galiprandi/job-seeker / .agents/skills/dashboard
dashboard
VerifiedOpens a local web dashboard that visualizes the job application pipeline, funnel stats, recent messages, and target company status. The agent opens it at the end of a round so the user can visually review the pipeline.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.8 KB |
SKILL.md
View on GitHub---
name: dashboard
description: Opens a local web dashboard that visualizes the job application pipeline, funnel stats, recent messages, and target company status. The agent opens it at the end of a round so the user can visually review the pipeline.
trigger: dashboard
---
# Dashboard
## When to open
Open the dashboard at the end of any round that changes the pipeline:
- After `apply` finishes applying to jobs
- After `news` finishes processing updates
- After `daily` completes its routine
- After `targets` finishes registering or applying
- When the user says `dashboard`, "show me the pipeline", "show dashboard"
## How to open
```bash
node scripts/dashboard.js --open
```
This starts a local server at `http://localhost:7531` and opens it in the user's default browser. The dashboard auto-refreshes every 30 seconds.
## What it shows
- **Stats bar**: active count, in-interview count, offers, rejections, closed total
- **Funnel chart**: visual bar chart of pipeline stages (discovered -> hired)
- **Kanban board**: columns for each active stage with cards showing company, role, match level, platform, and date
- **Target companies**: registration status summary (pending, registered, no fit, etc.)
- **Recent messages**: last 10 recruiter/contact messages with channel, sender, subject, and status
## Rules
- Always use `--open` flag so it opens automatically
- If port 7531 is in use, use `--port <alternative>`
- The dashboard is read-only. To move cards, use `scripts/pipeline.js --move <id> <stage>`
- The dashboard auto-refreshes, so the user can keep it open during a session
- Close the dashboard server with Ctrl+C when the session is done
## Script reference
### `scripts/pipeline.js` -- Pipeline kanban board
The kanban board for tracking applications and contacts. Unifies LinkedIn invites, direct emails, and formal applications into a single pipeline with canonical stages.
```bash
# Full board (active cards)
node scripts/pipeline.js
# Include closed (rejected, withdrawn, skipped)
node scripts/pipeline.js --closed
# Funnel summary (counts per stage)
node scripts/pipeline.js --funnel
# Filter by stage
node scripts/pipeline.js --stage interview
# Filter by company
node scripts/pipeline.js --company <company>
# Move a card to another stage (updates status + adds to stage_history)
node scripts/pipeline.js --move 82 interview
# View card detail (with linked messages via application_id)
node scripts/pipeline.js --card 82
```
**Canonical stages (ordered):** `discovered` -> `contacted` -> `applied` -> `in_review` -> `screening` -> `interview` -> `offer` -> `hired`. Closed: `rejected`, `withdrawn`, `skipped`.
**When the agent moves cards:** when it detects a status change (recruiter replies, interview scheduled, rejection), it uses `pipeline.js --move <id> <stage>` instead of a direct UPDATE. This maintains the audit trail in `data.stage_history`.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |