customer-journey
Map one persona's path through one JTBD — stages, what they're doing/thinking/feeling, touchpoints, pain; mark evidence vs assumption.
- License 许可
- MIT
- 最近更新
- 2026-10-29
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- customer-journey
- description
- Map one persona's path through one JTBD — stages, what they're doing/thinking/feeling, touchpoints, pain; mark evidence vs assumption.
03 SKILL.md 正文
customer-journey
One persona, one job-to-be-done, 5–7 stages. Multiple personas → multiple journeys; don't merge.
Mode: analytical — judgment inside a fixed frame. Keep the output shape; every verdict cites its evidence; unknowns are marked [TBD] or [VERIFY], never filled in.
When to use
- A team has a persona doc and wants to surface where in the user's flow they're losing.
- Funnel analytics show drop-off but the team doesn't know why.
Inputs
- The persona doc (required).
- The job-to-be-done in JTBD form ("When <situation>, I want to <motivation>, so I can <outcome>.").
- Optional: existing funnel analytics.
Procedure
- Read
Customer-journey.md. - Slug from the JTBD's outcome clause: a workflow's
${workflow.slug}wins; otherwise lowercase it, replace each run of characters outsidea-z0-9with-, trim-at the ends, and cut to ≤ 60 characters at a-. An existing file at the target path is updated in place (show the diff), never duplicated. - Draft
docs/research/journeys/<slug>.md:- JTBD — verbatim in the doc.
- Stages — 5–7. User-perspective, not product features. Trigger → Search → Evaluate → Onboard → First success → Habit → Tell others is a good default.
- Per stage — what they're doing, thinking/feeling, touchpoints, pain.
- Peak pain moments — the 1–2 highest-drop-off stages. These are the leverage points.
- Evidence vs assumption — mark every stage
✓ Evidence(quote-supported) or? Assumption(guess). - Improvements — top 3 changes sized by impact, with the metric each would move.
Quality bar
- Stages are user-perspective ("evaluating options"), not product-perspective ("uses comparison page").
- Every stage marked Evidence or Assumption. Assumption-heavy journeys are flagged for research before action.
- Peak pain moments named explicitly.
- One persona per journey. Multi-persona journeys are merged guesses.
Output
- File:
docs/research/journeys/<slug>.md. - Summary listing the 2 peak pain moments + the top improvement.
Anti-patterns to avoid
- Generic "AAARRR" funnel re-labeled as a journey. The stages must reflect this specific JTBD.
- Stages full of
? Assumptionshipped as if they were research. - "Delight" stage added as a vanity step. If there's no evidence of delight, don't add it.
- Improvements sized by "ease" or "what we can ship next sprint" instead of impact.
04 同仓库更多 Skills
runbook
Write or refresh an operational runbook for an alert/symptom; structured as TL;DR + Pre-checks + Steps + Verification + Rollback + Escalation.
rfc
Draft a lightweight design RFC to docs/rfcs/<slug>.md; Summary, Motivation, Detailed design, Drawbacks, Alternatives, Unresolved questions. A proposal to debate, not a recorded decision (adr).
editorial-pass
Review and tighten prose in a Markdown artifact for a target tone (terse, formal, friendly) without dropping information; preserve quotations and load-bearing constraints.
architecture-review-facilitation
Run an architecture review as a process — entry criteria, reviewer checklist, decision log, and follow-up actions — pairing the design artifact with a red-team pass.
architecture-doc
Write a C4-style architecture document; System Context + Containers (+ Components when interesting) with mermaid diagrams. Describes structure, not a decision (adr) or proposal (rfc).
adr
Write an Architecture Decision Record (Michael Nygard format) to docs/adrs/NNNN-<slug>.md; frontmatter validated by the ADR artifact schema. Records a made decision, not a proposal to debate (rfc).