Initial skills documentation — 25 categories, all SKILL.md + references + scripts
This commit is contained in:
root
@@ -0,0 +1,101 @@
|
||||
---
|
||||
name: recurring-information-scout
|
||||
description: "Periodic cron-driven information scanning — search the web for new products, vehicles, competitors, or market entries, cross-reference against a known database, de-duplicate against prior scans, and produce a structured delta report. Designed for weekly/daily cron jobs that keep a reference database fresh."
|
||||
version: 1.0.0
|
||||
author: Sho'Nuff
|
||||
tags: [research, cron, scanning, database-maintenance, periodic, monitoring]
|
||||
---
|
||||
|
||||
# Recurring Information Scout
|
||||
|
||||
Umbrella for cron-driven periodic scanning tasks. Covers the workflow of searching the web for newly announced entities (products, vehicles, competitors, market entries), cross-referencing against a known database, checking what was reported in prior scans, and producing a clean delta report.
|
||||
|
||||
## Triggers
|
||||
|
||||
- Cron job that scans for new vehicles/products/competitors and reports delta
|
||||
- Periodic market scan against a reference database
|
||||
- "Check if anything new appeared since last week"
|
||||
- Database maintenance cron that requires web research to keep fresh
|
||||
|
||||
## Workflow
|
||||
|
||||
### Phase 1: Load Prior Context
|
||||
|
||||
Always start by checking what was found in PREVIOUS scans of this same cron job. This avoids reporting the same vehicle/product twice across runs.
|
||||
|
||||
Use `session_search(query="<cron-job-name> or <topic>", limit=5, sort="newest")` to find recent prior runs. Extract the list of previously-reported items from those sessions to build a de-duplication blocklist.
|
||||
|
||||
**Key technique:** Don't just read the summary — extract the ACTUAL count of items found in each prior run and add them to your de-duplication check.
|
||||
|
||||
### Phase 2: Verify Current Database State
|
||||
|
||||
Read the live database file (JSON, CSV, whatever format) and build a full list of entities already present. This gives you the primary de-duplication set.
|
||||
|
||||
For JSON databases with a pattern like `{Make: {Model: {Year: HP, ...}}}`:
|
||||
```python
|
||||
import json
|
||||
v = json.load(open('/path/to/database.json'))
|
||||
# Check if a specific make/model exists
|
||||
exists = make in v and model in v[make]
|
||||
```
|
||||
|
||||
### Phase 3: Search Fresh Sources (Parallel)
|
||||
|
||||
Batch independent web searches for:
|
||||
- General industry query: `"2025 2026 new [category] [attribute] announced"`
|
||||
- Event-specific queries (e.g., current auto shows, trade events happening this week)
|
||||
- Niche/startup queries for small-volume producers
|
||||
- **Expanded model-year window:** Include BOTH `"2025"` and `"2026"` model years separately. A vehicle announced as a 2025 model in early 2025 won't appear in a "2026 new" search. Run queries for both current and previous model year to catch announcements that aged out of the news window.
|
||||
- **Manufacturer press sites** (e.g., audi-mediacenter.com, lamborghini.com/news, ford.com/performance) — search directly for recent press releases from the OEM's media portal. These often contain confirmations months before automotive press picks them up.
|
||||
|
||||
Use `web_search` (up to 10 results) for each independent angle. Fire them in parallel with a single assistant turn.
|
||||
|
||||
**MCP Exa Search:** When the `mcp__exa__web_search_exa` tool is available (via an Exa MCP server), prefer it over `web_search` for this phase. Exa's semantic search catches niche and boutique manufacturers (Zenvo, McMurtry, Denza) that keyword-based search often misses — it indexes both major press and deep sources. Exa's date-sorted results also help identify which findings are genuinely new vs. old news being recirculated. When using Exa, set `numResults=10` and phrase queries as natural-language descriptions of the ideal page rather than keyword lists.
