Trial Readout Analysis logo

Trial Readout Analysis

Community
agentii-ai
trial-readout-analysis

Clinical-trial readout analysis: pull the trial, evaluate the readout with AdCom-style scrutiny (endpoints, statistics, subgroups, missing data, safety, tolerability/persistence), place it in a cross-trial comparison lattice vs SoC and class peers, and size the stock reaction with historical grounding. The judgment core for binary biotech events.

Overview

Publisheragentii-ai
Repositoryagentii-investment-intelligence
Skill nametrial-readout-analysis
Stars
207
Forks
16
Bundled files
2
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by agentii-ai on GitHub. Read the source before you install it.

Installation

Install the Trial Readout Analysis AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/agentii-ai/agentii-investment-intelligence/tree/main/marketplace-beachhead/plugins/bio-pharm/skills/agentii/trial-readout-analysis
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/agentii-ai/agentii-investment-intelligence.git /tmp/agentii-investment-intelligence
mkdir -p .claude/skills
cp -r /tmp/agentii-investment-intelligence/marketplace-beachhead/plugins/bio-pharm/skills/agentii/trial-readout-analysis .claude/skills/trial-readout-analysis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Trial Readout Analysis in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Trial Readout Analysis on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Trial Readout Analysis is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Methodology inspired by publicly taught clinical-trial frameworks; all text is an original paraphrase.

Defaults

ParameterDefault ValueRationale
scrutiny_axesall six + tolerabilitySafety/stats/subgroups/missing data/endpoints/benefit-risk + tolerability/persistence as co-equal axis
lattice_comparatorsSoC + class peersEvery readout is placed against standard of care and same-class peers
safety_imbalancedefer to outcomesSmall-N safety imbalances defer the verdict to a larger outcomes trial
conflict_policymateriality-ratedConflicting readings surfaced verbatim, rated by materiality or deferred
outcome_framingbase/bull/bearBinary readouts need scenario sizing
reaction_contexthistorical casesSize moves from past analogues

Preflight

Run canonical pre-flight per contracts/preflight.md. Include the X-Agentii-Trace header on every tool call per contracts/x-agentii-trace-header.md — carry the _run_id from your first tool result and name yourself (and your parent, if you were spawned).

Triggers

  • "Evaluate [ticker]'s upcoming trial readout."
  • "What should I look for in [trial]'s data?"
  • "Size the readout for [drug] phase 3."
  • "What did the AdCom-style scrutiny say about similar trials?"
  • "Base/bull/bear for [ticker]'s readout."
  • "Which endpoints matter for [trial]?"
  • "How has the market reacted to similar readouts?"
  • "Readout checklist for [ticker]."
  • "Is this trial design adequate?"
  • "What are the red flags in [trial]'s design?"

Production Grounding

  • Readout ≠ approval: phase-3 success is necessary but not sufficient; FDA re-analyzes sponsor data.
  • Apply the six scrutiny axes (safety signals, statistical adequacy, subgroup analyses, missing data, endpoint appropriateness, benefit-risk) plus tolerability/persistence as a co-equal axis — discontinuation rates, dose reductions, and AE-driven dropout often decide commercial uptake. The 道/法 frameworks in references/knowledge-frameworks.md are the authoritative checklist.
  • Cross-trial lattice: every readout is placed against standard of care and same-class peers on aligned endpoints; a readout judged in isolation is incomplete.
  • Safety-imbalance deferral: a safety imbalance seen at readout scale defers the verdict to a larger outcomes trial; never over-weight small-N imbalances.
  • Materiality-rated conflicts: conflicting characterizations of the same data are surfaced verbatim and rated by materiality or deferred — never averaged.
  • Readout framing: readout design, then stock sizing (binary-risk expected value), then historical analogue comparison.

