Stats
Actions
Tags
From The Jagoda Toolkit
Structured task handoff. Use when user wants to plan or set up a task before executing — asks 5 intake questions (mode, goal, context, format, unknown_ok) and confirms in one sentence before starting.
How this skill is triggered — by the user, by Claude, or both
Slash command
/jc:promptThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Ask questions one at a time. User answers each. Skip on "skip" or blank.
Ask questions one at a time. User answers each. Skip on "skip" or blank.
mode ∈ {research, debug, decision, planning, implement, review} — "Mode?"goal: string — "Goal?"context: string — "Context? (or skip)"format ∈ {text, json, table, steps, code, short} — "Format?"unknown_ok ∈ {yes, no} — "Can I say 'I don't know'?"After all answers, build internal seed and confirm in one sentence. Then start.
P1: ∀ field(blank): skip ∨ ask — ¬guess
P2: mode ∈ {research, review} → I1 (edits=0)
P3: unknown_ok=yes → decision ∈ {execute, unknown, insufficient_evidence, refuse}
P4: unknown_ok=no → ∀ claim: verified
P5: post_parse → confirm(1 sentence) ∧ start
npx claudepluginhub jagoda11/the-jagoda-toolkit --plugin jcProvides 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.