@sassoftware/sas-score-mcp-serverjs 1.0.0 → 1.0.1-2

package/.skills/skills/sas-read-strategy/SKILL.md

@@ -1,156 +0,0 @@
----
-name: sas-read-strategy
-description: >
-  Guide the user in choosing the right data retrieval tool: sas-score-read-table (for raw row access with filters)
-  or sas-score-sas-query (for analytical queries, aggregations, joins). Use this skill when the user wants to
-  fetch records from a SAS/CAS table. Trigger phrases include: "read records from", "get data where",
-  "fetch rows from", "query the table", "give me the first N records", "aggregate by", "join tables",
-  or any request that starts with data retrieval.
----
-
-# SAS Read Strategy
-
-Guides the decision between `sas-score-read-table` and `sas-score-sas-query` based on the user's intent and the nature
-of the data operation. Determines which server contains the data and which retrieval tool is most appropriate.
-
-## Determine the server location
-
-Before retrieving data, verify the library and determine which server(s) contain the table:
-
-**Step 1: Verify library existence**
-- Use `sas-find-library-smart` skill to check the library in CAS first, then SAS if needed
-- This establishes the correct server and uppercase convention for SAS libraries
-- Informs the user which server contains the library
-
-**Step 2: Locate the specific table**
-- Use `sas-score-find-table` to check if the table exists in the library
-- Possible outcomes:
-  - If table exists **only in CAS** → set `server: "cas"`
-  - If table exists **only in SAS** → set `server: "sas"`
-  - If table exists **in both** → ask the user: *"The table exists in both CAS and SAS. Which server would you prefer to query from?"*
-  - If table exists **in neither** → inform user and suggest verifying the table name
-
----
-
-## Determine the read strategy
-
-Ask yourself: does the user already have the data in hand?
-
-- **Yes (user pasted values, or data is already in context)** → skip this strategy; data is ready to use.
-- **No** → choose the read tool based on intent:
-
-| User's Intent | Tool | Example |
-|---|---|---|
-| Get specific raw rows, apply simple filter, retrieve first N records | `sas-score-read-table` | "Show me 10 rows from customers where status='active'" |
-| Aggregate/summarize, calculate, join tables, analytical question | `sas-score-sas-query` | "Average salary by department", "Count orders by region" |
-
----
-
-## Using read-table
-
-**When:**
-- User asks for raw records, row-by-row data
-- Simple WHERE filtering (e.g., "where status = 'active'")
-- Pagination needed ("first 50 rows", "next 10 rows")
-
-**How:**
-```
-sas-score-read-table({
-  table: "tablename",
-  lib: "libraryname",
-  server: "cas" or "sas",  // determined from sas-score-find-table check
-  limit: N,        // default 10, adjust based on user request
-  where: "..."     // optional SQL WHERE clause
-})
-```
-
-**Rules:**
-- Always determine the server first using `sas-score-find-table`
-- Keep batch size ≤ 50 rows unless the user explicitly requests more
-- If table name is missing, ask: *"Which table should I read from? (format: lib.tablename)"*
-- If library is missing, ask: *"Which library contains the table?"*
-- If table exists in both servers, ask user which to use
-- Return raw column values; do not transform or aggregate
-
----
-
-## Using sas-query
-
-**When:**
-- User asks for aggregation (SUM, AVG, COUNT, GROUP BY)
-- User asks for joins, calculations, or analytical insights
-- User's question is phrased analytically ("compare", "analyze", "breakdown", "trend")
-
-**How:**
-```
-sas-query({
-  table: "lib.tablename",
-  query: "user's natural language question",
-  sql: "SELECT ... FROM ... WHERE ... GROUP BY ..."  // generated from query
-})
-```
-
-**Rules:**
-- Check which server(s) contain the table using `sas-score-find-table` first
-- If table exists in both CAS and SAS, ask user which to query from
-- Parse the user's natural language question into a PROC SQL SELECT statement
-- Ensure SELECT statement is valid SQL syntax
-- Do not add trailing semicolons to the SQL string
-- If table name is missing, ask: *"Which table should I query? (format: lib.tablename)"*
-- If the intent is unclear, ask for clarification: *"Do you want raw rows, or an aggregated summary?"*
-
----
-
-## Common patterns
-
-**Pattern A — Raw row retrieval**
-> "Show me the first 5 rows from Public.customers"
-
-→ `sas-score-read-table({ table: "customers", lib: "Public", limit: 5 })`
-
-**Pattern B — Filtered retrieval**
-> "Get all high-value orders (amount > 5000) from mylib.orders"
-
-→ `sas-score-read-table({ table: "orders", lib: "mylib", where: "amount > 5000" })`
-
-**Pattern C — Aggregation**
-> "What is the average price by make in Public.cars?"