Data Source Priority

  1. search_clinical_trials / get_clinical_trial — design, status, endpoints, dates.
  2. search_documents / read_source_* — sponsor disclosure, prior data cuts.
  3. search_fda_approvals — regulatory history of the drug/program.
  4. Knowledge layer: search_investment_cases(event_type=trial_readout|adcom_vote) + strategies for judgment frameworks.

Methodology

Retrieval Scope

unstructured_document_search

Retrieval Strategy

  1. Pull the trial record (get_clinical_trial by NCT id, or search_clinical_trials by drug/ticker).
  2. Assess design + endpoint quality against scrutiny axes, including tolerability/persistence.
  3. Build the cross-trial lattice: comparator trials for SoC and class peers on aligned endpoints.
  4. Frame base/bull/bear outcomes with sizing; defer safety-imbalance verdicts to outcomes trials where needed.
  5. Ground in historical readout/adcom cases via knowledge tools.

Temporal Scope

See frontmatter temporal_scope block.

Tool Allowlist

See frontmatter allowed_tools.

Protocol

  1. Trial record
  2. Scrutiny-axes assessment (incl. tolerability/persistence)
  3. Cross-trial lattice vs SoC and class peers
  4. Outcome scenarios + sizing
  5. Analogue grounding

Modes

  • Pre-readout (default): design scrutiny + scenario sizing.
  • Post-readout: results evaluation + reaction context.
  • Program view: multiple trials across a program.

Tool Fallbacks

FailureFallback
search_clinical_trials emptyUse filings + press via search_documents; annotate coverage_gap
Trial record thinNote undisclosed fields; do not fabricate
Knowledge tools emptyProceed with structured data + static frameworks

Output File

{ticker}/{YYYY-MM-DD_HHMM}_trial-readout-analysis_{affix}.md

Output Structure

  1. Executive Summary — readout stance in 2-3 sentences
  2. Trial Profile — design, endpoints, status, dates
  3. Scrutiny Assessment — the six axes plus tolerability/persistence, with evidence
  4. Cross-Trial Lattice — aligned endpoints vs standard of care and class peers
  5. Outcome Scenarios — base/bull/bear with sizing; safety-imbalance deferrals flagged
  6. Historical Analogues — cases with /v/ citations
  7. Coverage Gaps — degraded flags

Error Handling

ErrorFallback
NCT id unknownSearch by drug/ticker; flag if unresolved
Endpoints undisclosedFlag explicitly; scrutiny limited to disclosed data
Conflicting readings of the same dataSurface both verbatim; rate materiality or defer to a larger outcomes trial — never average
No comparator data for the latticeMark lattice cells unavailable; flag the gap — do not guess

Memory Load

See contracts/memory-load.md.

Snapshot

See contracts/snapshot-synthesis.md.

Final Summary (TUI)

Include ### Key Citations block with 0-10 clickable /v/ URLs.

References

  • contracts/citation-and-memory.md
  • contracts/output-frontmatter-schema.md
  • contracts/memory-load.md
  • contracts/snapshot-synthesis.md
  • contracts/preflight.md
  • references/knowledge-frameworks.md

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Trial Readout Analysis AI skill do?

Clinical-trial readout analysis: pull the trial, evaluate the readout with AdCom-style scrutiny (endpoints, statistics, subgroups, missing data, safety, tolerability/persistence), place it in a cross-trial comparison lattice vs SoC and class peers, and size the stock reaction with historical grounding. The judgment core for binary biotech events.

Why use Trial Readout Analysis on TypingMind?

Because you install it once and use it with any model. Trial Readout Analysis is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Trial Readout Analysis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agentii-ai/agentii-investment-intelligence/tree/main/marketplace-beachhead/plugins/bio-pharm/skills/agentii/trial-readout-analysis. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Trial Readout Analysis?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Trial Readout Analysis?

As many as you like. As long as a model supports skills, you can use Trial Readout Analysis with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Trial Readout Analysis AI skill free?

Yes. It is published on GitHub by agentii-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