From grace
Assess any code change request before implementation. Classifies scale (trivial/small/medium/large), applies a sniff test, and routes to the appropriate process depth. Use before accepting any implementation instruction.
How this skill is triggered — by the user, by Claude, or both
Slash command
/grace:change-assessmenthaikuThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill before accepting implementation work.
Use this skill before accepting implementation work.
Classify the change scale:
For small changes, apply the sniff test:
If concerns arise, surface them as an observation, not a hidden veto:
If constraints force a shortcut, apply the Ideal Solution Pattern:
Route to the appropriate next step:
trivial -> implement directlysmall -> implement after sniff testmedium + existing analysis present -> analysis-review (delta-focused review of the existing analysis)medium + no existing analysis -> business-analysis (initial analysis)large -> business-analysis to update or re-baseline the product graph, then design-reviewProduce a brief classification record containing:
npx claudepluginhub grace-method/grace-marketplace --plugin graceProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.