|
||||
|
||||
### Phase 4: Deep-Dive on Findings
|
||||
|
||||
For each candidate found in Phase 3:
|
||||
1. Extract the specific page with `web_extract` to get confirmed specs
|
||||
2. Verify against the Phase 2 database state — is it REALLY absent?
|
||||
3. Check against the Phase 1 prior-report blocklist — was it already reported but not added?
|
||||
4. Build a structured entry: Make, Model, Year, HP/Spec, Source URL
|
||||
|
||||
### Phase 5: Cross-Reference Prior Reports Against Database
|
||||
|
||||
De-duplication is NOT a single pass. A vehicle reported in a prior run may be:
|
||||
- **Already added to the database** — silently skip (it was caught)
|
||||
- **Still absent from the database** — re-report it with a note that it's been pending since the earlier date
|
||||
|
||||
Use python to iterate the prior reports' known item list against the live database state and flag any that are still missing.
|
||||
|
||||
### Phase 6: Compile and Deliver Report
|
||||
|
||||
Structure the output by:
|
||||
|
||||
1. **New discoveries today** — items found THIS run that were in neither prior reports nor the database
|
||||
2. **Accumulated from prior reports still missing** — items flagged on earlier dates that remain absent from the database
|
||||
3. **Database corrections** — items in the DB with wrong specs that need updating
|
||||
4. **Patterns / recommendations** — trends noticed (e.g., boutique builders appearing, need for "custom" entry option on forms)
|
||||
|
||||
Use a consistent format:
|
||||
```
|
||||
| # | Make | Model | Year | HP | Notes | Source |
|
||||
```
|
||||
|
||||
When the DB needs updating, include specific instructions at the bottom.
|
||||
|
||||
## Pitfalls
|
||||
|
||||
- **session_search de-duplication is approximate** — FTS5 can miss some prior sessions. Always cross-reference at the data level (check the actual database file), not just via search results.
|
||||
- **Prior reports may have missed items that were already in the DB** — always verify each prior-run claim against the actual file before re-reporting it as "still missing."
|
||||
- **Cron context means no user follow-up** — everything you need must be gathered in one pass. You cannot ask "should I add this" so use judgment: report findings clearly and let the user decide.
|
||||
- **News is time-bound** — a Goodwood FoS debuts article published July 9 is only fresh for about a week. Don't report July debuts as new discoveries in August. Use `web_extract` timestamps or search sort by date.
|
||||
- **Small/deep sources matter** — the big auto news sites cover Ferraris and Porsches. Goodwood FoS entry lists, niche hypercar blogs, and Chinese auto shows catch the Zenvo/Denza/McMurtry ones. Don't rely on a single source.
|
||||
- **Deliver findings as the final response, not via send_message** — cron jobs deliver output as the response text. Put the primary content directly in your response.
|
||||
- **When the user isn't present** (cron context), structure the report for mobile-friendly reading — no pipe tables, ASCII-only if the delivery channel is Telegram or phone.
|
||||
|
||||
## Linked Files
|
||||
|
||||
See `references/exotic-vehicle-scout-workflow.md` for the specific implementation of this skill for the Apex Track Experience vehicle database cron job, including the exact de-duplication and cross-referencing patterns used.
|
||||
|
||||
See `references/apex-track-experience-vehicle-db.md` for the vehicle database schema, file locations, and known corrections.
