Agent skill

Grad Coopetition

by asgard-ai-platform in asgard-ai-platform/skills

Apply the Co-opetition Value Net framework (Brandenburger and Nalebuff, 1996) to map cooperative and competitive dynamics in business relationships.

MITAuto-check passed

Install Grad Coopetition

skills CLI
$ npx skills add asgard-ai-platform/skills --skill grad-coopetition -a claude-code

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

GitHub CLI
$ gh skill install asgard-ai-platform/skills grad-coopetition --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/asgard-ai-platform/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/grad-coopetition .claude/skills/grad-coopetition && 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
grad-coopetition
GitHub stars
242
Token cost
~1.3k tokens
SKILL.md length
503 words
Files
4 (incl. references)
Skills in repo
207
Repo updated
First seen
Licence
MIT

At a glance

Apply the Co-opetition Value Net framework (Brandenburger and Nalebuff, 1996) to map cooperative and competitive dynamics in business relationships.

  • Works in 4 steps: Map the Value Net → Assess Added Value → Apply PARTS Framework → …
  • The user needs to identify complementors
  • SKILL.md covers Overview, When to Use, Assumptions and Methodology, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Grad Coopetition is an agent skill from asgard-ai-platform/skills. Apply the Co-opetition Value Net framework (Brandenburger and Nalebuff, 1996) to map cooperative and competitive dynamics in business relationships. Use this skill when the user needs to identify complementors, analyze the PARTS framework, or design strategies that simultaneously cooperate and compete with the same players.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `examples/sample_scenario.md`, `references/coopetition-game-theory.md` and `references/parts-framework-guide.md`).

The repository describes itself as: 301 open-source coding agent skills across 22 domains — methodology, judgment & gotchas packaged as Claude Agent Skills for the Asgard AI Platform. The licence is MIT.

When your agent uses it

  • The user needs to identify complementors
  • Analyze the PARTS framework
  • Design strategies that simultaneously cooperate and compete with the same players

Example prompts

  • “/grad-coopetition”

Workflow steps

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

  1. Map the Value Net
  2. Assess Added Value
  3. Apply PARTS Framework
  4. Design Co-opetition Strategy

What it can do on your machine

Read from SKILL.md and the folder at commit 4e7f4f8. 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 (its code samples are markdown).

    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

Grad Coopetition loads about 1.3k tokens when it runs, and up to ~7.9k if it reads all its reference files. Until then it costs about 86 tokens; SKILL.md has 503 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.9k

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 asgard-ai-platform/skills at commit 4e7f4f8, republished under its MIT licence (© asgard-ai-platform). 503 words, ~1,330 tokens.

Download SKILL.mdSave it as .claude/skills/grad-coopetition/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
grad-coopetition
description
Apply the Co-opetition Value Net framework (Brandenburger and Nalebuff, 1996) to map cooperative and competitive dynamics in business relationships. Use this skill when the user needs to identify complementors, analyze the PARTS framework, or design strategies that simultaneously cooperate and compete with the same players.
metadata.category
WP-24 創新與國際化
metadata.tags
coopetition, value-net, brandenburger-nalebuff, PARTS-framework, complementors, game-theory-strategy

Co-opetition: The Value Net (Brandenburger & Nalebuff, 1996)

Overview

Co-opetition recognizes that business relationships are never purely competitive or purely cooperative. The Value Net model extends Porter's focus on rivalry by adding complementors — players whose products increase the value of yours. The PARTS framework (Players, Added value, Rules, Tactics, Scope) provides a structured approach to changing the game rather than just playing it.

When to Use

Trigger conditions:

  • User is analyzing a relationship that is simultaneously cooperative and competitive
  • User asks about strategic alliances with competitors
  • User needs to identify complementors or map all players in a value network
  • User mentions "frenemy", "coopetition", "complementors", or "value net"

When NOT to use:

  • For pure competitive analysis -> use Porter's Five Forces
  • For internal organizational balance -> use grad-ambidexterity
  • For international market entry mode -> use grad-oli

Assumptions

IRON LAW: Every Business Relationship Contains BOTH Cooperative
          and Competitive Elements

There is NO purely competitive or purely cooperative relationship.
A supplier cooperates (provides inputs) AND competes (captures margin).
A competitor competes (takes share) AND cooperates (grows the category).

