From career-navigator
Benchmarks the user's pipeline conversion rates, response timelines, ATS scores, and compensation positioning against industry norms segmented by role, level, company size, and geography. Invokes analyst Operation 4.
npx claudepluginhub tmargolis/career-navigator --plugin career-navigatorThis skill uses the workspace's default tool permissions.
Benchmark the user's pipeline performance against industry norms for their role, level, company size, and geography.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Builds scalable data pipelines, modern data warehouses, and real-time streaming architectures using Spark, dbt, Airflow, Kafka, and cloud platforms like Snowflake, BigQuery.
Builds production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. For data pipelines, workflow orchestration, and batch job scheduling.
Benchmark the user's pipeline performance against industry norms for their role, level, company size, and geography.
Read {user_dir}/CareerNavigator/tracker.json. Count the total number of applications (any status). If fewer than 5:
"You need at least 5 applications to run a meaningful benchmark — you have {n} so far. Keep logging applications via
/career-navigator:track-applicationand run this again once you have more history."
Stop here if below threshold.
If ≥5 but fewer than 10 resolved outcomes, proceed with a note that results are preliminary.
Hand off to the analyst agent with:
CareerNavigator/tracker.jsonCareerNavigator/artifacts-index.jsonCareerNavigator/profile.mdUse the output from the analyst to render:
**Benchmark Report** — {today's date}
Data confidence: {Preliminary / Directional / Moderate / High} ({n} applications, {n} resolved outcomes)
PIPELINE CONVERSION
App → Response: {user%} (norm: {low}–{high}% · {above/below/at norm})
Response → Screen: {user%} (norm: {low}–{high}% · {above/below/at norm})
Screen → Interview: {user%} (norm: {low}–{high}% · {above/below/at norm})
Interview → Offer: {user%} (norm: {low}–{high}% · {above/below/at norm})
TIMELINES
Avg days to response: {n} days (norm: {low}–{high} days for {company size mix})
Ghosting rate: {user%} (norm: {low}–{high}% · {above/below/at norm})
ATS SCORES
Avg artifact score: {n}/100 (competitive threshold: 70+ · {above/below})
Lowest artifact: {score} — {filename}
MARKET CONTEXT
{1–2 sentences on geographic competitiveness and role-level supply/demand for user's target}
GAPS TO ADDRESS
{Numbered list of the 1–3 metrics most below norm, with a one-line interpretation each}
STRENGTHS
{1–2 metrics above norm — acknowledge what's working}
If a metric cannot be calculated (e.g., no offers yet, so interview → offer rate is undefined), show — and note why.
Based on the lowest-performing metric:
/career-navigator:resume-score against your weakest-performing artifact."/career-navigator:pattern-analysis to see which ExperienceLibrary units are in stalled applications."/career-navigator:track-application to ensure follow-ups are scheduled."/career-navigator:ats-optimization to surface the highest-impact fixes on your active artifacts."