craft-star
Skill0 starsChanged 4 months agoMITView on GitHub
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.
In this repository7 other files it gives its agents.
- audit-career-evidenceSkill
- capture-sessionSkill
- export-resumeSkill
- initSkill
- quiz-projectSkill
- tilSkill
- update-projectSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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
- Distinctive: line 17
If the target competency is not specified, infer up to three viable options such as technical depth, problem solving, failure and recovery, …
- Very specific: line 24
Use reviewed records and [confirmed] claims for a final story.
- Distinctive: line 37
Ask one high-impact question at a time when ownership, result, or rationale is missing.
- Very specific: line 65
Use <plugin-root>/templates/project/STAR.md.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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:
Situation: concise context, problem, scale, and constraint.Task: the user's responsibility and success criterion.Action: specific actions in decision order, including why, how, alternatives, and collaboration boundaries.Result: observed outcome with confirmed metrics; otherwise give a qualitative result and a missing-evidence note.Learning: what changed in the user's approach and what they would do next.- One resume bullet using action + scope + result.
- A 30-second summary.
- 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.
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
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.