Any analysis that labels a player as ONLY competitor or ONLY partner
is incomplete. Always map BOTH dimensions.
  • Business is a game — but players can change the game, not just play it
  • Value creation is cooperative; value capture is competitive
  • The same player can be a competitor AND a complementor simultaneously

Methodology

Step 1: Map the Value Net

Place the focal firm at the center and map four player types: Customers, Suppliers, Competitors (whose products DECREASE your value), and Complementors (whose products INCREASE your value). Key insight: a player can occupy multiple roles (Samsung supplies displays to Apple AND sells competing phones).

Step 2: Assess Added Value

For each player, calculate added value:

  • Added value = Total value of the game WITH the player MINUS total value WITHOUT the player
  • A player can never capture more than their added value
  • Strategies should aim to increase YOUR added value and manage others'
Show full SKILL.md (239 more words)Show less
Step 3: Apply PARTS Framework

Systematically evaluate five levers to change the game:

LeverQuestionAction
PlayersWho is in the game? Should we add/remove players?Bring in new complementors, attract new competitors to reduce supplier power
Added valueHow can we increase our added value?Differentiate, build switching costs, create loyal customers
RulesWhat rules govern the game? Can we change them?Contracts, regulations, industry standards, MFN clauses
TacticsHow do perceptions shape the game?Signaling, commitments, transparency vs fog
ScopeWhat is the boundary of the game?Link or de-link games, expand or narrow scope
Step 4: Design Co-opetition Strategy

For each key relationship, specify:

  • Where to cooperate (value creation): joint R&D, standard setting, market expansion
  • Where to compete (value capture): pricing, customer acquisition, differentiation
  • Boundary rules: what information to share, what to protect

Output Format

markdown
# Co-opetition Analysis: {Focal Firm}

## Value Net Map
- Customers / Suppliers / Competitors / Complementors: {list each, note dual roles}

## Added Value Assessment
| Player | Added Value | Leverage |
|--------|-------------|----------|
| {Focal firm} | {assessment} | {high/medium/low} |

## PARTS Analysis
| Lever | Current State | Recommended Change |
|-------|---------------|-------------------|
| Players / Added value / Rules / Tactics / Scope | {current} | {action} |

## Co-opetition Strategy
- Cooperate on: {activities} | Compete on: {activities} | Boundary rules: {policy}

Gotchas

  • Complementor identification is the hardest part: Force yourself to ask: "Whose product makes mine more valuable?" The biggest insights hide here.
  • Dual roles create tension: When a partner is also a competitor, define explicit information boundaries.
  • Added value is dynamic: Every major move changes everyone's added value. Reassess after launches or market entries.
  • Cooperation without boundaries leads to knowledge leakage: Alliances need explicit IP firewalls.
  • PARTS is about changing the game: If your analysis only describes the current game, you missed the point.

References

  • For game theory foundations of co-opetition, see references/coopetition-game-theory.md
  • For PARTS framework detailed application guide, see references/parts-framework-guide.md

© asgard-ai-platform, MIT. 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 (references) in grad-coopetition of asgard-ai-platform/skills.

  • SKILL.md
  • examples/sample_scenario.md
  • references/coopetition-game-theory.md
  • references/parts-framework-guide.md

Open the folder on GitHubat commit 4e7f4f8

Compare with similar skills

Grad Coopetition 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.

Grad Coopetition compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Grad Coopetition this skillasgard-ai-platform/skills242—~1.3kAutomated safety check: PassMIT
Graham Net Netquestflowai/investorskills1.9k—~478Automated safety check: PassMIT
Value Propositionphuryn/pm-skills27k—~1.5kAutomated safety check: PassMIT
Value Prop Statementsphuryn/pm-skills27k—~758Automated safety check: PassMIT
Nano Nets AutomationComposioHQ/awesome-claude-skills77k3 repos~738Automated safety check: PassNone
Aria Valid Attr Valuethedaviddias/Front-End-Checklist74k—~456Automated safety check: PassMIT

Similar skills

  • Graham Net Net

    questflowai/investorskills

    A skill your agent uses when evaluating Benjamin Graham-style deep value: net-nets, working capital bargains, margin of safety, statistical cheapness, and balance-sheet protection.

    1.9k GitHub stars~478 tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • Value Proposition

    phuryn/pm-skills

    Design a detailed value proposition using a 6-part JTBD template — Who, Why, What before, How, What after, Alternatives.

