aimerfan
UserConceptual-grounding Claude skills for Ignition 8.1 and SepaSoft Batch Procedure — anti-hallucination knowledge, not a troubleshooting DB.
Categories
Indexed Skills (7)
ignition-scripting
Author, review, and refactor Inductive Automation Ignition Jython scripts. Use this skill when the user's request involves (1) writing or editing a gateway script (timer, tag-change, message handler, startup, shutdown), (2) writing or editing a Perspective session/view/component event script, (3) writing or editing a Vision client event script, (4) writing or editing a project-library script module (`shared.*` / `project.*`), (5) reviewing a script for scope correctness, threading safety, Jython 2.7 compatibility, or SQL-injection risk, or (6) deciding which scope a piece of logic should live in. This skill is Ignition 8.1+ focused (Jython 2.7); flag version-specific behavior explicitly.
ignition-sql-authoring
Author, review, and tune SQL artifacts for Inductive Automation Ignition projects. Use this skill when the user's request involves (1) authoring a Named Query, (2) designing a table or DDL migration, (3) speeding up a slow query, dashboard, or report, (4) reviewing a Perspective SQL binding or inline scripted SQL, (5) building a historian report against `sqlt_data_*` / `sqlth_te`, (6) writing an EXPLAIN / query-plan verification procedure, (7) refactoring inline SQL to a Named Query, (8) debugging a slow dashboard caused by DB access, (9) choosing between `system.db.runQuery` / `runPrepQuery` / `runNamedQuery` / Query Tag / Named Query, or (10) mapping alarm-journal (`alarm_events`) data into a custom report. Dialect agnostic — supports MSSQL, PostgreSQL, MySQL / MariaDB, Oracle, and SQLite. Dialect confirmation is the first step of the workflow and is non-skippable; no SQL is emitted before the dialect is pinned.
ignition-tag-authoring
Author, review, and refactor Inductive Automation Ignition tags and UDTs. Use this skill when the user's request involves (1) creating or editing tag JSON for any Ignition provider, (2) designing or modifying UDT Definitions or Instances, (3) choosing between OPC / Memory / Expression / Query / Derived / Reference / UDT Instance tag types, (4) mapping PLC register types (S7, Modbus, OPC UA, Allen-Bradley) to Ignition data types, (5) reviewing a tag export for naming, structure, or anti-pattern issues, or (6) generating tag structures from device specs (CSV, I/O lists). This skill is Ignition 8.1+ focused; flag version-specific behavior explicitly.
prp-create
Author a Product Requirements Prompt (PRP) for an Ignition multi-artifact feature. Use when the user asks to "plan", "scope", "structure", or "draft a blueprint" for work that touches more than one Ignition artifact (tags + SQL + views + scripts); use when the user says "before we start building, I want a structured plan"; use when the user names a feature that clearly spans multiple artifact types ("build the production-log dashboard", "replace the hand-written SCADA form with a proper Perspective view backed by a Named Query"); use when the user references PRPs directly ("write a PRP for X", "let's PRP this"). The skill produces a single markdown file at `<project-root>/prp/{slug}.md` following a strict section contract enforced by `scripts/validate_prp.py`. Execution of the PRP is a separate skill (`prp-execution`) — do not start emitting artifacts inside this skill. For single-artifact work (one tag, one query, one script), do NOT use this skill — invoke the domain skill directly. A PRP is overhead until
prp-execution
Execute a previously-authored Product Requirements Prompt against the Ignition framework's domain skills. Use when the user asks to "execute", "run", "build", or "work through" a PRP ("execute prp/production-log-dashboard.md", "let's build the plan", "start the implementation from the PRP", "work through the blueprint"). Use when the user references a PRP file path directly. The skill loads the PRP, validates its structure, plans task execution, delegates each task to the owning domain skill, enforces Level 1 / 2 / 3 validation gates between tasks, and produces a completion report. It does NOT author new PRPs — that's `prp-create`. It does NOT skip the PRP — if the user hasn't written one, redirect. Escalates immediately (stops and asks the user) when: confidence on a task falls below 0.85, Level 1/2 validation fails twice in a row for the same artifact, a cited file or skill is missing, or the PRP contradicts the runtime observation.
ignition-foundations
Conceptual grounding for Ignition 8.1 (SCADA platform by Inductive Automation): system.* scripting API surface, execution scopes, Jython 2.7 behavior, and Perspective. This is a foundation skill — load it whenever a task plausibly touches Ignition: scripting, system.* calls, execution scope, Jython 2.7 / Java interop, tags or UDTs, Perspective bindings/props, expressions, named queries, messaging, or alarms. Loading is cheap and guessing an API signature or scope here is high-risk, so load it eagerly. Read this SKILL.md first; it is an index, not the answer — for any concrete signature, option list, or version-specific behavior, open the relevant references/ file and verify against docs.inductiveautomation.com before answering. Covers 8.1 with 8.1 to 8.3 version-sensitive notes flagged inline.
sepasoft-foundations
Conceptual grounding for the SepaSoft Batch Procedure module on Ignition (MES, ISA-88 batch): ISA-88 four-layer model, system.mes.* API surface, EBR data model, batch lifecycle/state machine, and SepaSoft parameter path syntax. This is a foundation skill — load it whenever a task plausibly touches SepaSoft/MES batch: recipes, phases, batch state, EBR, parameter paths, system.mes scripting, or ISA-88 hierarchy. Loading is cheap and guessing structure or an API here is high-risk, so load it eagerly. Read this SKILL.md first; it is an index, not the answer — for any concrete signature, option list, or version-specific behavior, open the relevant references/ file and verify against docs.sepasoft.com before answering. Based on current stable release with known forward changes flagged inline.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.