Skip to content
SkillModel-led613 tokens in use

job-stories

Write job stories in the When, I want to, so I can format, each with six to eight outcome-focused acceptance criteria and a design link.

28,201 stars on the repository MIT Licensephuryn/pm-skills · pm-execution/skills/job-stories
claude plugin install pm-execution@pm-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing job-stories costs

54tokens idle
613tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure22/25
  • Examples3/15
  • Output12/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity80
  • Maintenance76
  • Community60
  • Maturity32
  • Momentum40

job-stories has an agent break a feature into backlog items that start from a user situation. Each story states the situation, the motivation and the outcome, then lists observable acceptance criteria and links to the design. It takes the product, feature, design link and context as inputs.

What You Get

  • A complete set of job stories for the feature
  • A title, a description in the When, I want to, so I can format and a design link for each story
  • Six to eight acceptance criteria per story focused on outcomes
  • An example story with its criteria to calibrate the format

Common Use Cases

  • Splitting a new feature into JTBD-style backlog items
  • Rewriting role-based user stories around situations
  • Adding acceptance criteria that test whether the outcome was achieved

What Makes It Unique

It writes from the situation and the job, with no persona or role. Acceptance criteria cover recognizing the situation, enabling the motivation, visible progress, edge cases and notifications.

Under The Hood

The skill is one SKILL.md of instructions with no bundled scripts and no commands. The agent works from the product, feature, design link and context you give it and writes the stories in the chat. It reaches no outside service.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers