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 acts as a guardrail for AI automation workflows, ensuring agents adhere to explicit task boundaries. It is designed for builders who need to stop agents from introducing unrequested hashes, checksums, or unnecessary hardening that leads to overengineering.
By resolving repeated verification loops and limiting speculative additions, the skill helps maintain a strict focus on the requested work without expanding the project scope beyond the user's requirements.
WHO IT'S FOR
AI agent / automation builders
preventing task-scope creep in AI coding agents
Technical leads / architects
reviewing possible overengineering in AI generated code
Technical writers / content strategists
reducing defensive disclaimers in reader-facing prose
Platform / DevEx teams
implementing guardrails for Codex and GPT workflows
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.
Its intended audience and any supporting material needed to preserve its claims.
Make sure stss is installed in your agent before trying this task.
Use the stss skill in rewrite mode on the paragraph I provide. Reduce defensive disclaimers and stacked hedging while preserving the supplied facts, attribution, uncertainty, and limitations that affect the reader's understanding or decisions. Return only the revised paragraph.
Claude
Codex
OpenCode
Hermes
Pi