-
-→ `sas-score-sas-query({ table: "Public.cars", query: "average price by make", sql: "SELECT make, AVG(msrp) AS avg_price FROM Public.cars GROUP BY make" })`
-
-**Pattern D — Join + analysis**
-> "Show me total sales by customer in the sales and customers tables"
-
-→ `sas-score-sas-query()` with a JOIN in the generated SQL
-
----
-
-## Error handling
-
-| Problem | Action |
-|---|---|
-| Library not found | Use `sas-find-library-smart` skill to verify the library exists |
-| Table not found in either server | Inform user and suggest checking the table name |
-| Table exists in both CAS and SAS | Ask: *"The table exists in both servers. Which would you prefer: CAS or SAS?"* |
-| Table exists only in one server | Use that server automatically in your request |
-| Table name missing entirely | Ask: *"Which table should I read from?"* |
-| Ambiguous intent (raw vs aggregate) | Ask: *"Do you want individual rows or a summary by some field?"* |
-| Empty result | Inform user, ask to adjust filter or query |
-
----
-
-## Integration with other skills
-
-- **Before this skill**: Use `sas-find-library-smart` to verify and locate the library
-- **After this skill**: Use `sas-read-and-score` to score the retrieved data
-
----
-
-## Next steps
-
-Once data is retrieved, typical follow-ups include:
-- **Visualize** — present as table or chart
-- **Export** — format and offer download
-- **Analyze further** — ask clarifying questions
-- **Score** — run predictions on the data
-- **Combine** — join with other datasets

package/.skills/skills/sas-request-classifier/SKILL.md

@@ -1,69 +0,0 @@
----
-name: sas-request-classifier
-description: Classify ambiguous SAS or Viya requests before using MCP tools. Use when prompts mention jobs, code, models, scoring, CAS tables, content, or resources and the correct SAS domain is not yet clear.
----
-
-# SAS Request Classifier
-
-Use this skill to determine what kind of SAS object, workflow, or environment the user is referring to before selecting tools.
-
-## When to use
-Use this skill when the request contains ambiguous domain terms such as:
-- model
-- score
-- scoring
-- read
-- query
-- job
-- jobdef
-- code
-- table
-- content
-- asset
-- resource
-
-Use this skill before any execution-oriented tool call if there is a chance the request is referring to the wrong SAS domain.
-
-## Goal
-Map the user request to the most likely SAS domain and hand off to the correct downstream skill or tool path.
-
-## Classification targets
-Classify the request into one or more of these categories:
-- Reading or querying tables → Route to **sas-read-strategy**
-- CAS resource, caslib, or table discovery → Route to **sas-find-library-smart** or **sas-list-tables-smart**
-- SAS data, libref, or table discovery → Route to **sas-find-library-smart** or **sas-list-tables-smart**
-- Score model or scoring artifact → Route to **sas-score-workflow**
-- Read data and score together → Route to **sas-read-and-score**
-- SAS job or flow execution
-- SAS code or program analysis
-- General content or metadata lookup
-- Environment, auth, or connectivity issue
-
-## Procedure
-1. Read the request and identify ambiguous nouns and verbs.
-2. Infer whether the request is asking to discover, inspect, execute, deploy, score, compare, or troubleshoot.
-3. Decide the most likely SAS domain and matching skill.
-4. If confidence is low, ask one focused clarifying question.
-5. If confidence is high, load and use the relevant skill:
-   - **sas-find-library-smart** — Find CAS or SAS libraries
-   - **sas-list-tables-smart** — Browse tables in a library
-   - **sas-read-strategy** — Choose read-table vs. sas-query for data retrieval
-   - **sas-read-and-score** — Combine data reading with model scoring
-   - **sas-score-workflow** — Route scoring requests to correct execution engine
-6. Only after classification and skill guidance, use MCP tools.
-
-## Disambiguation hints
-- "Run" often implies job execution, but may also mean scoring or model invocation. Check for "score" or "model" context.
-- "Model" may refer to MAS models, SAS jobs, jobdefs, or SCR models. Look for context or type suffix (e.g., `.job`, `.mas`, `.scr`).
