Skip to content

Stakeholder Persona: Practitioner

Who is this for (2)
FieldValue
CategoryEXTERNAL Stakeholder
Actor Typehuman
Primary GoalGet a change from intent to a reviewed, landed result with the Spec Kitty CLI, without fighting the tool.
Persona IDaud-ext-practitioner
Created / Updated2026-11-16 / 2026-11-16
Domain / ContextSpec Kitty 4.x
Statuscanonical

Overview

  • Role Focus: Hands-on use of the CLI in their own project.
  • Primary Function: Installs Spec Kitty (uv tool install spec-kitty-cli, pipx install spec-kitty-cli or python -m pip install spec-kitty-cli), runs spec-kitty init in a repository, and drives Missions through /spec-kitty.specify, /spec-kitty.plan, /spec-kitty.tasks, implementation, review, spec-kitty accept and spec-kitty consolidate, usually with an AI coding agent doing the work.
  • Environment / Context: A developer or small-team lead working in their own repository, new to Spec Kitty or using it every day. They are not a Spec Kitty contributor and do not read its source.

Core Motivations

  • Professional Drivers: Ship the change they set out to make, with a spec and a review behind it, in less time than doing it by hand.
  • Emotional or Cognitive Drivers: Confidence that the next command is the right one and that a refusal can be recovered from.
  • Systemic Positioning: Runs the workflow; does not set governance policy (the Project Owner does) or decide adoption (the evaluators do).

Desiderata

CategoryExpectation / NeedDescription
InformationThe next step, alwaysWants to know where a Mission stands and what to run next: spec-kitty agent tasks status, spec-kitty next --agent <name> --mission <slug>.
InteractionCopy-paste commandsExpects every command on a page to run as printed on the current release, with the flags it really takes.
SupportRecovery recipesNeeds a named remedy for each refusal code a command prints, and the recovery commands (spec-kitty doctor, spec-kitty consolidate --resume / --abort, spec-kitty upgrade).
GovernanceLight, visible gatesAccepts the discovery interview and review gates when they say why they block and what answers they need.
Decision AuthorityTheir own MissionsDecides scope inside a Mission, approves or rejects work packages, and chooses when to consolidate and open a pull request.

Frustrations and Constraints

  • Pain Points: Commands or flags in the docs that the installed CLI does not have; a refusal code with no remedy; wording that mixes senses of “lane”, “merge” or “primary”; pages written for evaluators or contributors when they need a task done.
  • Trade-Off Awareness: Accepts the interview and review steps if they catch real problems early.
  • Environmental Constraints: Limited time per session, work that spans several sessions, and an agent that follows the docs literally.

Behavioral Cues

SituationTypical BehaviorInterpretation
Stable / RoutineRuns the command sequence from memory or a tutorialTrusts the workflow while it behaves as documented.
Change / UncertaintySearches the docs for the error code or command they just sawNeeds reference and how-to pages keyed to codes and commands.
Under PressureReaches for --force or hand edits of .kittify/ filesNeeds the safe recovery path to be easier to find than the shortcut.

Collaboration Preferences

  • Decision Style: Pragmatic; picks the path that gets the Mission moving again.
  • Communication Style: Short steps, exact commands, expected output.
  • Feedback Expectations: Errors that name the cause and the next command to run.

Design Impact

  • Affected By: Tutorials, task how-tos, CLI reference pages, refusal messages and the commands agents print.
  • Needs From Design: A first Mission that works end to end on the current release, and a recovery path for every refusal.
  • Risk If Ignored: Abandoned Missions, hand-edited state, and loss of trust in the tool.
  • Acceptance Signal: A new user completes a first Mission from spec-kitty init to spec-kitty consolidate without asking for help.

Measures of Success

DimensionIndicatorType
PerformanceTime from installation to the first consolidated MissionQuantitative
QualityShare of documented commands that run as printed on the current releaseQuantitative
GrowthConfidence recovering from a refusal without hand-editing stateQualitative

Narrative Summary

The Practitioner installs Spec Kitty and uses it to get their own work done. They run the commands, answer the interviews, review what their agent produced and consolidate the result. They read tutorials and how-tos, not architecture pages, and they judge the docs by one test: does the command on the page work, and when it refuses, does the page say what to do next.