Predictive Intelligence for ServiceNow — auto-categorization, similarity and clustering
Use ServiceNow Predictive Intelligence from the agent: sn_ml.ClassificationPredictor for auto-categorization, SimilarityPredictor for related records, ClusteringPredictor, model training/retraining, and prediction-feedback accuracy tracking
- What
- Use ServiceNow Predictive Intelligence from the agent: sn_ml.ClassificationPredictor for auto-categorization, SimilarityPredictor for related records, ClusteringPredictor, model training/retraining, and prediction-feedback accuracy tracking
- Cost
- Free
- Needs
- a ServiceNow instance (free Personal Developer Instance for dev; licensed instance for production); the Serac agent tooling environment configured (snow_* tools)
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @serac-labs's predictive-intelligence skill, listed here with credit to its creator: a developer playbook for driving ServiceNow Predictive Intelligence from an agent — configuring classification solutions (the `ml_solution` table: target field, input fields, capability type), getting predictions with `sn_ml.ClassificationPredictor` (predicted value, confidence, top predictions), auto-applying classifications to records, using `SimilarityPredictor` to find related records and `ClusteringPredictor` to group related items, plus regression and recommendation capabilities, model training/retraining flows, and prediction-feedback accuracy tracking. It documents the key tables (`ml_solution`, `ml_solution_definition`, `ml_capability_definition`, `ml_model`, `ml_prediction_result`) and the available agent tools (snow_query_table, snow_execute_script, snow_ml_predict, snow_list_pi_solutions, snow_train_pi_solution). Honest caveats: everything here runs inside a ServiceNow instance — you need one to use it (ServiceNow offers a free Personal Developer Instance for dev work; production requires a licensed instance) — and the agent tools it references assume the Serac skill/tooling environment is configured; classification models trained on your incident data need periodic retraining and feedback tracking to stay accurate, and auto-applying predictions to production records can change live data — review before enabling. Apache-2.0 licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: a ServiceNow instance (free Personal Developer Instance for dev; licensed instance for production); the Serac agent tooling environment configured (snow_* tools) Install "Predictive Intelligence for ServiceNow — auto-categorization, similarity and clustering" for me. It gives my agent @serac-labs's playbook for ServiceNow Predictive Intelligence: configuring classification solutions, getting and applying predictions via sn_ml.ClassificationPredictor, similarity and clustering predictors, model training/retraining, and prediction-feedback accuracy tracking — with the key ml_* tables and the available snow_* tools. Apache-2.0 licensed. Repository: https://github.com/serac-labs/serac/blob/main/packages/skills/predictive-intelligence/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). The skill's scripts run against a live ServiceNow instance — verify every query pattern targets expected tables and that instance credentials never appear in code. This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "predictive-intelligence". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. configure my ServiceNow instance access via the vault — never paste credentials into the skill, set up the Serac snow_* tooling, and decide whether predictions are applied automatically or reviewed first — auto-apply changes live data). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.