-- "Score" may refer to model scoring or job execution. Look for model name or context.
-- "Table" usually suggests CAS, but confirm library name and server context.
-- "Find", "list", "browse" — starts as discovery. Route to sas-find-library-smart or sas-list-tables-smart.
-- "Read", "query", "fetch" — data retrieval. Route to sas-read-strategy.
-- "Predict", "score records", "run model on data" — combined workflow. Route to sas-read-and-score or sas-score-workflow.
-
-## Output
-When you finish classification, state:
-- the inferred SAS domain
-- the confidence level
-- the relevant skill(s) to load
-- any remaining ambiguity or clarifying questions needed

package/.skills/skills/sas-score-workflow/SKILL.md

@@ -1,314 +0,0 @@
-gi ---
-name: sas-score-workflow
-description: >
-  Guide the full model scoring workflow: validate model familiarity, route to appropriate scoring tool 
-  based on model type, invoke scoring with scenario data, and present merged results. Use this skill 
-  when the user wants to run predictions on data (already fetched or user-supplied). Supports generic 
-  syntax: "score with model <name>.<type> scenario =<params>" where type is job|jobdef|mas|scr|sas.
-  Trigger phrases: "score these records", "predict using model", "run model on", "score with model X.mas".
----
-
-# SAS Score Workflow
-
-Orchestrates model validation, type-based routing, scoring invocation, and result presentation. 
-Handles both MAS models and alternative scoring engines (jobs, jobdefs, SCR, SAS programs).
-
----
-
-## Generic Scoring Syntax
-
-Users can invoke scoring with a unified syntax that automatically routes to the correct tool:
-
-```
-score with model <name>.<type> [scenario =<key=value pairs>]
-score <name>.<type> [scenario =<key=value pairs>]
-```
-
-**Type determines the routing:**
-- `.job` → route to `sas-score-run-job` with scoring parameters
-- `.jobdef` → route to `sas-score-run-jobdef` with scoring parameters
-- `.mas` → route to `sas-score-model-score` (Model Analytical Service — default)
-- `.scr` → route to `sas-score-scr-score` (SAS Container Runtime)
-- `.sas` → route to `sas-score-run-sas-program` to run sas program in folder
-
-If no type is specified (bare model name), assume `.mas` (MAS model).
-
----
-
-## Type-Based Routing
-
-### Parse and Strip Model Type
-
-When a user provides a model name with a type suffix (e.g., `simplejon.job`, `churn.mas`):
-
-1. **Extract the type:** Split on the last dot to identify the type suffix
-   - `simplejon.job` → type = `job`, base name = `simplejon`
-   - `churn.mas` → type = `mas`, base name = `churn`
-   - `fraud_detector.jobdef` → type = `jobdef`, base name = `fraud_detector`
-
-2. **Validate the type:** Confirm it matches one of the supported types: `job`, `jobdef`, `mas`, `scr`, `sas`
-   - If type is unrecognized, assume `.mas` (default MAS model) and treat the entire input as the model name
-
-3. **Strip the type suffix:** Remove the `.type` from the model name before passing to the routing tool
-   - **Critical:** Always pass the base name (without the dot and type) to the invoked tool
-   - `simplejon.job` → pass `simplejon` to `sas-score-run-job`
-   - `churn.mas` → pass `churn` to `sas-score-model-score`
-   - `fraud_detector.jobdef` → pass `fraud_detector` to `sas-score-run-jobdef`
-
-### Type: `.mas` (Model Aggregation Service)
-- **Tool**: `sas-score-model-score`
-- **Use for**: Standard MAS-deployed predictive models
-- **Example**: `score with model churn.mas scenario =age=45,income=60000`
-- **Invocation**: `sas-score-model-score({ model: "churn", scenario: {...} })`
-
-### Type: `.job` (SAS Viya Job)
-- **Tool**: `sas-score-run-job`
-- **Use for**: Pre-built scoring jobs with parameters
-- **Example**: `score with model monthly_scorer.job scenario =month=10,year=2025`
-- **Invocation**: `sas-score-run-job({ name: "monthly_scorer", scenario: {...} })`
-
-### Type: `.jobdef` (SAS Viya Job Definition)
-- **Tool**: `sas-score-run-jobdef`
-- **Use for**: Job definitions that perform scoring logic
-- **Example**: `score with model fraud_detector.jobdef using amount=500,merchant=online`
