From agent-flywheel
One-sentence summary of what this skill does. Start with a verb, keep it specific enough that Claude can decide when to invoke it.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-flywheel:_templateThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
<!--
<One-paragraph framing of what this skill does and why. Reference $ARGUMENTS
if the skill accepts them.>
<Instructions. Cite the exact tool names: Bash, Read, Edit, AskUserQuestion,
and any MCP tool as tool_name (e.g. flywheel_doctor).>
<Instructions.>
<Instructions. If the skill terminates with a user decision, use
AskUserQuestion — never free-text prompts. See UNIVERSAL RULE 1 in
skills/start/SKILL.md.>
If your skill calls flywheel_* MCP tools, route on
result.structuredContent?.data?.error?.code rather than parsing
error.message. Surface error.hint inline — it is the user's next step.
Provides 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.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub burningportra/agent-flywheel-plugin --plugin agent-flywheel