From flowstate
Document a learning or insight discovered during development. Use when the user says "learned something", "TIL", "note this", "remember this for next time", or when a non-obvious discovery is made while working.
How this skill is triggered — by the user, by Claude, or both
Slash command
/flowstate:add-learninghaikuThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Document an insight, mistake, or discovery so it can be referenced in future work.
Document an insight, mistake, or discovery so it can be referenced in future work.
Learning description (optional): $ARGUMENTS
Verify .backlog/ exists. If not, tell the user to run /flowstate:setup first.
The default mode is auto-draft: write the learning directly from available context, no questions. Only fall back to interactive mode when context is genuinely insufficient.
Auto-draft mode (preferred): use it if ANY of these are true:
$ARGUMENTS is non-emptyInteractive mode: only if $ARGUMENTS is empty AND no clear insight is present in recent context.
Derive every field from $ARGUMENTS + recent conversation. Do NOT ask the user:
Skip directly to Step 3.
Ask only when context is missing:
database, testing, deployment)Check .backlog/tasks/active/:
--task TSK-XXX). Do NOT ask.--task.cat <<'BODY' | node "${CLAUDE_PLUGIN_ROOT}/dist/bin/flowstate.js" learning-create --title "{{TITLE}}" --tags "{{TAGS}}" --task {{TSK_ID}} --body -
{{LEARNING_CONTENT}}
BODY
The CLI handles ID assignment, directory creation, index update, and task linking automatically.
Omit --task if no active task is linked.
Added LRN-{{ID}}: {{TITLE}}
Tags: {{TAGS}}
Linked to: TSK-{{XXX}} (or "No active task")
Directory: .backlog/learnings/LRN-{{ID}}-{{slug}}/
Edit the file directly to refine. Add screenshots/attachments to the directory.
npx claudepluginhub jmlweb/skills-monorepo --plugin flowstateCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.