-- **Invocation**: `sas-score-run-jobdef({ name: "fraud_detector", scenario: {...} })`
-
-### Type: `.scr` (Score Code Runtime)
-- **Tool**: `sas-score-scr-score`
-- **Use for**: Models deployed in SCR containers (REST endpoints)
-- **Example**: `score https://scr-host/models/loan.scr using age=45,credit=700`
-- **Invocation**: `sas-score-scr-score({ url: "https://scr-host/models/loan", scenario: {...} })`
-
-### Type: `.sas` (SAS Program / SQL)
-- **Tool**: `sas-score-run-sas-program`
-- **Use for**: Custom SAS or SQL scoring code
-- **Example**: `score my_scoring_code.sas using x=1,y=2`
-- **Invocation**: `sas-score-run-sas-program({ folder: "my_scoring_code", scenario: {...} })`
-
-
-
----
-
-## Scenario Parsing
-
-The scenario parameter (comma-separated key=value pairs) is parsed into an object:
-
-```
-scenario =age=45,income=60000,region=South
-  ↓ parsed as:
-{ age: "45", income: "60000", region: "South" }
-```
-
-Accepted formats:
-- **String**: `age=45,income=60000`
-- **Object**: `{ age: 45, income: 60000 }`
-- **Array** (batch): `[ {age:45, income:60000}, {age:50, income:75000} ]`
-
----
-
-## Integration with other skills
-
-- **Before scoring table data**: Use `sas-find-library-smart` to verify the library, then `sas-read-strategy` to fetch records
-- **For read + score workflows**: Use `sas-read-and-score` for the complete end-to-end pattern
-
----
-
-## Step 1 — Check model familiarity before scoring
-
-Score immediately if:
-- The user names a specific model they've used before in this session, OR
-- The model name matches a previously confirmed model in the conversation
-
-Pause and suggest investigation if:
-- The model name is new, vague, or misspelled-looking (e.g. "the churn one", "that cancer model")
-- The user seems unsure of the required input variable names
-
-**Suggested message:**
-> "I don't recognize that model — want me to run `find-model` to confirm it exists,
-> or `model-info` to check its required inputs first?"
-
----
-
-## Step 2 — Prepare the scenario data
-
-**For a single record** (one object):
-```javascript
-scenario = { field1: value1, field2: value2, ... }
-```
-
-**For batch scoring** (multiple records — the typical case):
-```javascript
-scenario = [
-  { field1: val1, field2: val2, ... },
-  { field1: val3, field2: val4, ... },
-  ...
-]
-```
-
-**Critical rules:**
-- Loop or call sas-score-model-score **once per row**.
-- Field names in the scenario must match the model's expected input variable names **exactly**.
-  - If table column names differ from model input names, **flag this to the user** and ask for confirmation before scoring.
-  - Example: Table has `age_years`, but model expects `age` → ask user which column maps to which input.
-- Do not add units, labels, or extra metadata — raw field values only.
-
----
-
-## Step 3 — Invoke the appropriate scoring tool
-
-Based on the type extracted from the model name, invoke the corresponding tool:
-
-**For `.mas` (default):**
-```javascript
-sas-score-model-score({
-  model: "<modelname>",
-  scenario: scenario,  // object or array
-  uflag: false         // set true if you need field names prefixed with _
-})
-```
-
-**For `.job`:**
-```javascript
-sas-score-run-job({
-  name: "<jobname>",
-  scenario: scenario
-})
-```
-
-**For `.jobdef`:**
-```javascript
-sas-score-run-jobdef({
-  name: "<jobdefname>",
-  scenario: scenario
-})
-```
-
-**For `.scr`:**
-```javascript
-sas-score-scr-score({
-  url: "<scr_endpoint_url>",
-  scenario: scenario
-})
-```
-
-**For `.sas`:**
-```javascript
-sas-score-run-sas-program({
-  src: "<sas_or_sql_code>",
-  scenario: scenario
-})
-```
-
-**Rules:**
-- Pass the full batch in one call; do not loop over rows
-- If scoring fails, return the structured error and suggest troubleshooting
-- For MAS models, include uflag parameter if underscore-prefixed output is needed
-- For jobs/jobdefs, scenario becomes parameter arguments
-- For SCR, include full URL endpoint
-
----
-
-## Step 4 — Present the results
-
-Merge the scoring output back with the input records and present as a table where possible.
