days ago

Similar skills

Product Manager Toolkit
davila7/claude-code-templates
Scores feature requests with RICE, mines customer interview transcripts for pain points, and offers PRD templates, with two Python scripts behind it.
33k GitHub starsUsed in 7 repos~2.2k tokens
Product & Project ManagementAuto-check passed
Opportunity Solution Tree
avelikiy/great_cto
Builds an Opportunity Solution Tree that links one measurable outcome to customer opportunities, candidate solutions and experiments.
103 GitHub stars~1.8k tokensUpdated yesterday
Product & Project ManagementAuto-check passed
Product Manager Toolkit
majiayu000/spellbook
Product management helpers: a RICE scoring script, an interview transcript analyzer and PRD templates for prioritizing features, synthesizing research and writing requirements.
287 GitHub stars~2.2k tokensUpdated 3 days ago
Product & Project ManagementAuto-check passed
Product Discovery
majiayu000/spellbook
Product discovery and market research expert. An agent skill from majiayu000/spellbook.
287 GitHub stars~3.3k tokensUpdated 3 days ago
Product & Project ManagementAuto-check passed
Product Manager Toolkit
borghei/Claude-Skills
Product manager toolkit covering RICE prioritization, customer interview analysis, PRDs, and discovery frameworks.
891 GitHub stars~5.8k tokensUpdated 4 days ago
Product & Project ManagementAuto-check passed
Product Frameworks
yonatangross/orchestkit
Product management frameworks for business cases, market analysis, strategy, prioritization, OKRs/KPIs, personas, requirements, and user research.
292 GitHub stars~1.1k tokensUpdated yesterday
Product & Project ManagementAuto-check passed

Questions about Product Methodology

What does Product Methodology do?

Product management frameworks embedded in references/: RICE, MoSCoW, Opportunity Solution Trees, customer interviews, spec template, stakeholder communication, decision log. Product Methodology is an agent skill from magnus919/hermes-profiles. Product management frameworks embedded in references/: RICE, MoSCoW, Opportunity Solution Trees, customer interviews, spec template, stakeholder communication, decision log.

When should I use Product Methodology?

Product Methodology fits situations like: tasks that involve User research; tasks that involve Architecture decision records; tasks that involve Internal communications.

How do I install Product Methodology in Claude Code?

Run `npx skills add magnus919/hermes-profiles --skill product-methodology -a claude-code`. Or copy the skill folder (skills/product-methodology in magnus919/hermes-profiles) into .claude/skills/product-methodology in your project. Claude Code loads it when a task matches its description.

How do I install Product Methodology in Codex?

Run `npx skills add magnus919/hermes-profiles --skill product-methodology -a codex`. Or copy the skill folder (skills/product-methodology in magnus919/hermes-profiles) into .agents/skills/product-methodology in your project. Codex loads it when a task matches its description.

Can I use Product Methodology 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 magnus919/hermes-profiles --skill product-methodology -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-methodology, .gemini/skills/product-methodology, .github/skills/product-methodology and .opencode/skills/product-methodology in your project.

What does Product Methodology need to run?

SKILL.md names no scripts, command-line tools or credentials: Product Methodology is instructions for the agent only.

Does Product Methodology 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 Methodology 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 Product Methodology use?

Product Methodology is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Product Methodology use?

About 1.5k tokens (SKILL.md is roughly 5.8k 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 9.9k tokens, read only when the agent opens those files.

What are the alternatives to Product Methodology?

Skills that share tags, products or a category with Product Methodology: Product Manager Toolkit (davila7/claude-code-templates, 33k stars), Opportunity Solution Tree (avelikiy/great_cto, 103 stars), Product Manager Toolkit (majiayu000/spellbook, 287 stars) and Product Discovery (majiayu000/spellbook, 287 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Product Methodology?

magnus919 (a GitHub user) maintains it in magnus919/hermes-profiles, which has 289 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on June 27, 2026.

Source: magnus919/hermes-profiles on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Product Methodology

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Product Management Methodology

Canonical Output

Production Flow

Phase 1: Scaffold

Phase 2: Build L3 Dossiers

Phase 3: Build L2 Analysis Files

Phase 4: Build L1 Summary

Phase 5: Quality Gate Audit

Phase 6: Respond

References

Loading

Files

Compare with similar skills

Similar skills

More from magnus919/hermes-profiles

Related

Questions about Product Methodology