From career-navigator
Builds and incrementally updates a JSON interview story corpus from journal entries, PKM notes, debriefs, resumes, and related documents for interview prep.
How this skill is triggered — by the user, by Claude, or both
Slash command
/career-navigator:mine-storiesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Create and maintain a persistent interview story corpus so downstream interview skills never need to read full raw journals repeatedly.
Create and maintain a persistent interview story corpus so downstream interview skills never need to read full raw journals repeatedly.
{user_dir} and required pathsUse:
{user_dir}/CareerNavigator/StoryCorpus.json (target corpus){user_dir} (raw source discovery root)If StoryCorpus.json is missing, create it using the schema in step 5.
Scan {user_dir} recursively for likely story-bearing files, prioritizing:
Exclude:
{user_dir}/CareerNavigator/*.jsonIf StoryCorpus.json already exists:
If no prior corpus metadata exists, run full build once.
For each new/changed source:
"Extract any anecdote, decision, challenge, outcome, or project detail from this entry. Output structured JSON."
Each candidate should include:
StoryCorpus.json (Layer 2)Use this top-level shape:
{
"meta": {
"created": "YYYY-MM-DD",
"updated": "YYYY-MM-DD",
"version": "1.0",
"description": "Interview story corpus extracted from user-owned sources for prep and mock interview retrieval."
},
"stories": [
{
"story_id": "story-uuid",
"source": "journal | pkm | debrief | resume | other",
"source_path": "relative/path/to/file",
"source_entry_ref": "date heading or chunk id",
"date": "YYYY-MM-DD",
"raw_summary": "Concise evidence summary from extraction.",
"themes": ["technical_leadership", "crisis_management"],
"competencies": ["problem_solving", "ownership", "cross_functional"],
"result_signal": true,
"ownership_signal": true,
"star_ready": false,
"star": {
"situation": "",
"task": "",
"action": "",
"result": ""
},
"quality": {
"clarity": "low | medium | high",
"specificity": "low | medium | high",
"credibility": "low | medium | high"
},
"embedding": [],
"score_hint": 0.0,
"last_refreshed": "YYYY-MM-DD"
}
],
"source_index": [
{
"path": "relative/path",
"mtime": "ISO-8601",
"status": "processed | skipped",
"last_processed": "ISO-8601"
}
]
}
Merge behavior:
story_id where the same source entry is re-processed.After merge:
Report:
star_readyWhen this runs during launch/setup, suggest running story-retrieval inside prep workflows rather than re-mining.
npx claudepluginhub tmargolis/career-navigator --plugin career-navigatorRetrieves competency-matched interview stories from a persistent corpus for prep and mock interview workflows, returning compact context sets with STAR readiness status.
Personal experience knowledge graph for Claude Code. Build and grow a markdown ontology from Q&A interviews and document ingestion (PDF, DOCX, MD, TXT), then render English resumes, Korean cover letters, and meeting notes from the same vault. Runs entirely on the user's Claude Code subscription — never calls the Anthropic API directly. Activate when the user mentions lockedin by name, asks to set up or update a personal career / experience graph, asks to render a resume / cover letter / meeting note from their own experience, drops a resume PDF or DOCX with a request to absorb it, or queries their own experience ("what projects used Rust?", "which roles taught me X"). Do NOT activate for unrelated coding, code review, or general questions.
Extracts deep context from raw sources like transcripts, documents, and sessions. Builds extraction plans, tracks processed items, discovers people, subjects, patterns, and routes to structured bundles.