|
||||
+75
@@ -0,0 +1,75 @@
|
||||
# Apex Track Experience Vehicle Database Reference
|
||||
|
||||
## File Locations
|
||||
|
||||
| Copy | Path | Purpose |
|
||||
|------|------|---------|
|
||||
| **Canonical** | `/root/docker/docuseal/data/vehicles.json` | The pretty-printed comprehensive version (~2,277 lines, 47 makes, 373 models) |
|
||||
| **Dev/Mockup** | `/root/portal-mockup/vehicles.json` | Flat-format version used in portal mockups (~234 lines, simpler structure) |
|
||||
| **Live served** | `https://core.itpropartner.com/vehicles.json` | Served via Caddy from `/var/www/static/vehicles.json` — the DocuSeal form fetches this URL |
|
||||
|
||||
## Schema
|
||||
|
||||
```json
|
||||
{
|
||||
"Make Name": {
|
||||
"Model Name": {
|
||||
"YYYY": HP,
|
||||
"YYYY+1": HP
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
- Years are **strings**, not integers (`"2024"` not `2024`)
|
||||
- Makes are capitalized English names: `"Mercedes-AMG"`, `"Gordon Murray Automotive"`
|
||||
- Each model entry lists year-HP pairs; a model existing at one HP doesn't mean it exists at that HP for all years
|
||||
|
||||
## Coverage Rules
|
||||
|
||||
- **Years:** 2015+ for production cars
|
||||
- **Threshold:** 400+ HP (though this scout focuses on 500+ HP for the Apex Track Experience)
|
||||
- **All makes globally** — including Chinese, Korean, boutique
|
||||
- **All body styles** — coupe, sedan, SUV, pickup, convertible, wagon
|
||||
|
||||
## Currently Missing (As of Jul 11, 2026)
|
||||
|
||||
### Entire Makes Not in DB (needs new key added):
|
||||
- Denza (BYD sub-brand, Denza Z at 1,582 hp)
|
||||
- Gordon Murray Automotive (T.33 at 615 hp, T.33 Spider at 607 hp)
|
||||
- Zenvo (Aurora at 1,850 hp)
|
||||
- AC Cars (Cobra GT Coupe at 720 hp)
|
||||
- McMurtry (Speirling Pure at 1,000 hp)
|
||||
- Apollo (Evo at 789 hp)
|
||||
- Ruf (B8 prototype at 1,000+ hp, pre-production)
|
||||
- Sanrivatti (hypercar, 1,000+ hp, startup/development stage)
|
||||
- Toyota (GR GT at 641 hp)
|
||||
- Renault (5 Turbo 3E at 555 hp)
|
||||
|
||||
### Models Missing Under Existing Makes:
|
||||
- Ferrari: 12Cilindri (819hp), 12Cilindri Manuale (819hp), 296 Speciale (869hp), 296 Speciale Aperta (869hp), Amalfi (631hp), 849 Testarossa (1,036hp)
|
||||
- Aston Martin: DB12 S (690hp), DBX S (717hp), Vantage S, Valiant (735hp), Vanquish Volante (824hp)
|
||||
- Pagani: Huayra 70 Derecho (852hp), Utopia Roadster (864hp)
|
||||
- Bentley: Supersports (657hp), Torcal EV SUV (~1,139hp)
|
||||
- Maserati: MC20 GT2 Stradale (631hp), MCPura (621hp)
|
||||
- Mercedes-AMG: PureSpeed (577hp), CLA 45 4Matic+ Electric (680hp), GT 63 S E Performance Coupe 2-door (805hp), GT 4-Door Coupe EV (1,153hp, 2027)
|
||||
- BMW: M5 G90 2025+ (717hp — separate from older 617hp M5), M5 Touring G99 (717hp), iX5, i3 50 xDrive
|
||||
- Porsche: N/A (comprehensive)
|
||||
- GMC: Hummer EV 3X Pickup 2026 (1,160hp — DB has earlier years at 830-1000hp, needs 2026 entry added)
|
||||
- Ford: Mustang GTD (815hp)
|
||||
- Dodge: Charger Daytona Scat Pack EV (670hp), Charger Daytona R/T EV (536hp)
|
||||
- Ram: 1500 TRX SRT 777hp (2027), 1500 SRT Rumble Bee Hellcat (2027)
|
||||
- Cadillac: Lyriq-V (615hp, 2026), Optiq-V (519hp, 2026)
|
||||
- Chevrolet: Blazer EV SS (615hp, 2025), Corvette ZR1X (2027, 1,250hp)
|
||||
- Genesis: G80 Magma (525hp)
|
||||
- Audi: Nuvolari (1,001hp)
|
||||
- Polestar: 6 (884hp)
|
||||
- Jaguar: Type 01 GT (986+ hp)
|
||||
- Hyundai: N Vision 74 (~800hp)
|
||||
- Alfa Romeo: 33 Stradale (620hp gas / 750hp EV)
|
||||
- Bugatti: Tourbillon (1,775hp)
|
||||
- Rimac: Nevera R (2,107hp)
|
||||
- Hennessey: Venom F5-M Evolution (2,031hp — base Venom F5 is in DB at 1,817hp)
|
||||
|
||||
### Spec Corrections Needed:
|
||||
- Aston Martin Valhalla: DB says 998hp → should be 1,064hp
|
||||
+80
@@ -0,0 +1,80 @@
|
||||
# Exotic Vehicle Scout — Implementation Notes
|
||||
|
||||
Specific implementation details for the Apex Track Experience vehicle database cron job.