    27k GitHub stars~1.5k tokensUpdated yesterday
    Marketing & SEOAuto-check passed
  • Value Prop Statements

    phuryn/pm-skills

    Generate value proposition statements for marketing, sales, and onboarding from existing value propositions.

    27k GitHub stars~758 tokensUpdated yesterday
    Marketing & SEOAuto-check passed
  • Nano Nets Automation

    ComposioHQ/awesome-claude-skills

    Automate Nano Nets tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.

    77k GitHub starsUsed in 3 repos~738 tokens
    Productivity & AutomationAuto-check passed
  • Aria Valid Attr Value

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Use valid values for ARIA attributes.

    74k GitHub stars~456 tokensUpdated 5 days ago
    Frontend & DesignAuto-check passed
  • Official

    Refreshes stored golden values from a GitHub Actions run, reports signed percentage changes per model, and writes a summary ready for a pull request description.

    18k GitHub stars~2.8k tokensUpdated today
    Testing & QAAuto-check passed

More from asgard-ai-platform/skills

All 207 skills in this repo
  • Algo Ecom Bm25

    asgard-ai-platform/skills

    Implement BM25 ranking function for e-commerce product search relevance scoring.

    242 GitHub stars~1.4k tokensUpdated 4 mo ago
    Auto-check passed
  • Algo Mfg Cpk

    asgard-ai-platform/skills

    Calculate Cpk process capability index to assess whether a process meets specification requirements.

    242 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Algo Price Elasticity

    asgard-ai-platform/skills

    Calculate price elasticity of demand to quantify how price changes affect sales volume.

    242 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Algo Rank Bayesian

    asgard-ai-platform/skills

    Apply Bayesian averaging to rank items by combining observed ratings with prior expectations.

    242 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Algo Rank Elo

    asgard-ai-platform/skills

    Implement Elo rating system to rank items or players from pairwise comparison outcomes.

    242 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Algo Rank Wilson

    asgard-ai-platform/skills

    Calculate Wilson Score confidence intervals for ranking items by positive proportion with sample size correction.

    242 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed

Questions about Grad Coopetition

What does Grad Coopetition do?

Apply the Co-opetition Value Net framework (Brandenburger and Nalebuff, 1996) to map cooperative and competitive dynamics in business relationships. Grad Coopetition is an agent skill from asgard-ai-platform/skills. Apply the Co-opetition Value Net framework (Brandenburger and Nalebuff, 1996) to map cooperative and competitive dynamics in business relationships.

When should I use Grad Coopetition?

Grad Coopetition fits situations like: the user needs to identify complementors; analyze the PARTS framework; design strategies that simultaneously cooperate and compete with the same players.

How do I install Grad Coopetition in Claude Code?

Run `npx skills add asgard-ai-platform/skills --skill grad-coopetition -a claude-code`. Or copy the skill folder (grad-coopetition in asgard-ai-platform/skills) into .claude/skills/grad-coopetition in your project. Claude Code loads it when a task matches its description.

How do I install Grad Coopetition in Codex?

Run `npx skills add asgard-ai-platform/skills --skill grad-coopetition -a codex`. Or copy the skill folder (grad-coopetition in asgard-ai-platform/skills) into .agents/skills/grad-coopetition in your project. Codex loads it when a task matches its description.

Can I use Grad Coopetition 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 asgard-ai-platform/skills --skill grad-coopetition -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/grad-coopetition, .gemini/skills/grad-coopetition, .github/skills/grad-coopetition and .opencode/skills/grad-coopetition in your project.

What does Grad Coopetition need to run?

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

Does Grad Coopetition 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 Grad Coopetition 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 Grad Coopetition use?

Grad Coopetition is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Grad Coopetition use?

About 1.3k tokens (SKILL.md is roughly 5.3k 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 6.6k tokens, read only when the agent opens those files.

What are the alternatives to Grad Coopetition?

Skills that share tags, products or a category with Grad Coopetition: Graham Net Net (questflowai/investorskills, 1.9k stars), Value Proposition (phuryn/pm-skills, 27k stars), Value Prop Statements (phuryn/pm-skills, 27k stars) and Nano Nets Automation (ComposioHQ/awesome-claude-skills, 77k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Grad Coopetition?

asgard-ai-platform (a GitHub organization) maintains it in asgard-ai-platform/skills, which has 242 GitHub stars. The repository holds 207 skills in this directory. The repository was last updated on June 6, 2026.

Source: asgard-ai-platform/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.