# Craft Star

> Turn a Chronicle project experience into an evidence-backed STAR story, resume bullet, 30-second summary, and one-minute interview answer. Use when preparing behavioral or technical interview stories, explaining a project decision or failure, or converting reviewed project records into career-ready narratives.

- Skill: `r-jelly/craft-star` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add r-jelly/craft-star`
- Raw SKILL.md: https://api.skillmd.com/api/skills/r-jelly/craft-star/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: r-jelly (https://skillmd.com/u/r-jelly)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/r-jelly/craft-star

---


# Craft STAR

Build a defensible story from Chronicle records. Keep missing evidence visible
instead of filling gaps with persuasive fiction.

## Choose the Story

Resolve the project under `<vault>/chronicle/projects/<project-id>/` and read its
ledger plus relevant session records. Prefer one meaningful challenge or
decision over a summary of the whole project.

If the target competency is not specified, infer up to three viable options such
as technical depth, problem solving, failure and recovery, collaboration,
ownership, performance, or prioritization. Ask the user to choose only when the
choice materially changes the story.

## Evidence Gate

Use `reviewed` records and `[confirmed]` claims for a final story. A draft may
use `[inferred]` or `[needs-evidence]` material only when it is visibly labeled
and excluded from final resume bullets.

Before writing, verify:

- what the user personally owned;
- the situation and relevant constraint;
- the goal or responsibility;
- the concrete actions and why they were chosen;
- alternatives or trade-offs when relevant;
- the observed result and how it was measured.

Ask one high-impact question at a time when ownership, result, or rationale is
missing. Do not require answers to low-value details.

## Construct the Story

Write:

1. `Situation`: concise context, problem, scale, and constraint.
2. `Task`: the user's responsibility and success criterion.
3. `Action`: specific actions in decision order, including why, how,
   alternatives, and collaboration boundaries.
4. `Result`: observed outcome with confirmed metrics; otherwise give a
   qualitative result and a missing-evidence note.
5. `Learning`: what changed in the user's approach and what they would do next.
6. One resume bullet using action + scope + result.
7. A 30-second summary.
8. A one-minute answer that can naturally support follow-up questions.

Make the user the subject only for directly owned actions. Use “the team” for
shared outcomes. Do not inflate verbs or create numbers.

## Review and Save

Show the draft and list every non-confirmed sentence. Offer the smallest
questions needed to resolve them. Save only after approval by appending to:

`<vault>/chronicle/projects/<project-id>/STAR.md`

Use `<plugin-root>/templates/project/STAR.md`. Let `<plugin-root>` be
`${CLAUDE_PLUGIN_ROOT}` when Claude Code supplies it; otherwise use the
directory two levels above this `SKILL.md`. Preserve existing stories and avoid
duplicates with the same competency, event, and evidence set. Mark the story
`draft` until its critical claims are confirmed; mark it `reviewed` only after
user review.

Report the saved path, status, target competency, and remaining evidence gaps.