Intent Modeling
Pause before executing author instructions and separate literal wording from intended outcome so the agent aligns with what the user actually needs.
Install
npx skills add https://github.com/haowjy/creative-writing-skills --skill intent-modelingWhat is this skill?
- Separates what the author said from what they meant before taking action
- Counters literal obedience when context implies a pivot (e.g., less X, more Y)
- Explicitly asks when instructions are ambiguous instead of guessing
- Treats misalignment as a pattern to fix everywhere, not a one-off correction
Adoption & trust: 1 installs on skills.sh; 241 GitHub stars; trending (+100% hot-view momentum).
Recommended Skills
Microsoft Foundrymicrosoft/azure-skills
Azure Aimicrosoft/azure-skills
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Lark Eventlarksuite/cli
Running Claude Code Via Litellm Copilotxixu-me/skills
Setup Matt Pocock Skillsmattpocock/skills
Journey fit
Primary fit
Agent-tooling is the canonical first shelf because the skill governs how the coding or writing agent interprets directives before any domain-specific work begins. It is procedural meta-behavior for agents—not a single feature ship task—so it sits with other agent discipline skills rather than launch or grow tactics.
SKILL.md
READMESKILL.md - Intent Modeling
# Intent Modeling Understand what the author means before acting on it. "Stop doing X" might mean literally stop, or it might mean less X and more Y — LLMs default to the literal reading. Read the context to tell which. When ambiguous, ask. The helpfulness instinct pulls toward what feels helpful rather than what was asked for. Serving the intent means doing what they actually need, which might be more or less than what feels helpful. Misalignments come from systematic misreadings, not one-off mistakes. When you catch one, check everywhere the same pattern might exist.