agentleFS
Pearl1531Pearl1531/Archetype-talk/.claude/skills/journey-map/SKILL.md

journey-map

Skill2 starsChanged 50 days agoMITView on GitHub

Build a journey map for a persona from her Product usage moments and linked Pains/Signals. Use when the user runs /journey-map, asks for a customer/user journey, or a designer wants pain points mapped to moments of use.

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Read the persona + her linked Signals/Evidence (+ Product Context.md for feature names the map may reference descriptively).

    line 19
  2. Very specific:

    Keep the map per-persona. A cross-persona map is really a comparison — point to /persona-talk --panel findings or build one map per persona …

    line 33

“Common” is measured: kept by at least 6 in 10 of the 10 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-map — Journey map from the graph

Generate a journey map where every pain point is a citation, not an opinion. The stages come from the persona's actual Product usage moments; the pains at each stage come from her linked Signals/Evidence — clickable back to source.

Trigger

/journey-map Personas/Emma.md
/journey-map Personas/Emma.md --scenario "commute"   ← one scenario, deeper

Workflow

  1. Read the persona + her linked Signals/Evidence (+ Product Context.md for feature names the map may reference descriptively).
  2. Derive stages from data: the "When she listens / uses" moments in Product usage (e.g. morning commute → workday background → gym) — never a generic Awareness→Retention template. If the data only supports two stages, the map has two stages.
  3. For each stage fill:
    • Doing — observed behaviour (Product usage, Signals)
    • Thinking/feeling — only from quotes and Signal observations; no invented inner monologue
    • Pain points — each one linked to its Signal/Evidence file, with its Level (analyst artefact — codes allowed) and a staleness note where the 3-month rule applies
    • Opportunities — only from existing ## Correlations → Opportunity: lines and Ideas/ files, named and linked
  4. Gaps stay visible: a stage with no researched pain gets an explicit "no data — not researched" cell, not a plausible guess. Offer to add those gaps to Research backlog.md.
  5. Output as a markdown table (default) — offer to save as Research/Journey <Persona> <YYYY-MM-DD>.md, and optionally a Mermaid journey diagram for quick pasting into docs.

Rules

  • Nothing enters the map that isn't in the graph — a journey map is a view of the data, not new synthesis. New hypotheses it provokes go to the backlog.
  • Emotions shown must trace to a quote or observation ("laughs at her own chaos" — INT-01 observer note), never inferred from stage logic ("users feel frustrated at checkout").
  • Keep the map per-persona. A cross-persona map is really a comparison — point to /persona-talk --panel findings or build one map per persona side by side.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.