← TTMNG Pharmaceutical assistCONTENT HISTORY
WHAT CHANGED
Update to TTMNG Pharmaceutical assist
Snapshot Oct 24, 2026 · 13:39 UTC · version 1.4.0
Collection source: downloaded plugin package.
First saved snapshot
No earlier snapshot is available to establish a change.
Save TTMNG Pharmaceutical assist and check future changes in Following.
Up to 10 plugins free · no card required.
Compare saved observations
Download comparison JSONFull technical diff · 0 changed fields
Full snapshot data
{
"description": "Read and explain current TTMNG foreign medicine evidence across all 243 selected families, with exact products, source citations, original conditions and recorded research through the authenticated project service.",
"included_files": [],
"name": "inspect-medicine",
"skill_md_contents": "---\nname: inspect-medicine\ndescription: Read and explain current TTMNG foreign medicine evidence across all 243 selected families, with exact products, source citations, original conditions and recorded research through the authenticated project service.\n---\n\nUse the current project tools, beginning with `ttmng_reference_catalog` kind=medicine and its page cursor. It covers all 243 selected families, with exact required targets and separately labelled supporting products. Select the exact reference_id/presentation_id from the catalog. Preserve ingredient/salt/strength basis, form, route, jurisdiction and identifier. Do not transfer a source to another formulation or use a Thai product as a current foreign target.\n\nRead `ttmng_reference_answer` and follow next_offset when the requested scope needs further pages. Use `ttmng_evidence_record` for exact record_ids and `ttmng_evidence_batch` for bounded groups of independent reads. For an actual evidence question, use `ttmng_evidence_question` with the exact selection and relevant topic. Inspect the returned facts, original conditions, citations and recorded research before proposing any new search. Request only an indispensable unresolved product/context choice; no extra source, name, chemistry, release or repeated clinical approvals.\n\nLead with what the sources support and cite their exact dated versions. Preserve population, route, dose/formulation, renal/study/withdrawal limits, negative results, source conflicts and missing fields. A source-labelled regimen is reference evidence, not a patient-specific prescription or dose-adjustment instruction. Do not infer latest whole-PI coverage, current market stock, interchangeability, co-use safety or an unrecorded pathway from a family completion count.\n\nWhen the existing evidence answers the question, use it without repeating research. For a real remaining gap, inspect recorded search scope/outcomes first and use available host primary-source tools if appropriate. The remote reader itself performs no new searches or canonical writes; state tool/access limits and do not claim new results were saved or reviewed. Historical ALTACE/LUPIN context retains its own conditions and never substitutes for the required TRIATEC France target.\n\nAll data calls require server-side approved access. Provisioned OpenAI reviewers have permanent account entitlement; ordinary users require owner approval. Never request passwords in chat, trust caller role flags, read private authoring files or invoke legacy 1.2 tools. `ttmng_reference_status` reports this release's actual counts/date and disabled legacy data dispatch.\n"
}SHA-256 of public snapshot: a0245cb4a7baf05c524ce6998ae1c6e0c7697b11295d256627254489226b9036