Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This skill provides a structured approach for corporate strategy executives managing long-horizon bets. It assists in determining market entry, evaluating build-buy-partner decisions, and framing strategic partnerships under uncertainty.
By focusing on corporate development and target screening, the skill helps clarify deal theses and valuation framing for business line allocation.
WHO IT'S FOR
Corporate strategy executives
planning multi-year portfolio choices and capital allocation
Corporate development teams
running deal thesis and acquisition diligence
Business development managers
evaluating new market entry and demand sizing
AI agent / automation builders
deploying structured organizational skills to AI agents
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Copy the technology department for ChatGPT or Codex
Installs: Complete `technology` department copied from the headcount repository. The listed skill path is a bounded mapping selected for the starter task; the department contains additional skills. · ChatGPT, Codex
Before you start
Run from: Your own project
In your own project, manually copy the technology department from the headcount repository into `.agents/skills/`. No terminal command is documented in the supplied evidence.
Copy the marketing department for ChatGPT or Codex
Installs: Complete `marketing` department copied from the headcount repository. The listed skill path is a bounded mapping selected for the starter task; the department contains additional skills. · ChatGPT, Codex
Before you start
Run from: Your own project
In your own project, manually copy the marketing department from the headcount repository into `.agents/skills/`. No terminal command is documented in the supplied evidence.
Copy the demand-generation department for ChatGPT or Codex
Installs: Complete `demand-generation` department copied from the headcount repository. The listed skill path is a bounded mapping selected for the starter task; the department contains additional skills. · ChatGPT, Codex
Before you start
Run from: Your own project
In your own project, manually copy the demand-generation department from the headcount repository into `.agents/skills/`. No terminal command is documented in the supplied evidence.
Make sure solution-exploration is installed in your agent before trying this task.
Use the solution-exploration skill to examine this proposed feature before any code is written. Clarify the desired outcome, current problem, affected users, explicit exclusions, and observable success condition. Then present three genuinely different approaches—including the smallest workable approach and one requiring no new moving parts—with costs, tradeoffs, and necessary assumptions. Recommend one approach, explain why the others lost, and identify the assumption on which the recommendation depends most heavily.
Make sure customer-research is installed in your agent before trying this task.
Use the customer-research skill to synthesize these interview notes for the stated decision. For each supported finding, report the claim, how many independent participants expressed it, one verbatim quote, and what decision would change if it is true. Clearly separate what participants said, what they did, and what you inferred. Do not treat a single interview as a general finding.
Repeating query pattern and available demand evidence
Description or sample of the dataset
Examples of how individual pages would differ
Examples of current ranking pages or their relevant strengths
Make sure programmatic-seo is installed in your agent before trying this task.
Use the programmatic-seo skill to assess whether this repeating search pattern is viable before building or publishing pages. Evaluate whether there is verified demand across many instances, sufficient quality data, genuine per-page value, and a defensible reason to outperform current results. Identify the minimum data threshold for generating a page and conclude with either a small validation step or a recommendation to create fewer, better pages.
Claude
Codex