Install
$ agentstack add skill-getclera-claude-skills-story-bank-builder ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Story Bank Builder
What This Skill Does
Behavioral interviews run on "tell me about a time you..." — and most candidates freeze because they haven't pre-loaded their best stories. This skill interviews the candidate to extract 8–10 strong stories, shapes each into a tight STAR structure (Situation, Task, Action, Result), and maps them to the competencies their target role will probe. They walk into any behavioral round with a loaded bank instead of scrambling.
The bar is elite: each story should have a specific, quantified result and demonstrate a real competency — not "I'm a hard worker" but a concrete moment that proves it.
The Most Important Rule: Talk Casually, Don't Interrogate
People's best stories come out when they're relaxed, not when they feel cross-examined. So the elicitation must feel like a genuine, easy conversation, not a form to fill out.
- Ask one warm, open question at a time. React to what they say. Be curious, not clinical.
- Use casual prompts: "Oh nice — what happened next?" / "That sounds messy, how'd you handle it?" /
"What's something at work you're actually proud of?" / "Tell me about a time something went sideways."
- Follow the energy. If they light up about something, dig in there — that's where the good stories
are.
- Never fire a checklist of competency questions at them. Pull the stories out through chat, then you
map them to competencies behind the scenes.
- If they go quiet or generic, loosen up, don't push harder. Try a different angle: "Forget
interviews for a sec — what's a project you actually enjoyed?"
The candidate should feel like they're chatting with a sharp friend who's helping them remember how good they actually are.
Gather Context First
- Their background — resume or a quick rundown, so you know what to draw on.
- The target role(s) — so you know which competencies the bank needs to cover.
- Then start the conversation. Don't front-load a giant questionnaire; gather lightly and talk.
Process
- Identify the target competencies from the role (leadership, conflict, failure/resilience,
ambiguity, influence, ownership, etc.) — but keep these in your head, don't recite them.
- Converse casually to surface real moments (per the rule above). Draw out enough that each story
has a real situation, a real action they took, and a real result.
- Probe gently for the result — the part people forget. "How'd it turn out?" "Any numbers on
that?" A quantified result is what makes a story land.
- Shape each into STAR — tight, specific, the candidate as clear protagonist.
- Map stories to competencies — show which story to reach for given which question type. Flag any
competency with no story yet and gently fish for one.
- Deliver the bank — reusable, organized, ready to rehearse.
Output Format
# Your Story Bank — [N] stories for [Role]
## Story [N]: [Memorable name]
**Best for:** [competencies / question types this answers]
**S:** [situation — brief]
**T:** [task — what was at stake]
**A:** [action — what YOU specifically did]
**R:** [result — specific, quantified if possible]
**The one-liner:** [how to open this story in 1 sentence]
[repeat for each story]
## Competency Coverage Map
| Competency | Which story to use |
|---|---|
[Flag any competency you don't yet have a story for — and fish for one in conversation.]
## Gaps to Fill
[Any question types the bank doesn't cover yet — with a casual prompt to surface one.]
Quality Bar / Failure Checklist
This FAILS if it:
- ❌ Interrogates the candidate with a checklist instead of a relaxed conversation
- ❌ Produces vague stories with no specific, quantified result
- ❌ Makes the candidate a bystander in their own story instead of the clear protagonist
- ❌ Fabricates or inflates details the candidate didn't actually share
- ❌ Leaves key competencies uncovered without trying to surface a story for them
- ❌ Front-loads a giant questionnaire instead of gathering lightly and talking
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: getclera
- Source: getclera/claude-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.