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 helps technical leads and architects pressure-test specifications or pull requests before they move to implementation. By comparing a proposed plan against existing documentation and source code, it identifies gaps in understanding and prevents the premature start of a build based on flawed assumptions.
It is particularly useful for refining launch packets for subagents or long-running coding tasks, ensuring that the agent has a grounded map of the territory before executing complex changes.
WHO IT'S FOR
Technical leads / architects
pressure-test hidden assumptions before merge
AI agent / automation builders
create better launch packets for subagents
Backend / infrastructure engineers
interrogate plans against unfamiliar APIs and docs
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.
Installs: User-level installation of the grill-for-unknowns skill folder · Claude Code
Before you start
Claude Code
Git
A Bash-compatible terminal
Run this complete command block in a terminal. It clones the repository into /tmp, creates the Claude Code user skills directory, and copies the grill-for-unknowns folder into it.
A complex implementation request provided as the context for “this”
Access to the relevant documentation or source code
Use grill-for-unknowns before implementing this. Inspect the relevant docs/source first, then interview me one material question at a time until we have shared understanding.