|
||||
|
||||
## Database
|
||||
|
||||
**Location:** `/root/portal-mockup/vehicles.json` (dev/mockup copy) and `/var/www/static/vehicles.json` (live, served via core.itpropartner.com/vehicles.json)
|
||||
|
||||
**Schema:** `{Make: {Model: {Year: HP, ...}, ...}}`
|
||||
- Makes are top-level keys (capitalized: "Ferrari", "Mercedes-AMG")
|
||||
- Models are sub-keys (capitalized: "296 Speciale", "Mustang GTD")
|
||||
- Years are string keys (not integers): `{"2025": 819, "2026": 819}`
|
||||
- Years span from 2015 onward (the database covers 2015+ per initial requirement)
|
||||
|
||||
**Duplicates exist:** There are TWO copies — `/root/portal-mockup/vehicles.json` (flat format with single-line years, ~234 lines, simpler) and `/root/docker/docuseal/data/vehicles.json` (pretty-printed, ~2,277 lines, comprehensive). The DocuSeal copy is the canonical one.
|
||||
|
||||
## De-duplication Check Pattern
|
||||
|
||||
In Python:
|
||||
```python
|
||||
import json
|
||||
v = json.load(open('/root/portal-mockup/vehicles.json'))
|
||||
|
||||
def is_in_db(make, model):
|
||||
"""Check if a make+model combination exists in the vehicle database."""
|
||||
if make in v:
|
||||
models = v[make]
|
||||
if model in models:
|
||||
return True
|
||||
# Also check partial matches (e.g., 'Mustang GTD' vs 'Mustang GT')
|
||||
matches = [m for m in models.keys() if model.lower() in m.lower()]
|
||||
if matches:
|
||||
return True
|
||||
return False
|
||||
```
|
||||
|
||||
For partial matches, be precise: "Corvette ZR1X" vs "Corvette ZR1" — these are DIFFERENT models. Use python to list ALL models under a make and manually review ambiguous cases.
|
||||
|
||||
## Prior-Report Cross-Reference
|
||||
|
||||
Use `session_search(query="exotic-vehicle-scout", limit=5, sort="newest")` to find prior cron runs. Each run delivers a full report with a table of findings. Extract those findings and check each one against the live DB:
|
||||
|
||||
```python
|
||||
# For each prior report's claimed new-find list:
|
||||
for item in prior_findings:
|
||||
still_missing = not is_in_db(item['make'], item['model'])
|
||||
# If still missing, include in the "accumulated" section
|
||||
```
|
||||
|
||||
## Key Sources for Vehicle Research
|
||||
|
||||
- **Exa Search (MCP via `web_search_exa`)** — best single source for niche/boutique brands (Zenvo, Denza, McMurtry). Semantic search catches what keyword search misses. Returns publication dates for recency filtering. Set `numResults=10`. Use natural-language page descriptions, not keyword lists.