-
-**Always surface:**
-- The key prediction/score field(s) (e.g. `P_churn`, `score`, `prediction`, `P_risk`)
-- Any probability/confidence fields for classification models (e.g. `P_class0`, `P_class1`)
-- Selected input fields that drove the prediction, so the user can see context
-
-**Formatting:**
-- Present results in a table for clarity
-- If results exceed 10 rows, show the first 10 and ask: *"Want to see more results or export the full set?"*
-- Round numeric predictions to 2–4 decimal places for readability
-
----
-
-## Common flows
-
-**Flow A — Score rows with MAS model**
-> "Score the first 10 customers in Public.customers with the churn model"
-
-1. `sas-score-read-table` → { table: "Public.customers", limit: 10 }
-2. `sas-score-model-score` → { model: "churn", scenario: [ ...10 row objects ] }
-3. Present merged results with prediction + key inputs
-
-**Flow B — Score with a scoring job**
-> "Score December sales with the monthly_scorer job using month=12,year=2025"
-
-1. `sas-score-run-job` → { name: "monthly_scorer", scenario: { month: "12", year: "2025" } }
-2. Capture job output and tables
-3. Present results
-
-**Flow C — Score with a job definition**
-> "Run fraud detection jobdef on transaction amount=500, merchant=online"
-
-1. `sas-score-run-jobdef` → { name: "fraud_detection", scenario: { amount: "500", merchant: "online" } }
-2. Capture log, listings, and tables
-3. Present results
-
-**Flow D — Score with SCR endpoint**
-> "Score with the loan model at https://scr-host/models/loan using age=45, credit_score=700"
-
-1. `sas-score-scr-score` → { url: "https://scr-host/models/loan", scenario: { age: "45", credit_score: "700" } }
-2. Capture prediction response
-3. Present result
-
-**Flow E — Score results of an analytical query with MAS**
-> "Score high-value customers (spend > 5000) in mylib.sales with the fraud model"
-
-1. `sas-score-sas-query` → { table: "mylib.sales", sql: "SELECT * FROM mylib.sales WHERE spend > 5000" }
-2. `sas-score-model-score` → { model: "fraud", scenario: [ ...result rows ] }
-3. Present merged results
-
-**Flow F — User supplies scenario data directly**
-> "Score age=45, income=60000, region=South with the churn model"
-
-1. Skip read step
-2. `sas-score-model-score` → { model: "churn", scenario: { age: "45", income: "60000", region: "South" } }
-3. Present result
-
-**Flow G — Model unfamiliar, need to confirm**
-> "Score Public.applicants with the creditRisk2 model"
-
-1. Pause — "creditRisk2" is new
-2. Suggest: `find-model` to confirm it exists, `model-info` to get input variables
-3. Once confirmed → `sas-score-read-table` + `sas-score-model-score`
-
-**Flow H — Generic score syntax with type routing**
-> "score with model churn.mas scenario =age=45,income=60000"
-> "score fraud_detector.jobdef where scenario =amount=500"
-> "score monthly_report.job using month=10,year=2025"
-
-1. Parse model name to extract type (.mas, .job, .jobdef, .scr, .sas)
-2. Route to appropriate tool based on type
-3. Parse scenario and invoke tool with parameters
-4. Present results from routed tool
-
----
-
-## Error handling
-
-| Problem | Action |
-|---|---|
-| Model not found | Suggest `find-model` to verify the model is deployed |
-| Input field name mismatch | Show the mismatch (table has X, model expects Y), ask user to confirm mapping |
-| Scoring error / invalid inputs | Return structured error, suggest `model-info` to check required inputs and data types |
-| Empty read result | Tell user, ask if they want to adjust the query/filter before scoring |
-| Missing input fields | Ask which table columns map to the required model inputs |
-
----
-
-## Tips
-
-- **Batch is better:** Always pass the full set of records in one `sas-score-model-score` call. Do not loop.
-- **Confirm mappings:** If column names don't match model inputs, ask before scoring.
-- **Show context:** Include key input columns in the result output so predictions make sense.
-- **Limit output:** For large result sets (>10 rows), ask before showing all.
-
----
-
-## Integration with other skills
-
-- **Before scoring table data**: Use `sas-find-library-smart` to verify the library, then `sas-read-strategy` to fetch records
-- **For read + score workflows**: Use `sas-read-and-score` for the complete end-to-end pattern