> ## Documentation Index
> Fetch the complete documentation index at: https://docs.appliedaifoundation.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> Reusable capabilities that extend agents — collectors, analyzers, and tools across maritime operations, documents, and reporting.

<Frame caption="Skills overview — collectors gather evidence, analyzers turn it into senior reviews, document tools index the corpus, utilities support reports and intelligence.">
  <img src="https://mintcdn.com/metaweaveconsultant/dljHqUb9Dh2JKdTD/images/hero/skills-overview-whitepaper.png?fit=max&auto=format&n=dljHqUb9Dh2JKdTD&q=85&s=61e212ddf426115d1a9e1047d116b13b" alt="Skills overview showing the four-category architecture — collectors, analyzers, document tools, and reports / utilities — with the collector → analyzer → review flow" style={{ width: '100%', height: 'auto', display: 'block', borderRadius: '8px' }} width="1672" height="941" data-path="images/hero/skills-overview-whitepaper.png" />
</Frame>

## What skills are

Skills are modular, reusable capabilities that agents invoke to do real work. Each skill packages a workflow — what it reads, what it produces, when to use it — into a portable unit any agent can call. The same skill works equally well for a senior agent reviewing a vessel and a human operator running a one-off check.

The library currently has 44 skills grouped into four areas: **collectors** that gather evidence, **analyzers** that turn that evidence into senior reviews, **document tools** that index and search the maritime knowledge base, and **utilities** for reports, images, and intelligence queries.

## How skills compose

Most maritime work follows a two-stage pattern:

1. A **data collector** fetches the latest evidence for a vessel domain (engine telemetry, certificates, defects, etc.) and files it as a timestamped, append-only record.
2. An **analyzer** reads that evidence, runs a deterministic analysis script, and produces a senior expert review with prioritised actions and an escalation decision.

Splitting the two means analyses are reproducible (re-runnable without re-fetching), auditable (every number traces to evidence), and cheap to operate (collection is a database query, analysis is one model call).

## Categories

### Collectors — gather evidence

Per-vessel data collectors that snapshot a single domain:

* [AE Performance](/skills/ae-performance-data-collector), [ME Performance](/skills/me-performance-data-collector), [ME Microapp](/skills/me-performance-microapp-data) — engine telemetry
* [Fuel Oil](/skills/fuel-oil-data-collector), [Lube Oil](/skills/lube-oil-data-collector), [Water Treatment](/skills/water-treatment-data-collector) — fluids and chemistry
* [Certificates](/skills/certificates-data-collector), [Class Society](/skills/class-society-data), [Compliance](/skills/compliance-data-collector) — regulatory and class
* [Crew](/skills/crew-data-collector), [PMS](/skills/pms-data-collector), [Defects](/skills/defect-data-collector) — manning and maintenance
* [Voyage](/skills/voyage-data-collector), [Purchase](/skills/purchase-data-collector), [Financial](/skills/financial-data-collector), [Forms](/skills/forms-data-collector) — operations and admin
* [CII / Emissions](/skills/cii-emissions-microapp-data) — emissions microapp evidence with screenshots

### Analyzers — produce senior reviews

Senior agents that turn collector evidence into TSI-grade reviews with escalation logic:

* [AE Performance](/skills/ae-performance-analyzer), [ME Performance](/skills/me-performance-analyzer) — engine reviews with SFOC variance, blackout risk, overhaul timing
* [Fuel Oil](/skills/fuel-oil-analyzer), [Lube Oil](/skills/lube-oil-analyzer), [Water Treatment](/skills/water-treatment-analyzer) — fluid and chemistry reviews
* [Certificates](/skills/certificates-analyzer), [Class Society](/skills/class-society-analyzer), [Compliance](/skills/compliance-analyzer) — detention-risk and compliance
* [Crew](/skills/crew-analyzer), [PMS](/skills/pms-analyzer), [Defects](/skills/defect-analyzer) — manning, maintenance, defect reviews
* [Voyage](/skills/voyage-analyzer), [Purchase](/skills/purchase-analyzer), [Financial](/skills/financial-analyzer), [Forms](/skills/forms-analyzer) — operations, procurement, budget reviews

### Documents & knowledge

Tools that turn the maritime corpus into searchable, citable knowledge:

* [Search Indexed Documents](/skills/search-indexed-documents) — search circulars, IMPA, IMO, manuals with exact-quote evidence
* [PDF to Markdown](/skills/pdf-to-markdown) — bulk convert PDFs to searchable markdown with embedded page images
* [PDF Vision Extractor](/skills/pdf-vision-extractor) — high-accuracy tiled extraction for diagrams and tables
* [Download Flag Circulars](/skills/download-flag-circulars), [Download Makers Circulars](/skills/download-makers-circulars) — keep the corpus current
* [Vessel Intelligence](/skills/vessel-intelligence) — query and write observations, notes, and learnings linked to cases
* [Outlook Email Sync](/skills/outlook-email-sync) — sync mailbox into a searchable local index

### Reports & utilities

Cross-cutting tools used during inspections, investigations, and reporting:

* [Maritime Report Generator](/skills/maritime-report-generator) — turns inspection photos + vessel data into polished VIR / Owner's / Incident reports
* [QHSE Investigation Report](/skills/qhse-investigation-report) — cross-domain Quality, Health, Safety, Environment investigation
* [Image Analysis](/skills/image-analysis) — vessel-mode equipment classification or general-mode description
* [Image Generator](/skills/image-generator) — AI image generation
* [Validate Consumption Log Data](/skills/validate-consumption-log-data) — pre-upload data quality check for CII, EU MRV, IMO DCS, FuelEU

## How a typical review flows

```
User asks "How are the AEs on POSUN?"
        │
        ▼
ae-performance-data-collector
   fetches telemetry, files evidence
        │
        ▼
ae-performance-analyzer
   runs analysis script
   writes senior review
   decides escalation
        │
        ▼
   ┌────┴────┐
   │         │
   OK     Escalation
            │
            ▼
   tsi-review picks up the case
```

The same pattern applies across every domain — engines, certificates, crew, voyages, finance — which means anyone reviewing fleet status sees the same shape of evidence regardless of who or what produced it.

## Why script-driven analysis

Pattern detection, threshold logic, and cost calculation all live in deterministic analysis scripts — not in the language model. The model interprets results into a narrative review; it doesn't recompute. Reviews stay **consistent across vessels**, **auditable** (every number traces to source evidence), and **cheap to run**.
