From idmp-plugin
IDMP analysis skill for listing, searching, reading, resuming, and preparing analysis create flows with path, trigger type, sub-template, and output-attribute checks.
How this skill is triggered — by the user, by Claude, or both
Slash command
/idmp-plugin:idmp-analysisThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Read [`../idmp-shared/SKILL.md`](../idmp-shared/SKILL.md) first.**
Read ../idmp-shared/SKILL.md first.
Before any write: Follow the 🛑 Destructive op confirmation protocol. Read-only commands stay read-only here, but delete / write / patch flows still require the shared yes-gate.
| Shortcut | Purpose |
|---|---|
+list | Read analyses under one element. |
+search | Search analyses globally, including an empty-keyword starting point. |
analysis read flows../idmp-workflow-analysis-create/SKILL.md../idmp-workflow-alert-create/SKILL.md| Context | Why it must be resolved before create or resume |
|---|---|
| Final owner and mode | You need the exact elementId or elementTemplateId before you can choose the right command family or reserve a name. |
| Business root | Element-mode analysis creates still need rootElementId from the business root, even when the real owner moves to a data-bearing leaf. Prove that root with element elements path plus element fullpath get before you send the create payload. |
| Candidate analysis name | analysis.analyses.new-name and analysis-template.analyses.new-name require a candidate name. |
| Trigger scope | You need to know applyOnSelf, child-template scope, and which trigger type is valid after that choice. |
| Output plan | Decide whether to reuse or create output attributes, which valueType they need, and whether they land on self or child scope. |
| Runtime target | Decide whether Ready is acceptable or whether the final workflow must end in Running and therefore needs resume. |
POST /api/v1/ai/analysis/create for natural-language analysis or alert intents, then persist the returned draft through the normal create path. Use the structured DTO workflow as the fallback when the draft is unsuitable or persistence fails.analysis.analyses.new-name and analysis-template.analyses.new-name require a candidate name and --ack-risk; do not call them with only the owner scope.rootElementId comes from the business root rather than the current leaf element.trigger-types list is empty on the current owner.applyOnSelf=false, the backend can legitimately expose only Session and Interval, so do not assume DataInput or Event will stay available.rootElementId, startAfterCreated, a valid trigger, and real output.attributes[].attrId values. For current live ELE_SUBET flows, child-scope analyses can use owner-element output attributes while output.elementTemplate.id continues to point at the child template.get, list, and, when needed, resume prove the backend kept the object in the expected runtime state.resume prove the analysis itself worked, classify leaked output-attribute cleanup as a backend boundary instead of a wrong create payload.../idmp-workflow-alert-create/SKILL.md instead of treating it as a generic read or create flow.create reread shows the same name on the persisted object.analysis analyses get and analysis analyses list show the same id, owner scope, and expected state bits.Ready; reread after resume and confirm the runtime state actually changed.rootElementId was part of the write path, keep the element elements path and element fullpath get evidence with the create proof.path, attributes, sub-templates, trigger-types, and new-name before create or edit.analysis.analyses.new-name and analysis-template.analyses.new-name require a candidate name and --ack-risk; do not call them with only the owner scope.rootElementId from the business root, not the current element.../idmp-workflow-analysis-create/SKILL.md, especially when the payload must include output.attributes[].applyOnSelf and, for child scope, the selected template.resume it if the expected state is running.idmp-cli schema analysis.analyses.list
idmp-cli analysis analyses list --params '{"elementId":123,"current":1,"size":20}'
idmp-cli schema analysis.analyses.get
idmp-cli analysis analyses get --params '{"elementId":123,"id":456}'
idmp-cli schema analysis.analysis.search
idmp-cli analysis analysis search --params '{"keyword":"voltage","current":1,"size":20}'
idmp-cli analysis analyses new-name --ack-risk --params '{"elementId":123,"name":"demo-analysis"}'
idmp-cli analysis trigger-types list --params '{"elementId":123,"applyOnSelf":true}'
idmp-cli analysis trigger-types list --params '{"elementId":123,"applyOnSelf":false,"elementTemplateId":456}'
idmp-cli schema analysis.analyses.resume
idmp-cli analysis analyses resume --ack-risk --params '{"elementId":123,"id":456}'
trigger-types list changes after applyOnSelf or the child template changes, discard the earlier trigger choice and re-read it.Session or Interval, redesign the analysis around those trigger families or move back to self scope; do not force Event or DataInput.rootElementId is known. Treat “resolved” as element elements path plus element fullpath get agreeing on the same first-level owner.attribute elements attributes-delete still reports the output attribute is referred by the analysis, classify that as a backend cleanup boundary after you have already captured the create or running proof; stop retrying generic cleanup loops.get still shows an unexpected state, verify with list and then use resume instead of sending another create.id from a different element or template scope.idmp-cli schema analysis.analyses.list and idmp-cli analysis analyses list --params '{"elementId":123,"current":1,"size":20}'.idmp-cli analysis analyses get --params '{"elementId":123,"id":456}'.idmp-cli analysis analysis search --params '{"keyword":"voltage","current":1,"size":20}'.idmp-cli element elements path --params '{"elementId":123}' and idmp-cli element fullpath get --params '{"rootElementId":100,"elementId":123}', then validate create prerequisites with idmp-cli analysis analyses new-name --ack-risk --params '{"elementId":123,"name":"demo-analysis"}' and idmp-cli analysis trigger-types list --params '{"elementId":123,"applyOnSelf":false,"elementTemplateId":456}'.idmp-cli analysis analyses create --dry-run --ack-risk --params '{"elementId":123}' --data '{...}', then prove the runtime branch with idmp-cli analysis analyses get --params '{"elementId":123,"id":456}', idmp-cli analysis analyses list --params '{"elementId":123,"current":1,"size":20}', and idmp-cli analysis analyses resume --dry-run --ack-risk --params '{"elementId":123,"id":456}'.npx claudepluginhub taosdata/agent-skills --plugin idmp-pluginGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.