|
||||
- **Goodwood Festival of Speed entry lists** (July, annual) — catches boutique/hypercar debuts
|
||||
- **motor1.com** — good factory-style coverage of all industry events
|
||||
- **CarThrottle** — catches niche/meme-worthy debuts (Ruf B8, Apollo Evo)
|
||||
- **roadandtrack.com / thedrive.com** — performance-focused journalism
|
||||
- **Manufacturer press sites** — for official HP figures (ferrari.com, pagani.com, audi-mediacenter.com, lamborghini.com/news, ford.com/performance)
|
||||
- **carscoops / carnewschina** — Chinese-market vehicles (BYD/Denza, Xiaomi, Nio)
|
||||
- **caranddriver.com/future-cars** — aggregated future vehicle guide
|
||||
|
||||
## Known Model Name Variations
|
||||
|
||||
When checking the DB, you need to account for inconsistencies in model naming:
|
||||
- "Corvette Stingray" != "Stingray" — always use full manufacturer model names
|
||||
- "M5" in DB currently ends at 2024/617hp — the 2025+ G90 generation (717hp) needs separate entries
|
||||
- "GT 63 S 4-Door" is in the DB but "GT 63 S E Performance Coupe" (2-door, 805hp) is NOT
|
||||
- "Ioniq 5 N" vs "IONIQ 5 N" — capitalization differs but python dict check is case-sensitive; check `.lower()` on both sides
|
||||
|
||||
## Apex Track Experience Event
|
||||
|
||||
- Date: September 19, 2026
|
||||
- Invites: Any vehicle 500+ HP regardless of body style or drivetrain
|
||||
- Registration form: DocuSeal-based, fetches make/model from vehicles.json dropdown
|
||||
- Known gaps: "custom/homebuilt" option needed for prototype/low-volume builds
|
||||
|
||||
## Database Corrections (Known)
|
||||
|
||||
- Aston Martin Valhalla: DB says 998 hp, actual is 1,064 hp (1,079 PS)
|
||||
- BMW M5 (G90): 2025+ entries at 717 hp are missing (DB ends at 2024/617hp)
|
||||
- Polestar 6 (884 hp, 2026): missing — DB only has Polestar 1
|
||||
+48
@@ -0,0 +1,48 @@
|
||||
# Session: Jul 11, 2026 — Exotic Vehicle Scout Run
|
||||
|
||||
This was a model run of the `recurring-information-scout` workflow. Key patterns:
|
||||
|
||||
## Batching Strategy
|
||||
|
||||
9 web searches in 3 parallel batches (3 searches each) to maximize coverage:
|
||||
- General "new exotic car announcements July 2026"
|
||||
- "New hypercar/supercar 2026 revealed"
|
||||
- "New performance SUV 2026-2027"
|
||||
- Event-specific: Goodwood FoS 2026 (the main event happening that week)
|
||||
- Chinese market: Denza BYD etc.
|
||||
- Korean market: Genesis Magma
|
||||
- Startup/boutique: McMurtry, Apollo, Sanrivatti
|
||||
|
||||
## Deep-Dive Pattern
|
||||
|
||||
After initial search, extracted Goodwood FoS debuts from Motor1 and CarThrottle (both covered the same event with different niche angles). Cross-referenced:
|
||||
|
||||
1. Motor1: Encyclopedic event entry list with all manufacturers and model names
|
||||
2. CarThrottle: Journalistic writeup with HP figures and quirky details (Ruf B8 flat-eight, Apollo Evo Ferrari V12)
|
||||
3. Manufacturer press sites (Hennessey, Pagani) for exact figures
|
||||
|
||||
## Prior-Session Cross-Reference
|
||||
|
||||
Used `session_search(query="exotic-vehicle-scout", limit=5, sort="newest")` which returned 3 prior runs (Jul 8, 9, 10). Also found a deeper prior session from Jul 5/7 about the initial vehicles.json build. Extracted all claimed missing vehicles from these reports.
|
||||
|
||||
Then ran a Python script to check every claimed missing vehicle against `/root/portal-mockup/vehicles.json`:
|
||||
- 41 vehicles from prior reports still missing
|
||||
- 16 that were already in the DB (either added between runs or mis-classified)
|
||||
- 3 spec corrections needed (Valhalla 998->1064, M5 missing 2025+ generation, Polestar 6 missing entirely)
|
||||
|
||||
## De-duplication Bug
|
||||
|
||||
The prior report from Jul 10 listed 6 vehicles as "new" that were actually already flagged on Jul 9. Without cross-referencing the prior reports against each other, these get double-counted. The Phase 5 step (cross-referencing prior reports) catches this.
|
||||
|
||||
## Goodwood FoS 2026 Timing
|
||||
|
||||
The festival runs July 9-12, 2026. The Jul 11 run caught debuts that were JUST announced on Jul 9-10:
|
||||
- Hennessey Venom F5-M Evolution (Goodwood debut)
|
||||
- McMurtry Speirling Pure production version (Goodwood debut)
|
||||
- Pagani Huayra 70 Derecho (world premiere at Goodwood)
|
||||
- Apollo Evo production version (Goodwood debut)
|
||||
- McLaren 788HS (Goodwood debut)
|
||||
- Zenvo Aurora Tur production prototype (Goodwood debut)
|
||||
- Ruf B8 prototype (Goodwood debut)
|
||||
|
||||
This was the most productive single run because the event concentrated many debuts in one week.
|
||||
Reference in New Issue
Block a user