agentleFS
Sign inStart free
kv0906kv0906/pm-kit/.claude/skills/journey/SKILL.md

journey

Skill138 starsChanged 7 months agoMITView on GitHub

Maps a user journey with steps, touchpoints, friction, evidence, and opportunities. Use for /journey, user journey maps, or visualizing an end-to-end user experience.

We split this skill into the rules it gives an agent

9 rules. 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read _core/knowledge.md and _core/judgment.md.

    line 14
  2. Distinctive:

    Use a compact table with stage, user action/goal, touchpoint, friction, evidence, and opportunity.

    line 21
  3. Distinctive:

    Do not assume the journey begins at signup or ends at purchase if the user's job extends beyond those boundaries.

    line 25
  4. Very specific:

    Add a small plain-text flow when sequence or branching is important.

    line 27
  5. Distinctive:

    Use Mermaid only when requested and Excalidraw only for an explicitly requested editable file.

    line 28
  6. Distinctive:

    Keep visual structure and table consistent.

    line 29
  7. Very specific:

    Keep proposed opportunities separate from confirmed needs.

    line 34
  8. Very specific:

    Keep output in chat unless asked to save it.

    line 36
  9. Distinctive:

    Do not create a UI prototype, roadmap, or external tickets unless requested.

    line 37

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/journey — User Journey Map

Expose where a user struggles to make progress, with sources and visible gaps.

Input and Context

/journey [project, actor, and scenario]

Read _core/knowledge.md and _core/judgment.md; use relevant research, feedback, and product context. Define one actor or segment, their job, the trigger, and the end condition. Use /discover if these are unclear. Choose current-state or proposed future-state; never present the proposed experience as an observation. Map only the stages needed for the question. Separate materially different actors or paths rather than inventing an average persona.

Build the Map

Use a compact table with stage, user action/goal, touchpoint, friction, evidence, and opportunity. Include emotions only when observed or reported; otherwise label them as inferred or unknown. Mark each unsupported step as a hypothesis. Cite source notes or research beside observed claims. Show relevant branches, abandonment, failure, recovery, and human or offline handoffs. Do not assume the journey begins at signup or ends at purchase if the user's job extends beyond those boundaries.

Add a small plain-text flow when sequence or branching is important; follow /show-me for the host's diagram format. Use Mermaid only when requested and Excalidraw only for an explicitly requested editable file. Keep visual structure and table consistent; avoid decoration that hides uncertainty.

Output and Next Step

Return the scope, map, most consequential evidenced friction, and unanswered questions. Keep proposed opportunities separate from confirmed needs. Use /prioritize only when choosing between competing interventions. Suggest the smallest research or validation step for an important gap; do not invent metrics to rank pain points. Keep output in chat unless asked to save it. For a saved map, use /doc conventions and retain evidence links. Do not create a UI prototype, roadmap, or external tickets unless requested.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free