star-stories — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited star-stories (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
For mock interviews or curating which stories to lead with for a specific role, use interview-prep. STARify produces the raw material; interview-prep selects and rehearses it.
After STARifying a project (or batch of projects), suggest the user run /interview-prep in audit mode to refresh the competency index, or in cheat-sheet mode if there's an upcoming round the new stories should feed.
$PERSONAL is the personal-docs sibling directory defined in CLAUDE.md. Resolve it once at the start of the session.
Source documents (read all that exist):
$PERSONAL/career/impact-doc.md — primary source. Has roles, projects, scope, metrics.$PERSONAL/career/brag-doc.md — wins and recognition. Cross-check metrics; brag doc often has sharper numbers.$PERSONAL/career/rish-career.md — narrative framing. Use to recover the why and the struggle behind a project, which often gets compressed out of impact-doc bullets.Or: user-pasted project text. If the user pastes a single project description, skip the file reads and STARify the paste directly.
Triggered by: "STARify my resume", "build STAR stories for everything", "go through all my projects".
$PERSONAL/career/star/<slug>.md using the template below.Triggered by: "STARify [project name]", or user pastes one project's worth of detail.
$PERSONAL/career/star/<slug>.md.Triggered by: "tighten the Agentic Dev Team story", "add a conflict angle to OPEX", "the metric is wrong in trinity-mcp.md".
One file per project. Each file contains:
---
slug: agentic-dev-team
project: Agentic Dev Team
company: Bill
years: 2025-2026
scope: 10-agent SDLC pipeline, adopted across multiple teams
primary_competencies: [leadership, ambiguity, technical-depth, leverage]
---
# Agentic Dev Team
## Context
(2-3 sentences. What was the system, what team, what was the state of the world when you started. Reader should be able to evaluate the rest without back-and-forth.)
---
## Angle 1: Leadership / influence without authority
**Best for:** "Tell me about a time you drove a change without formal authority."
- **Situation:** ...
- **Task:** ...
- **Action:** ...
- **Result:** ...
## Angle 2: Ambiguity
**Best for:** "Describe a time you had to define the problem before solving it."
- **Situation:** ...
- **Task:** ...
- **Action:** ...
- **Result:** ...
## Angle 3: Technical depth / architecture
**Best for:** "Walk me through a technically complex system you designed."
- **Situation:** ...
- **Task:** ...
- **Action:** ...
- **Result:** ...
(Add more angles as the project supports them. A strong project supports 3-5 angles. Don't pad.)
---
## Quick-fire facts (for follow-ups)
- One-line scope:
- Key metrics:
- Who else was involved:
- What I'd do differently:
- Why this matters now:**RESULT-NEEDS-METRIC:** ... and ask the user inline.[VERIFY] and ask. Never fabricate scope, names, or numbers.## Angle X: Conflict — N/A for this project, see [other-project].md instead.$PERSONAL/career/star/<slug>.md. Create the directory if missing.[VERIFY] or RESULT-NEEDS-METRIC flags the user needs to resolve.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.